{"schema_version":1,"generated":"2026-10-19","items":[{"id":"morluto-rea--build-similar-feature-for-my-project","t":"Rebuild a feature you saw, in your own project","s":"Have your agent study a feature in an app, then write and test a version for your codebase.","w":"Solo founder who wants a comparable feature in their product after studying how another app does it","o":"A working implementation in your project, grounded in what the agent observed in the target app.","c":"Software & DevOps","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/build-similar-feature-for-my-project/","b":true,"f":true,"sc":0.738},{"id":"morluto-rea--inspect-web-player-from-browser","t":"Map how a website's front end behaves","s":"Let your agent inspect a site's page structure, scripts and network calls and explain what the client does.","w":"Frontend developer curious how a web app wires its UI to its scripts and requests","o":"A summary of the page structure, scripts and observed network requests for the site.","c":"Software & DevOps","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/inspect-web-player-from-browser/","b":false,"f":true,"sc":0.727},{"id":"morluto-rea--learn-how-app-feature-works","t":"Learn how a feature in another app works","s":"Point your agent at an installed app and get an explanation of one feature, with the evidence behind it.","w":"Indie developer who likes a feature in a desktop app and wants to understand how it is built","o":"A written explanation of how the feature works, with the evidence listed and unknowns flagged.","c":"Software & DevOps","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/learn-how-app-feature-works/","b":false,"f":true,"sc":0.69},{"id":"morluto-rea--explain-game-wasm-build","t":"Pull apart a game's web build","s":"Use your agent to inspect a game's WASM web build and surface what it contains.","w":"Hobbyist or modder who wants to know how a cross-platform game's web build is put together","o":"A decoded view of the WASM imports, exports and sections, plus the agent's notes on what they suggest.","c":"Security & Science","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/explain-game-wasm-build/","b":false,"f":true,"sc":0.61},{"id":"morluto-rea--replay-saved-network-capture","t":"Understand traffic from a saved HAR or SAZ file","s":"Feed a saved network capture to your agent to see requests, responses and the payloads they expose.","w":"Developer debugging how an app talks to its server using a capture they already recorded","o":"A readable breakdown of requests, responses and exposed payloads tied to source locations.","c":"Software & DevOps","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/replay-saved-network-capture/","b":false,"f":false,"sc":0.586},{"id":"morluto-rea--analyze-electron-app-directory","t":"List modules and IPC in an Electron app","s":"Run one command on an extracted Electron app or ASAR to see its modules, imports and process boundaries.","w":"Developer vetting or learning from an Electron desktop app they have installed","o":"A JSON report of modules, imports, Electron boundaries and the evidence for each.","c":"Security & Science","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/analyze-electron-app-directory/","b":false,"f":false,"sc":0.573},{"id":"morluto-rea--decode-unity-il2cpp-metadata","t":"List types and methods in a Unity game","s":"Decode a Unity IL2CPP metadata file to see assembly images, type names and method names.","w":"Game modder or QA engineer who needs the class and method names in a shipped Unity game","o":"A list of assembly images, types and methods with index ranges from the metadata file.","c":"Security & Science","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/decode-unity-il2cpp-metadata/","b":false,"f":false,"sc":0.488},{"id":"morluto-rea--understand-native-binary-behavior","t":"Get readable pseudocode from a native binary","s":"Connect your agent to Hopper, Ghidra or IDA and ask what a native program's function does.","w":"Engineer inheriting an old compiled tool whose source is lost, needing to know what one routine does","o":"Pseudocode, strings, symbols and call references for the routine, explained in plain words.","c":"Security & Science","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/understand-native-binary-behavior/","b":false,"f":true,"sc":0.48},{"id":"morluto-rea--audit-android-apk-manifest","t":"Check what an Android APK declares and does","s":"Inspect an APK's manifest, classes and decompiled methods to see what the app declares.","w":"IT admin or security reviewer vetting an Android app before approving it for staff devices","o":"A report of manifest declarations, classes and decompiled methods you can review.","c":"Security & Science","r":"morluto/rea","rs":"morluto-rea","u":"/use-cases/morluto-rea/audit-android-apk-manifest/","b":false,"f":false,"sc":0.421},{"id":"google-research-harness2--audit-which-harness-edits-actually-stuck","t":"Audit which harness edits were adopted and why","s":"Read the adopted harnesses and reflection notes from a run to learn which prompt or tool edits drove a gain.","w":"Agent builder who wants to copy the winning edits into a hand-maintained harness instead of re-running refinement","o":"A short list of concrete edits (system prompt, guardrails, memory, tool guidance and so on) with their stated evidence, ready to port by hand.","c":"Software & DevOps","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/audit-which-harness-edits-actually-stuck/","b":true,"f":true,"sc":0.727},{"id":"google-research-harness2--try-self-improving-agent-demo-no-keys","t":"Watch an agent improve its own setup in 5 minutes, no API key","s":"Run the built-in demo to see both recursion modes edit a harness with real Python executions and zero credentials.","w":"Curious developer who saw Harness2 trending and wants proof it runs before investing in setup","o":"A runs/demo folder showing parallel and sequential recursion with deterministic editors, produced locally in seconds.","c":"Software & DevOps","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/try-self-improving-agent-demo-no-keys/","b":false,"f":true,"sc":0.725},{"id":"google-research-harness2--improve-office-web-code-agent-workbuddy","t":"Boost an office, web or coding agent on WorkBuddy tasks","s":"Refine an agent's harness on one WorkBuddy-Bench subset to see if office, web or code results improve.","w":"Builder of an internal assistant that edits documents, browses, or writes code and wants a measurable harness upgrade","o":"A judged WorkBuddy run for one subset showing whether a Propose-Probe-Compose step beat the base harness.","c":"Software & DevOps","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/improve-office-web-code-agent-workbuddy/","b":false,"f":true,"sc":0.645},{"id":"google-research-harness2--test-harness-refinement-on-legal-tasks","t":"Test whether harness edits lift your agent on legal tasks","s":"Run one LAB legal-work task with refinement, then judge and report, to see if edits beat the base harness.","w":"Legal-tech engineer whose agent drafts antitrust or competition analysis and who wants evidence that prompt and tool edits help","o":"A judged and reported result for one LAB task, with the adopted harness and reflection notes saved under runs/.","c":"Software & DevOps","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/test-harness-refinement-on-legal-tasks/","b":false,"f":false,"sc":0.542},{"id":"google-research-harness2--benchmark-agent-harness-without-answer-leaks","t":"Run a clean benchmark with network limits against rubric leaks","s":"Lock down network access before evaluating so an agent cannot look up public benchmark answers.","w":"Researcher reporting harness-improvement numbers who must show the agent could not read public rubrics","o":"A benchmark run done under network restrictions, giving numbers you can defend as not contaminated by leaked grading criteria.","c":"Research & Knowledge","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/benchmark-agent-harness-without-answer-leaks/","b":false,"f":true,"sc":0.532},{"id":"google-research-harness2--compare-parallel-vs-sequential-recursion","t":"Compare parallel and sequential refinement on the same task","s":"Run the same benchmark task in both recursion modes to pick the cheaper or stronger refinement strategy.","w":"ML engineer deciding how to spend an agent-refinement compute budget on a recurring task type","o":"Two reports for the same task, one per mode, that you can compare side by side to choose a strategy.","c":"Research & Knowledge","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/compare-parallel-vs-sequential-recursion/","b":false,"f":false,"sc":0.513},{"id":"google-research-harness2--swap-codex-executor-into-agent-loop","t":"Run harness refinement with the Codex executor","s":"Switch from the default OpenCode executor to Codex to see how the executor changes refined-harness results.","w":"Developer who already uses Codex as a coding agent and wants harness improvements tuned to that executor","o":"A refinement run on Codex whose results are stored separately so you can compare it against an OpenCode run.","c":"Software & DevOps","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/swap-codex-executor-into-agent-loop/","b":false,"f":false,"sc":0.493},{"id":"google-research-harness2--resume-interrupted-multi-task-refinement-run","t":"Resume a long refinement run after it stops midway","s":"Re-issue the same command to continue a multi-task run without redoing finished tasks.","w":"Researcher running a larger JobBench or LAB sweep that was interrupted by a crash or quota limit","o":"A completed run that picked up where it stopped, with results kept under the same runs directory.","c":"Research & Knowledge","r":"google-research/harness2","rs":"google-research-harness2","u":"/use-cases/google-research-harness2/resume-interrupted-multi-task-refinement-run/","b":false,"f":false,"sc":0.462},{"id":"debpalash-voicestudio--replace-paid-cloud-voice-service-locally","t":"Replace a paid cloud voice tool with a free local one","s":"Install the desktop app and generate cloned or designed voices on your own computer with no subscription or upload.","w":"Solo creator paying monthly for a cloud voice-cloning service and uneasy about uploading voice recordings","o":"A working local app that turns typed text into speech in a cloned or designed voice, with nothing leaving your machine.","c":"Content & Creative","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/replace-paid-cloud-voice-service-locally/","b":true,"f":true,"sc":0.76},{"id":"debpalash-voicestudio--dub-video-into-another-language","t":"Dub a video into another language with timed speech","s":"Feed a video to the dubbing workspace and get a translated voice track that lines up with the original timing.","w":"YouTuber or course maker who wants one video to reach viewers in another language","o":"A dubbed version of the video with speech timed to the original, made locally.","c":"Content & Creative","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/dub-video-into-another-language/","b":false,"f":true,"sc":0.734},{"id":"debpalash-voicestudio--let-an-agent-call-local-voice-api-or-mcp","t":"Give your AI agent a local text-to-speech tool through MCP","s":"Expose the local API and MCP server so a coding or chat agent can generate speech on demand.","w":"Developer building an agent workflow that needs to speak or produce voiceovers without a paid API","o":"An agent that calls your local VoiceStudio to produce audio files on request.","c":"Software & DevOps","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/let-an-agent-call-local-voice-api-or-mcp/","b":false,"f":true,"sc":0.71},{"id":"debpalash-voicestudio--run-voice-work-on-a-laptop-without-a-gpu","t":"Run voice generation on an older laptop with no graphics card","s":"Use the CPU build to clone and generate voices on hardware without a dedicated GPU, trading speed for access.","w":"Student or hobbyist on an older laptop who wants to try local voice AI without buying a GPU","o":"A working, if slower, local voice setup on integrated graphics or an older PC.","c":"Software & DevOps","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/run-voice-work-on-a-laptop-without-a-gpu/","b":false,"f":true,"sc":0.703},{"id":"debpalash-voicestudio--turn-a-manuscript-into-an-audiobook","t":"Turn a finished manuscript into an audiobook","s":"Use the audiobook workflow to render a long text into narrated audio with your chosen voice.","w":"Self-publishing author with a finished manuscript and no budget for a narrator","o":"A narrated audiobook rendered locally from the manuscript text.","c":"Content & Creative","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/turn-a-manuscript-into-an-audiobook/","b":false,"f":true,"sc":0.694},{"id":"debpalash-voicestudio--design-a-new-voice-from-a-description","t":"Design a brand-new voice from a text description","s":"Describe the voice you want and generate it, with no reference recording needed.","w":"Indie game developer or narrator who needs a distinct character voice and has no actor","o":"A usable generated voice that fits the character, produced locally.","c":"Content & Creative","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/design-a-new-voice-from-a-description/","b":false,"f":false,"sc":0.581},{"id":"debpalash-voicestudio--batch-voiceovers-with-recipes-and-watch-folders","t":"Batch-produce voiceovers from a watched folder","s":"Use reusable recipes and watch folders to render many scripts to audio without manual clicks.","w":"Content team producing weekly narration for dozens of short scripts","o":"Scripts dropped into a folder come out as finished audio using a saved recipe.","c":"Content & Creative","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/batch-voiceovers-with-recipes-and-watch-folders/","b":false,"f":false,"sc":0.577},{"id":"debpalash-voicestudio--transcribe-recordings-and-dictate-offline","t":"Transcribe interviews and dictate text without the cloud","s":"Run transcription and the floating dictation widget locally so recordings and speech stay on your machine.","w":"Journalist or researcher with sensitive interview audio that cannot go to a cloud transcriber","o":"Text transcripts of your audio, plus dictated text, produced entirely on your own hardware.","c":"Research & Knowledge","r":"debpalash/VoiceStudio","rs":"debpalash-voicestudio","u":"/use-cases/debpalash-voicestudio/transcribe-recordings-and-dictate-offline/","b":false,"f":false,"sc":0.567},{"id":"wheresryan22-anatomy--vet-a-new-agent-skill-before-installing","t":"Read and sandbox a brand new skill before you install it","s":"Follow the habit seen in the field of checking a fresh repo's scripts before running an unknown skill.","w":"Cautious developer about to install a viral agent skill from a days-old repo","o":"A checked install where you have read the install scripts and hooks and ran it in an isolated environment first.","c":"Security & Science","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/vet-a-new-agent-skill-before-installing/","b":true,"f":true,"sc":0.809},{"id":"wheresryan22-anatomy--build-an-interactive-network-explainer","t":"Publish an interactive explainer of how a network works","s":"Turn a technical flow, like a message hopping across a radio mesh, into an animated page people can explore.","w":"Community organizer or maintainer who wants newcomers to understand how their network moves a message","o":"A public interactive explainer page, in more than one language if you ask for it.","c":"Software & DevOps","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/build-an-interactive-network-explainer/","b":false,"f":true,"sc":0.706},{"id":"wheresryan22-anatomy--explain-a-process-to-a-client-visually","t":"Show a client how a process works with a 3D figure","s":"Replace a long written explanation with a rotatable, clickable figure of the process.","w":"Consultant or architect who struggles to explain a process to a client in words","o":"An interactive figure the client can rotate and click through, shared as