# AI use cases for Sno Station Skills (sno-ai/sno-station-skills) Repo: [sno-ai/sno-station-skills](https://github.com/sno-ai/sno-station-skills) | Use cases: 5 | Page: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/ Sno Station Skills is a set of 31 open source skills that install into Claude Code and Codex so they can review each other's work, hand off tasks when quota runs out, report each morning, delegate with written success checks, and learn from past sessions. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Get a cold second review from the other vendor's agent: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/cross-vendor-peer-review/ - Keep an overnight build going when one agent runs out of quota: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/overnight-run-survives-quota/ - Read a one-page brief when you come back to the desk: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/morning-away-brief/ - Hand off a job with a charter that defines done: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/delegate-work-with-proof/ - Review nightly lessons from your own sessions before they stick: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/nightly-lessons-you-approve/ ## How to get a cold second review from the other vendor's agent with Sno Station Skills Repo: [sno-ai/sno-station-skills](https://github.com/sno-ai/sno-station-skills) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Have a fresh agent from the other vendor check your change before it lands. **Who it is for:** A developer who finished a code change in Claude Code or Codex and wants an independent check before merging. **The problem:** An agent reviewing its own work misses what it cannot see, so one vendor's review is often not enough. **The outcome:** A review from a fresh session with none of the author's conversation, plus a fix loop that runs until the review comes back clean. ### Steps 1. Install the skills with `sh -c 'sno_installer_body=$(curl -fsSL https://sno.ai/install) && printf "%s\n" "$sno_installer_body" | sh'` 2. If you add another agent later, run `sno setup` to connect it. 3. In your agent, finish a change and say "peer-review this". 4. Read the findings. The author fixes root causes and the review repeats until it is clean. ### Prompt to paste into your agent ```text In the repo , use the peer-review skill from Sno Station Skills on the latest uncommitted change, preferring the other vendor's CLI in a fresh session. Output the findings list with each finding's trigger, impact and refutation attempt. Verify that the first line of the report states whether the review was same-vendor. ``` ### Caveat The installer is a remote script piped to sh, so read it at sno.ai/install before you run it, and the cross-vendor review needs both CLIs installed. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/cross-vendor-peer-review/ ## How to keep an overnight build going when one agent runs out of quota with Sno Station Skills Repo: [sno-ai/sno-station-skills](https://github.com/sno-ai/sno-station-skills) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README Arm a handover so a second vendor's agent continues the task from the exact commit. **Who it is for:** A developer starting a long build before bed who cannot watch the agent through a quota limit. **The problem:** An agent stops dead when its quota runs out in the middle of a build, and the work stalls until morning. **The outcome:** When the working agent's quota reaches the threshold, it writes a handover brief, a fresh agent from the other vendor takes over after the brief is verified, and the work continues from the first unchecked task. ### Steps 1. Install the skills with the one-line installer from the README, then run `sno setup`. 2. Before bed, say "arm rotate-agent" in your working agent. 3. Leave the run going. The handover uses subscription-quota-check, heartbeat, rotate-agent and handoff. 4. In the morning, read the away brief to see what finished and what is stuck. ### Prompt to paste into your agent ```text In the repo , arm the rotate-agent skill from Sno Station Skills so that the task in hands over to the other vendor's agent when quota reaches the threshold. Output the handover brief and the commit to continue from. Verify that the receiving agent confirmed the brief before touching any file. ``` ### Caveat The README describes this flow on Sno Station's own repository; test it on a non-critical task before trusting it with an unattended build. Risk, account pooling: The handover moves work between Claude Code and Codex when one subscription runs low, so check that your vendor terms allow this before you rely on it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/overnight-run-survives-quota/ ## How to read a one-page brief when you come back to the desk with Sno Station Skills Repo: [sno-ai/sno-station-skills](https://github.com/sno-ai/sno-station-skills) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Get one page of what got done, what is stuck, and what waits for your answer. **Who it is for:** A developer who left agents running during the day or overnight and wants a quick status before doing anything else. **The problem:** Returning to a long agent run means digging through logs to learn what finished, what failed and what cost quota. **The outcome:** A brief of at most 60 lines covering completed work, stuck items with reasons, questions waiting for you, and quota cost. ### Steps 1. Install the skills with the one-line installer, then run `sno setup`. 2. Let your agents run unattended for the session. 3. When you return, say "away brief" to your agent. 4. Answer the questions listed under waiting for you. ### Prompt to paste into your agent ```text In the repo , produce an away brief with the away brief skill from Sno Station Skills covering the last of agent activity. Output at most 60 lines with done, stuck, waiting-for-you and quota-cost sections. Verify that every stuck item names a reason. ``` ### Caveat The brief summarizes only the work your agents recorded, so anything done outside them will not appear. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/morning-away-brief/ ## How to hand off a job with a charter that defines done with Sno Station Skills Repo: [sno-ai/sno-station-skills](https://github.com/sno-ai/sno-station-skills) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Write one charter with success checks, then let any agent deliver it. **Who it is for:** A lead who wants to give an agent a task with a clear definition of done and wants proof, not an agent's word, that it is finished. **The problem:** Agents often report work as done when the tests are green and nothing actually happened. **The outcome:** One charter file stating deliverables, out-of-bounds areas, prior decisions and how each success check is proven by a recorded real run. ### Steps 1. Install the skills with the one-line installer, then run `sno setup`. 2. Say "write a charter" and describe the job, the deliverables and the limits. 3. Review the success checks in the charter file. 4. Give the charter to any agent and have it deliver the work, with each check proven by a recorded run. ### Prompt to paste into your agent ```text In the repo , write a charter with the work-orders skill from Sno Station Skills for the job described in . Output one charter file with deliverables, out-of-bounds areas, decided items and a proof method for each success check. Verify that every success check names a real run that can pass or fail. ``` ### Caveat The charter is only as strong as the success checks you write, so vague checks will still produce vague proof. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/delegate-