an HTML page.","c":"Work & Operations","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/explain-a-process-to-a-client-visually/","b":false,"f":true,"sc":0.688},{"id":"wheresryan22-anatomy--explain-how-a-machine-works-interactively","t":"Turn a one-line question into a clickable machine cutaway","s":"Ask your agent how an engine or lock works and get an interactive isometric figure you can hover, click and pull apart.","w":"Curious learner or teacher who wants to see how a real machine works after reading a trending post","o":"A standalone interactive HTML page showing the machine in cutaway, with parts you can inspect and a live readout.","c":"Research & Knowledge","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/explain-how-a-machine-works-interactively/","b":false,"f":true,"sc":0.678},{"id":"wheresryan22-anatomy--visualize-a-product-or-vehicle-teardown","t":"Draw a teardown of a product from its public specs","s":"Describe a vehicle or device and its spec numbers, and get an exploded isometric figure with live values.","w":"Tech blogger or hobbyist who read a launch claim and wants a visual explainer of what is inside","o":"An interactive isometric figure of the device with its main parts, built from the specs you supply.","c":"Content & Creative","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/visualize-a-product-or-vehicle-teardown/","b":false,"f":true,"sc":0.627},{"id":"wheresryan22-anatomy--design-an-isometric-ui-for-a-small-app","t":"Give a hobby app an isometric machine-style interface","s":"Use the skill's look to design the interface of a small control panel, like a web remote.","w":"Hobbyist building a small web remote or dashboard who wants a distinctive visual style","o":"A web interface where controls look like parts of an isometric machine, built with the skill's shading and camera.","c":"Games & Hobbies","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/design-an-isometric-ui-for-a-small-app/","b":false,"f":true,"sc":0.62},{"id":"wheresryan22-anatomy--export-a-figure-as-svg-or-react","t":"Export an explainer figure as SVG or React components","s":"Generate a figure once and ship it as a lone SVG file or React and Next.js components.","w":"Frontend developer adding an interactive diagram to a docs site or landing page","o":"A figure delivered as an SVG file with embedded styles, or as React components you drop into your site.","c":"Software & DevOps","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/export-a-figure-as-svg-or-react/","b":false,"f":false,"sc":0.561},{"id":"wheresryan22-anatomy--make-a-spinnable-3d-part-in-a-figure","t":"Build a figure with a dial or part that turns in 3D","s":"Try the beta 3D mode to get a dial or turntable you can drag and spin.","w":"Tinkerer who wants an explainer where one moving part rotates in true 3D","o":"A figure where the moving parts are re-projected and re-shaded every frame as you drag, like the README's turning dial.","c":"Content & Creative","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/make-a-spinnable-3d-part-in-a-figure/","b":false,"f":false,"sc":0.552},{"id":"wheresryan22-anatomy--explain-a-software-concept-as-a-physical-object","t":"Explain a software concept as a working physical object","s":"Describe a concept like a cache key or rate limiter and get a figure built as a mechanism that behaves the same way.","w":"Developer or technical writer preparing docs or a blog post on an abstract concept such as a token bucket","o":"An interactive figure where a physical mechanism (the README gives a pin-tumbler lock for a cache key) stands in for the concept, ready to embed.","c":"Content & Creative","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/explain-a-software-concept-as-a-physical-object/","b":false,"f":false,"sc":0.52},{"id":"wheresryan22-anatomy--add-fire-water-and-glow-effects-to-a-diagram","t":"Add live fire, water or light effects to a figure","s":"Ask for a figure that needs exhaust, ripples or glow and get WebGL effects inside the isometric drawing.","w":"Educator or designer making a physics or engineering explainer that needs motion effects","o":"A figure whose WebGL layer draws the effect in the same isometric camera as the SVG parts, like the README's engine plume and ripple tank.","c":"Content & Creative","r":"wheresryan22/anatomy","rs":"wheresryan22-anatomy","u":"/use-cases/wheresryan22-anatomy/add-fire-water-and-glow-effects-to-a-diagram/","b":false,"f":false,"sc":0.506},{"id":"stablyai-orca--work-pr-and-linear-tasks-in-worktrees","t":"Turn a GitHub PR or Linear issue into its own agent workspace","s":"Browse PRs, issues and boards inside the app and open a fresh worktree for any task so an agent can start on it.","w":"Developer triaging a backlog who wants each ticket handled in a clean, separate checkout","o":"Each task gets its own worktree and agent, and you review the result without leaving the app.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/work-pr-and-linear-tasks-in-worktrees/","b":true,"f":true,"sc":0.715},{"id":"stablyai-orca--steer-agents-from-your-phone","t":"Get a phone alert when an agent finishes and send follow-ups","s":"Leave agents running on your desktop and use the mobile companion app to check progress and reply from anywhere.","w":"Developer who kicks off long agent runs, then walks away from the desk","o":"Your phone notifies you when an agent finishes, and you send the next instruction without going back to your computer.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/steer-agents-from-your-phone/","b":false,"f":true,"sc":0.709},{"id":"stablyai-orca--run-agents-on-remote-ssh-box","t":"Run agents on a bigger remote machine over SSH","s":"Point Orca at a beefy remote box and run agents there with full editing, git and terminals from your laptop.","w":"Developer whose laptop is too slow or too small to run several agents and their builds at once","o":"Agents work in worktrees on the remote machine while you edit, review and use terminals locally, with reconnects handled for you.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/run-agents-on-remote-ssh-box/","b":false,"f":true,"sc":0.702},{"id":"stablyai-orca--compare-agents-on-one-prompt","t":"Fan one prompt across five agents and merge the best result","s":"Send the same task to several coding agents in isolated worktrees, compare the diffs, and keep the winner.","w":"Developer stuck on a tricky refactor who wants more than one agent's attempt before committing","o":"You get several independent attempts at the same task, each on its own branch, and merge only the one you like.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/compare-agents-on-one-prompt/","b":false,"f":true,"sc":0.683},{"id":"stablyai-orca--annotate-agent-diff-and-send-back","t":"Comment on an agent's diff lines and send fixes back","s":"Leave notes on specific diff lines and ship them to the agent so it fixes exactly what you flagged.","w":"Reviewer who got a mostly right agent change and wants to correct a few lines without retyping context","o":"The agent receives line-level comments, revises the code, and you commit from the same window.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/annotate-agent-diff-and-send-back/","b":false,"f":false,"sc":0.605},{"id":"stablyai-orca--click-ui-element-into-agent-prompt","t":"Point at a UI element and send its HTML and CSS to an agent","s":"Use Design Mode in the built-in browser to click any element and drop its code and a screenshot into your prompt.","w":"Front-end developer fixing a visual bug who cannot easily describe which element is wrong","o":"The agent gets the element's real HTML, CSS and a cropped screenshot, so its fix targets the right code.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/click-ui-element-into-agent-prompt/","b":false,"f":false,"sc":0.574},{"id":"stablyai-orca--let-agents-operate-desktop-apps","t":"Let an agent operate a desktop app when a task needs real clicks","s":"Use Computer Use so an agent can interact with visible desktop UI during a workflow.","w":"Developer whose task requires poking at a native or visual app that has no API","o":"The agent operates the visible UI as part of the workflow and reports what it saw.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/let-agents-operate-desktop-apps/","b":false,"f":false,"sc":0.49},{"id":"stablyai-orca--script-orca-with-agent-driven-cli","t":"Let an agent create worktrees and drive the app via Orca CLI","s":"Use the Orca CLI so an agent can spin up worktrees and click through a UI on its own.","w":"Advanced builder automating a repeatable agent workflow instead of clicking through the app","o":"A script or agent creates worktrees and drives the browser using Orca's own commands.","c":"Software & DevOps","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/script-orca-with-agent-driven-cli/","b":false,"f":false,"sc":0.464},{"id":"stablyai-orca--watch-claude-codex-usage-and-swap","t":"Watch Claude and Codex usage and swap accounts at limits","s":"Track rate-limit resets across your agent accounts and switch accounts without logging in again.","w":"Heavy agent user who keeps hitting subscription limits in the middle of a task","o":"You see usage and reset times in one place and hot-swap to a second account to keep working.","c":"Work & Operations","r":"stablyai/orca","rs":"stablyai-orca","u":"/use-cases/stablyai-orca/watch-claude-codex-usage-and-swap/","b":false,"f":false,"sc":0.447},{"id":"tangency-labs-solidcraft--let-an-ai-agent-model-an-editable-part","t":"Let an AI agent model a part you can still edit","s":"Steer an agent through the built-in MCP server and get a real parametric model, not a mesh you can't fix.","w":"Maker who tried text-to-3D tools and got meshes they could not adjust","o":"You get a feature-timeline model where every dimension is still editable after the agent is done.","c":"Content & Creative","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/let-an-ai-agent-model-an-editable-part/","b":true,"f":true,"sc":0.736},{"id":"tangency-labs-solidcraft--convert-and-inspect-cad-files-between-formats","t":"Open and re-export STEP, STL and 3MF files","s":"Import a model from another tool and export it as STEP, STL, 3MF, glTF or URDF where supported.","w":"Maker handed a model in the wrong format for their printer or viewer","o":"The model opens in SolidCraft and exports in the format your next tool accepts.","c":"Games & Hobbies","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/convert-and-inspect-cad-files-between-formats/","b":false,"f":false,"sc":0.669},{"id":"tangency-labs-solidcraft--study-motion-in-a-small-mechanical-assembly","t":"Check how a small assembly moves before building it","s":"Combine parts with joints and run a motion study to spot interference before you print or machine anything.","w":"Hobbyist designing a hinge, linkage or small mechanism","o":"You see where parts interfere and can fix dimensions before making a physical copy.","c":"Games & Hobbies","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/study-motion-in-a-small-mechanical-assembly/","b":false,"f":false,"sc":0.589},{"id":"tangency-labs-solidcraft--design-a-3d-printable-enclosure-for-a-board","t":"Design a 3D-printable case for a dev board","s":"Follow the README's Raspberry Pi style workflow: dimensioned sketch, shell, standoffs, port cut-outs, then export for printing.","w":"Hobbyist who needs a custom case for a Raspberry Pi or similar board","o":"A parametric case where changing one height value rebuilds the whole part, exported as a printable file.","c":"Games & Hobbies","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/design-a-3d-printable-enclosure-for-a-board/","b":false,"f":false,"sc":0.583},{"id":"tangency-labs-solidcraft--design-sheet-metal-part-and-flat-pattern","t":"Design a bent sheet metal bracket and get its flat pattern","s":"Use flanges, hems and fold/unfold to model a bracket, then read out the flat pattern for cutting.","w":"Small fabricator or hobbyist ordering laser-cut and bent metal parts","o":"A bent sheet metal model with a flat pattern you can send to a cutting service.","c":"Work & Operations","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/design-sheet-metal-part-and-flat-pattern/","b":false,"f":false,"sc":0.571},{"id":"tangency-labs-solidcraft--try-parametric-cad-in-the-browser","t":"Try parametric 3D CAD in your browser, no install","s":"Open the web app, sketch a shape, extrude it and change a dimension to see the model rebuild.","w":"Curious beginner who heard about free CAD and does not want to install anything","o":"You sketch, extrude and resize a simple solid in a browser tab within minutes.","c":"Personal Productivity","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/try-parametric-cad-in-the-browser/","b":false,"f":false,"sc":0.504},{"id":"tangency-labs-solidcraft--watch-an-agent-drive-the-live-cad-app","t":"Watch an agent build a model live in the open app","s":"Connect the MCP server to your running SolidCraft window so you can see each modeling step as the agent makes it.","w":"Builder who wants to supervise an agent instead of trusting a headless run","o":"You watch the agent's commands appear in the app and can stop or correct it mid-build.","c":"Software & DevOps","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/watch-an-agent-drive-the-live-cad-app/","b":false,"f":false,"sc":0.485},{"id":"tangency-labs-solidcraft--batch-build-a-part-from-a-json-script","t":"Generate a STEP file from a JSON command script","s":"Run a saved JSON command list from the CLI so the same part can be rebuilt on demand, no GUI.","w":"Developer or engineer who wants repeatable CAD output in a build pipeline","o":"A text script in git that deterministically produces a STEP file you can hand to a manufacturer.","c":"Software & DevOps","r":"tangency-labs/solidcraft","rs":"tangency-labs-solidcraft","u":"/use-cases/tangency-labs-solidcraft/batch-build-a-part-from-a-json-script/","b":false,"f":false,"sc":0.421},{"id":"rehan-remade-universal-modder--write-up-modding-field-notes","t":"Turn a finished mod into a reusable field note","s":"Record the engine, route, versions and gotchas of your mod and open a pull request so the next agent starts ahead.","w":"Modder who finished a game mod and wants to help the next person avoid the same dead ends","o":"A checked field note in the shared knowledge base with versions, route, verification and gotchas.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/write-up-modding-field-notes/","b":true,"f":true,"sc":0.716},{"id":"rehan-remade-universal-modder--add-custom-items-to-owned-game","t":"Add a custom weapon or boss to a game you own","s":"Describe a new item or boss in plain words and have the agent build it, with art, and test it in the running game.","w":"Terraria player who wants a homing missile launcher and a custom boss but has never written a mod","o":"A working mod with generated sprites, tested in the real game, plus a recorded showcase clip.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/add-custom-items-to-owned-game/","b":false,"f":true,"sc":0.619},{"id":"rehan-remade-universal-modder--record-showcase-video-of-mod","t":"Cut a showcase video of your finished mod","s":"Record the game window with only game audio, pick the best moments and edit a styled clip.","w":"Modder who finished a mod and needs a trailer for Discord or social posts","o":"A short, cut video of the mod running in the real game with clean audio.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/record-showcase-video-of-mod/","b":false,"f":false,"sc":0.597},{"id":"rehan-remade-universal-modder--identify-game-engine-and-prior-mods","t":"Find a game's engine and see if it was modded before","s":"Point the agent at a game folder to get the engine, version, modding route and any existing field notes.","w":"Hobbyist who just bought an older PC game and wants to know whether modding it is realistic","o":"A MODDING_PLAN.md with engine, version, managed or native code, anti-cheat status, save folders and the best known route.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/identify-game-engine-and-prior-mods/","b":false,"f":false,"sc":0.585},{"id":"rehan-remade-universal-modder--mash-up-two-games-into-one","t":"Put one game's content inside another game","s":"Port characters, vehicles or mechanics from one game into a second, like Minecraft mobs in GTA V.","w":"Fan with a mashup idea, such as a Warthog from Halo driving around Minecraft","o":"A playable mashup mod where content from game A runs inside game B, with a showcase video.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/mash-up-two-games-into-one/","b":false,"f":true,"sc":0.576},{"id":"rehan-remade-universal-modder--generate-game-art-3d-and-audio","t":"Make sprites, 3D models and sound for a mod with fal","s":"Generate engine-ready sprites, 3D models, sound effects and music for a mod instead of drawing them by hand.","w":"Solo modder who can code a little but cannot draw or make audio","o":"A set of transparent sprites, rendered 3D headings or audio files sized and named to match the target game.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/generate-game-art-3d-and-audio/","b":false,"f":false,"sc":0.539},{"id":"rehan-remade-universal-modder--port-old-mod-to-newer-version","t":"Port an existing mod to a newer game version or loader","s":"Move a mod from an old Minecraft version or loader to a new one without behavior drifting.","w":"Minecraft mod maintainer whose favorite old mod stopped working after an update","o":"A ported mod built unit by unit from one pinned source, with audits and status docs you can resume.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/port-old-mod-to-newer-version/","b":false,"f":false,"sc":0.506},{"id":"rehan-remade-universal-modder--reverse-engineer-game-file-format","t":"Reverse engineer an unknown game file format","s":"Have the agent decode a proprietary asset or save format and prove it with a round trip.","w":"Tinkerer who wants to swap textures or data in an older game but cannot open its files","o":"A working reader and writer for the format, proven by unpacking and repacking a file and getting the same game behavior.","c":"Games & Hobbies","r":"rehan-remade/universal-modder","rs":"rehan-remade-universal-modder","u":"/use-cases/rehan-remade-universal-modder/reverse-engineer-game-file-format/","b":false,"f":false,"sc":0.483},{"id":"cathrynlavery-diagram-design--architecture-diagram-for-readme","t":"Draw an architecture diagram for your README without a design tool","s":"Describe your app in plain words and get a clean HTML and SVG diagram to drop into your README.","w":"Solo developer about to publish a repo who needs an architecture picture and does not want to open Figma or fight Mermaid","o":"One self-contained HTML file with an architecture diagram (frontend, backend, database, cache) you can open by double-clicking and export as PNG or SVG.","c":"Software & DevOps","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/architecture-diagram-for-readme/","b":true,"f":true,"sc":0.823},{"id":"cathrynlavery-diagram-design--review-plan-diagram-before-coding","t":"Draw the plan before your agent writes the code","s":"Ask for a flow or sequence diagram of a proposed change and approve the design first.","w":"Developer about to hand a multi-step feature to a coding agent who wants to catch design mistakes early","o":"A sequence or flow diagram of the planned change that you read, correct and approve before any code is written.","c":"Software & DevOps","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/review-plan-diagram-before-coding/","b":false,"f":true,"sc":0.79},{"id":"cathrynlavery-diagram-design--visualize-your-agent-setup","t":"Draw your agent setup: tools, data flows and approval points","s":"Diagram which tools your AI agent can call, where data moves and where a human must approve.","w":"Team lead documenting how an internal AI agent is wired before a security or ops review","o":"A diagram showing the agent, its tools, data flows and approval points that can be attached to a review document.","c":"Software & DevOps","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/visualize-your-agent-setup/","b":false,"f":true,"sc":0.786},{"id":"cathrynlavery-diagram-design--map-unfamiliar-repo-for-review","t":"Map an unfamiliar repo's components before you change it","s":"Have your agent read a codebase and draw its parts and connections so you can orient before editing.","w":"Developer joining a project or reviewing a pull request who needs a quick mental map of an unfamiliar repo","o":"A component and data-flow diagram of the repo that you can review with teammates before approving or writing code.","c":"Software & DevOps","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/map-unfamiliar-repo-for-review/","b":false,"f":false,"sc":0.659},{"id":"cathrynlavery-diagram-design--turn-repo-into-explainer-video-with-diagram","t":"Pair diagrams with a video skill to explain a GitHub repo","s":"Use the diagram skill alongside HyperFrames to turn a repo README into a short explainer video.","w":"Maintainer or creator who wants a quick explainer video for a GitHub project without editing footage","o":"A short explainer video for a repo where the architecture scenes come from diagrams drawn by the skill.","c":"Content & Creative","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/turn-repo-into-explainer-video-with-diagram/","b":false,"f":true,"sc":0.639},{"id":"cathrynlavery-diagram-design--match-diagrams-to-your-brand","t":"Make every diagram match your website's colors and fonts","s":"Give the skill your site URL once and every later diagram uses your palette and fonts.","w":"Founder or marketer who needs diagrams for decks, docs and blog posts that look like their own brand","o":"A saved brand profile so each new diagram comes out in your palette and typography without extra prompting.","c":"Content & Creative","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/match-diagrams-to-your-brand/","b":false,"f":false,"sc":0.627},{"id":"cathrynlavery-diagram-design--replace-mermaid-diagrams-with-cleaner-ones","t":"Redraw an old Mermaid or draw.io diagram in a cleaner style","s":"Import an existing Mermaid, draw.io or Excalidraw file and get it back as a polished editorial diagram.","w":"Docs maintainer with a folder of ugly Mermaid or draw.io diagrams in their README and wiki","o":"The same diagrams redrawn in one consistent editorial style, exported as PNG or SVG for the docs.","c":"Content & Creative","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/replace-mermaid-diagrams-with-cleaner-ones/","b":false,"f":false,"sc":0.6},{"id":"cathrynlavery-diagram-design--add-motion-to-ordered-explanations","t":"Add light motion to a diagram that explains steps in order","s":"Turn on optional motion so a process diagram reveals its steps one after another.","w":"Technical writer or educator presenting a process (request flow, pipeline) where order matters","o":"An HTML diagram with optional motion that walks a viewer through the steps in order, with a static version still available.","c":"Content & Creative","r":"cathrynlavery/diagram-design","rs":"cathrynlavery-diagram-design","u":"/use-cases/cathrynlavery-diagram-design/add-motion-to-ordered-explanations/","b":false,"f":false,"sc":0.591},{"id":"yetone-magpie--route-quick-questions-to-cheap-models","t":"Send quick questions to a cheap model and hard tasks to a strong one","s":"Use intent routing so a small model reads each turn and picks the model that fits it.","w":"Developer whose big model gets burned on simple questions like \"what does this do?\"","o":"Simple questions go to a fast model while test-writing and heavier work go to the strong model.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/route-quick-questions-to-cheap-models/","b":true,"f":true,"sc":0.746},{"id":"yetone-magpie--run-codex-on-deepseek-or-kimi","t":"Run your coding agent on a cheaper or different model","s":"Point Codex, Claude Code or Gemini CLI at DeepSeek, Kimi or GLM without hand-editing each agent's config.","w":"Developer who likes Codex or Claude Code but wants to try a cheaper model for everyday edits","o":"One of your installed agents answers on the model you picked, chosen from a searchable list, with its config rewritten safely.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/run-codex-on-deepseek-or-kimi/","b":false,"f":true,"sc":0.704},{"id":"yetone-magpie--fail-over-between-accounts-on-rate-limits","t":"Keep coding when one account hits its rate limit","s":"Group several accounts or models so the gateway quietly moves to the next one when a quota runs out.","w":"Developer with two Claude or ChatGPT accounts who keeps getting cut off mid-task by a 5-hour limit","o":"The agent keeps answering because requests move to the next account or model in your routing group, with no error shown.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/fail-over-between-accounts-on-rate-limits/","b":false,"f":true,"sc":0.704},{"id":"yetone-magpie--point-any-base-url-tool-at-local-gateway","t":"Point any base-URL tool at one local gateway","s":"Aim scripts and apps that take an OpenAI, Anthropic or Gemini base URL at magpie's local address.","w":"Builder with a script or editor tool that reads OPENAI_BASE_URL and wants it to use a different model","o":"The tool sends requests to 127.0.0.1:3425 and gets answers from whichever model magpie routes to.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/point-any-base-url-tool-at-local-gateway/","b":false,"f":false,"sc":0.61},{"id":"yetone-magpie--use-your-chatgpt-plan-in-other-agents","t":"Use a plan you already pay for inside other agents","s":"Let OpenCode or Gemini CLI run on the ChatGPT, Claude or Copilot subscription you are already signed in to.","w":"Developer paying for a ChatGPT or Claude plan who wants those models in a second agent without buying API credits","o":"A second agent runs on the models from your existing subscription, listed as a normal provider.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/use-your-chatgpt-plan-in-other-agents/","b":false,"f":true,"sc":0.606},{"id":"yetone-magpie--save-and-switch-model-profiles-per-task","t":"Switch every agent's model setup with one named profile","s":"Save a Budget or Focus profile and flip all your agents between them in one move.","w":"Developer who runs several agents and changes models by mood, deadline or budget","o":"One command swaps every agent between saved setups, such as a cheap Budget profile and a strong Focus profile.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/save-and-switch-model-profiles-per-task/","b":false,"f":false,"sc":0.59},{"id":"yetone-magpie--import-existing-providers-from-cc-switch","t":"Move your existing provider setup into one app","s":"Import providers from CC Switch, Claude Code, Codex or Alma instead of re-entering every key.","w":"Developer already juggling provider configs across several tools who wants to consolidate","o":"Your existing providers appear in magpie ready to assign to any agent.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/import-existing-providers-from-cc-switch/","b":false,"f":false,"sc":0.576},{"id":"yetone-magpie--add-gemini-or-pi-login-via-npm-plugin","t":"Add a model login through an npm plugin","s":"Install an OpenCode or pi plugin so a sign-in flow becomes a usable provider for your agents.","w":"Advanced user who wants Gemini or Antigravity models that need a plugin-based login","o":"The plugin's models show up in magpie and any agent can run on them like a normal provider.","c":"Software & DevOps","r":"yetone/magpie","rs":"yetone-magpie","u":"/use-cases/yetone-magpie/add-gemini-or-pi-login-via-npm-plugin/","b":false,"f":false,"sc":0.485},{"id":"ifixai-ai-ifixai--use-independent-judge-model","t":"Have a different vendor's model judge your agent's behavior","s":"Choose an independent judge so the agent is not grading its own homework.","w":"Team lead who does not trust a model to score its own output","o":"An audit graded by a separate vendor's judge (or a multi-judge ensemble), giving a more independent score.","c":"Software & DevOps","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/use-independent-judge-model/","b":true,"f":true,"sc":0.786},{"id":"ifixai-ai-ifixai--audit-agent-before-launch","t":"Grade a new AI agent against your business rules before launch","s":"Run a short audit that scores whether your agent follows your roles, policies and permissions.","w":"Founder or engineer about to put a support or ops agent in front of real customers","o":"A graded scorecard (A to F, broken down by category) that shows where the agent breaks policy before users find out.","c":"Software & DevOps","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/audit-agent-before-launch/","b":false,"f":true,"sc":0.759},{"id":"ifixai-ai-ifixai--audit-from-claude-code-plugin","t":"Let Claude Code or Codex run the audit and explain the results","s":"Install the plugin and ask in plain English; the agent builds the fixture, runs it and walks you through the scorecard.","w":"Developer already working in Claude Code or Codex who wants a guided, explained audit without learning flags","o":"A completed audit with an interactive scorecard and a plain-English walkthrough of what failed.","c":"Software & DevOps","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/audit-from-claude-code-plugin/","b":false,"f":true,"sc":0.721},{"id":"ifixai-ai-ifixai--audit-coding-agent-quick-grade","t":"Quickly grade a coding agent on whether it does the job it should","s":"Run the short default suite on a coding agent to get a fast pass/fail picture in about two minutes.","w":"Engineering manager evaluating whether a coding agent is safe to trust with team repos","o":"A quick graded scorecard covering checks like prompt injection, fake tool use and silent failures.","c":"Software & DevOps","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/audit-coding-agent-quick-grade/","b":false,"f":true,"sc":0.691},{"id":"ifixai-ai-ifixai--check-permissions-before-delete-rights","t":"Test an agent's permission boundaries before granting it delete access","s":"Point the audit at your agent's endpoint to see whether it respects role limits before you widen its powers.","w":"Engineer about to give an internal agent write or delete rights on real systems","o":"Evidence on whether the agent's permission-related checks pass, so you can decide to grant or withhold access.","c":"Security & Science","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/check-permissions-before-delete-rights/","b":false,"f":true,"sc":0.678},{"id":"ifixai-ai-ifixai--scaffold-audit-skill-in-any-agent","t":"Add an audit slash command to Cursor, Gemini or Zed in one step","s":"Scaffold a native /ifixai-skill command into the coding agent you already use, no plugin needed.","w":"Developer using Cursor, VS Code, Windsurf, Gemini or another agent that lacks the Claude Code plugin","o":"A working /ifixai-skill command in your agent that reads your setup, shows the cost, and runs the audit after you approve.","c":"Software & DevOps","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/scaffold-audit-skill-in-any-agent/","b":false,"f":false,"sc":0.548},{"id":"ifixai-ai-ifixai--gate-ci-on-agent-audit","t":"Fail your CI build when an agent audit regresses","s":"Script the audit with explicit CLI flags so every release is graded and the report is saved as an artifact.","w":"Platform or DevOps engineer who ships agent changes weekly and wants a repeatable policy check","o":"A scripted, flag-driven audit run in CI that writes JSON and Markdown reports for every change.","c":"Software & DevOps","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/gate-ci-on-agent-audit/","b":false,"f":false,"sc":0.522},{"id":"ifixai-ai-ifixai--find-harmful-action-sequences-policy-lab","t":"Find harmful chains of allowed actions with Policy Lab","s":"Use the offline Policy Lab to find the shortest harmful sequence of permitted actions and test permission fixes.","w":"Security-minded engineer reviewing a refund or payout workflow where each step is allowed but the combination is not","o":"A shortest harmful sequence found offline, plus a check that your permission repair still allows legitimate work.","c":"Security & Science","r":"ifixai-ai/iFixAi","rs":"ifixai-ai-ifixai","u":"/use-cases/ifixai-ai-ifixai/find-harmful-action-sequences-policy-lab/","b":false,"f":false,"sc":0.452},{"id":"feder-cr-git-ai--give-each-agent-its-own-token","t":"Give every coding agent its own token and branch limits","s":"Use per-agent tokens, an RPC allowlist and branch policies so each agent can only do what you allow.","w":"Engineering manager who just discovered an agent pushed to a protected branch and wants accountability per agent","o":"Each agent has its own identity and permitted actions, and each landed change is logged with the agent that made it.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/give-each-agent-its-own-token/","b":true,"f":true,"sc":0.708},{"id":"feder-cr-git-ai--reproduce-the-50-agent-benchmark","t":"Reproduce the 50-agent landing benchmark on your own machine","s":"Run the repo's acceptance script to compare classic retry-based landing with batched compare-and-swap landing.","w":"Engineer evaluating gitai who does not want to trust published numbers without running them","o":"You get your own landed-count, attempts-per-change and latency figures for 50 agents landing 250 changes with planned conflicts.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/reproduce-the-50-agent-benchmark/","b":false,"f":true,"sc":0.667},{"id":"feder-cr-git-ai--try-multi-agent-landing-locally","t":"Watch many agents land changes on one branch in minutes","s":"Build gitai and run the bundled quickstart to see agents land on a shared branch with no merge queue.","w":"Developer running several coding agents who wants to see if a shared branch can survive them before changing their setup","o":"You have a running server, a cache daemon, two agents and one landed change in a temporary directory, so you can judge the model first-hand.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/try-multi-agent-landing-locally/","b":false,"f":true,"sc":0.605},{"id":"feder-cr-git-ai--host-a-shared-repo-for-agent-fleet","t":"Stand up a shared server for a fleet of coding agents","s":"Run your own gitai server so each agent gets its own token and lands onto shared branches.","w":"Team lead whose parallel coding agents keep rebasing and retrying against one main branch","o":"You have a gitai server running from a config file, with agents landing on it through the graft CLI instead of pushing to a classic host.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/host-a-shared-repo-for-agent-fleet/","b":false,"f":true,"sc":0.551},{"id":"feder-cr-git-ai--auto-resolve-agent-merge-conflicts","t":"Resolve conflicting agent changes automatically with a chosen resolver","s":"Plug in a deterministic tool or any LLM provider so conflicting lands resolve instead of bouncing back to the agent.","w":"Developer whose agents touch overlapping files and keep getting conflicts returned","o":"Conflicts are resolved through the versioned resolver protocol and all 250 changes in the demo land, as the README describes for the deterministic resolver.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/auto-resolve-agent-merge-conflicts/","b":false,"f":false,"sc":0.536},{"id":"feder-cr-git-ai--sparse-checkout-for-short-lived-agent-tasks","t":"Give an agent only the folders it needs in a huge repo","s":"Use graft sparse and graft clone to materialize just the paths a short task touches instead of a full clone.","w":"Platform engineer whose agents each edit a few files in a large monorepo and waste time on full clones","o":"The agent fetches only the requested paths and can still land its change through the server.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/sparse-checkout-for-short-lived-agent-tasks/","b":false,"f":false,"sc":0.476},{"id":"feder-cr-git-ai--auto-revert-the-change-that-broke-main","t":"Test the branch tip after landing and revert the culprit","s":"Run graft-verify so a failing tip is bisected and the change that broke it is reverted without a human.","w":"Maintainer whose agents land fast and who needs broken builds caught after the fact, not before every land","o":"A failure on the tip is bisected to the offending change, which is reverted automatically.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/auto-revert-the-change-that-broke-main/","b":false,"f":false,"sc":0.471},{"id":"feder-cr-git-ai--watch-live-changeset-log-for-regressions","t":"Follow the live changeset log with a monitoring agent","s":"Have an agent watch every accepted update and report what matters to each component, including in Slack.","w":"Tech lead who wants to know which agent changed what in a repo receiving hundreds of changes a day","o":"A monitoring agent follows the changeset stream and posts a short report per component, optionally to Slack.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/watch-live-changeset-log-for-regressions/","b":false,"f":false,"sc":0.428},{"id":"feder-cr-git-ai--scale-repo-state-into-postgres-and-object-storage","t":"Move repo state into PostgreSQL and object storage for scale-out","s":"Switch a gitai repo to a database plus object storage so any server node can be added or rebuilt.","w":"Infrastructure engineer planning to run several gitai nodes behind one repository","o":"Your repositories are imported and served in authoritative mode from a database and object storage, with nodes acting as rebuildable caches.","c":"Software & DevOps","r":"feder-cr/git-ai","rs":"feder-cr-git-ai","u":"/use-cases/feder-cr-git-ai/scale-repo-state-into-postgres-and-object-storage/","b":false,"f":false,"sc":0.413},{"id":"leonxlnx-earshot--synthesize-new-sound-with-forge","t":"Synthesize a new sound in code and refine it by ear","s":"Let the agent write a sound recipe, then have a critic score and improve it against real references.","w":"Sound-curious developer who wants a custom click, whoosh or key press made entirely in code","o":"A folder of rendered WAVs, a report in the critic's words, spectrogram comparisons and an audition file.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/synthesize-new-sound-with-forge/","b":true,"f":true,"sc":0.733},{"id":"leonxlnx-earshot--rank-downloaded-sounds-by-description","t":"Pick the best sound from a pile of downloads","s":"Rank candidate files against a text description and trim the best moment from a long recording.","w":"Game or video maker who downloaded several candidate sound effects and needs to pick one","o":"A ranked list of files for your description, plus start and end seconds for the best moment in a long file.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/rank-downloaded-sounds-by-description/","b":false,"f":true,"sc":0.71},{"id":"leonxlnx-earshot--get-written-description-of-audio","t":"Get a written description of any audio file","s":"Turn a sound file into plain words, tags and measurements an agent can reason about.","w":"Builder with a folder of unlabeled sound files who needs to know what each one actually sounds like","o":"A short text reading with calibrated tags, closest alternative readings and numbers like peak level and brightness.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/get-written-description-of-audio/","b":false,"f":true,"sc":0.705},{"id":"leonxlnx-earshot--score-launch-film-audio-with-critique","t":"Score a launch film's audio against pro launch films","s":"Run a scorecard that lists timestamped fixes for your film's soundtrack and mix.","w":"Founder or motion designer finishing a launch video and unsure if the mix is up to standard","o":"A verdict with scored metrics and a numbered list of timestamped fixes, worst first.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/score-launch-film-audio-with-critique/","b":false,"f":true,"sc":0.679},{"id":"leonxlnx-earshot--turn-recording-into-editable-sound-recipe","t":"Turn a recording into code you can vary","s":"Fit a recording to a small synthesis model and get a Python recipe you can tweak or morph.","w":"Developer who has one good sound and wants endless variations or a blend of two sounds","o":"A recipe module that re-renders the sound with new takes, readable knobs and morphs between two recordings.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/turn-recording-into-editable-sound-recipe/","b":false,"f":true,"sc":0.673},{"id":"leonxlnx-earshot--build-sound-kit-for-code-made-film","t":"Build a sound kit for a code-made film","s":"Pick one sound per role from a bank of 201 effects and render them with measured sync points.","w":"Developer making a code-rendered film or app demo who needs whooshes, hits and clicks fast, with no recordings","o":"A kit.json plus rendered takes for every role, each with measured onset, peak and end times.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/build-sound-kit-for-code-made-film/","b":false,"f":true,"sc":0.645},{"id":"leonxlnx-earshot--let-agent-listen-via-mcp-server","t":"Give Claude Code ears with the MCP server","s":"Run earshot as an MCP server so your agent can listen without reloading models each call.","w":"Developer using Claude Code or another MCP-capable agent on audio-heavy projects like films and games","o":"The agent calls describe, match, timeline and critique as tools with models kept loaded.","c":"Software & DevOps","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/let-agent-listen-via-mcp-server/","b":false,"f":true,"sc":0.624},{"id":"leonxlnx-earshot--check-sound-lands-on-video-cuts","t":"Check that sound hits land on your video cuts","s":"Get a second-by-second listening transcript of a film and see if hits match the picture cuts.","w":"Developer whose coding agent renders a product demo video and wants the audio to line up with the cuts","o":"A timeline of sound events, loudness and sync results against the cuts, so the agent can adjust timings.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/check-sound-lands-on-video-cuts/","b":false,"f":true,"sc":0.605},{"id":"leonxlnx-earshot--detect-real-vs-synthesized-audio","t":"Tell a real recording from a code-made sound","s":"Score files for realness and compare them to reference recordings or each other.","w":"Audio-minded builder checking whether a sound in a project reads as a real recording or an obvious synthesis","o":"A real versus synthesized verdict with evidence and per-window scores, plus a plain-words A/B of two sounds.","c":"Content & Creative","r":"Leonxlnx/earshot","rs":"leonxlnx-earshot","u":"/use-cases/leonxlnx-earshot/detect-real-vs-synthesized-audio/","b":false,"f":false,"sc":0.483},{"id":"heygen-com-hyperframes--build-animated-chart-or-stat-video","t":"Build an animated chart or stat clip for social","s":"Use the motion-graphics skill to make a short kinetic-type or chart-hit clip with no narration.","w":"Analyst who wants a 10-second animated number or chart for a post or slide","o":"A short unnarrated motion graphic as an MP4 (or a transparent overlay) with kinetic type or a chart reveal.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/build-animated-chart-or-stat-video/","b":true,"f":true,"sc":0.741},{"id":"heygen-com-hyperframes--edit-video-text-with-one-html-change","t":"Fix a date or price in a finished video by editing HTML","s":"Change one line of text in the source and re-render, instead of reopening a timeline editor.","w":"Marketing manager whose launch date just moved from Friday to Monday","o":"The same animation re-rendered locally as a new MP4 with the corrected text.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/edit-video-text-with-one-html-change/","b":false,"f":true,"sc":0.734},{"id":"heygen-com-hyperframes--make-10-second-product-intro-video","t":"Make a 10-second product intro from one prompt","s":"Ask your coding agent for a short intro with a title, background video and music, and get an MP4 back.","w":"Solo founder who needs a launch clip for tomorrow and has no video editing skills","o":"A rendered 10-second MP4 with a fade-in title, background video and subtle music, built by your agent from HTML.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/make-10-second-product-intro-video/","b":false,"f":true,"sc":0.714},{"id":"heygen-com-hyperframes--turn-merged-pull-request-into-changelog-video","t":"Turn a merged pull request into a changelog video","s":"Point the pr-to-video skill at a PR and get a short explainer of what shipped.","w":"Developer who wants a release note people will actually watch after merging a feature","o":"A short changelog, feature-reveal or fix explainer video generated from the PR contents.","c":"Software & DevOps","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/turn-merged-pull-request-into-changelog-video/","b":false,"f":true,"sc":0.664},{"id":"heygen-com-hyperframes--make-launch-video-from-product-website","t":"Make a launch video from your product's website URL","s":"Give the product-launch-video skill a URL or brief and get a 30 to 90 second promo.","w":"Indie maker with a live landing page and no budget for a promo video","o":"A 30 to 90 second launch or site-tour video built from the site's own visuals and your brief.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/make-launch-video-from-product-website/","b":false,"f":false,"sc":0.622},{"id":"heygen-com-hyperframes--add-designed-captions-to-talking-head-video","t":"Add designed captions to a talking-head video","s":"Overlay styled subtitles on existing footage without touching the original video.","w":"Creator with a recorded talk or podcast clip who needs captions that look designed","o":"The original footage with verbatim captions, or captions embedded behind the subject, rendered as a new MP4.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/add-designed-captions-to-talking-head-video/","b":false,"f":false,"sc":0.608},{"id":"heygen-com-hyperframes--explain-a-concept-with-faceless-video","t":"Explain a topic in a faceless video from plain text","s":"Paste text and get an explainer built from typography, diagrams and data visuals, no footage needed.","w":"Educator or newsletter writer who wants a short explainer without filming or sourcing stock clips","o":"A faceless explainer MP4 where every visual is generated as typography, abstract motion, diagram or data-viz.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/explain-a-concept-with-faceless-video/","b":false,"f":false,"sc":0.597},{"id":"heygen-com-hyperframes--build-slide-deck-as-navigable-html","t":"Build a pitch deck that is an interactive HTML deck","s":"Use the slideshow skill to make a navigable deck with fragment reveals and presenter mode.","w":"Founder preparing a pitch who wants branching or clickable sections instead of a flat PDF","o":"A navigable presentation with discrete slides, fragment reveals, hotspot navigation and presenter mode.","c":"Work & Operations","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/build-slide-deck-as-navigable-html/","b":false,"f":false,"sc":0.571},{"id":"heygen-com-hyperframes--turn-music-track-into-beat-synced-video","t":"Turn a music track into a beat-synced lyric or promo video","s":"Feed the music-to-video skill an audio file and get a video whose pacing follows the beat.","w":"Musician or small label with a finished track and no budget for a music video","o":"A beat-synced lyric, slideshow or kinetic promo video where the music drives the cuts.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/turn-music-track-into-beat-synced-video/","b":false,"f":false,"sc":0.557},{"id":"heygen-com-hyperframes--package-interview-with-graphic-overlays","t":"Add lower-thirds and pull-quotes to an interview recording","s":"Use talking-head-recut to layer titles, data callouts and quotes over an existing video.","w":"Podcaster repackaging a long interview into a polished clip for social","o":"The same footage with designed lower-thirds, kinetic titles, pull-quotes and side panels rendered into a new MP4.","c":"Content & Creative","r":"heygen-com/hyperframes","rs":"heygen-com-hyperframes","u":"/use-cases/heygen-com-hyperframes/package-interview-with-graphic-overlays/","b":false,"f":false,"sc":0.556}]}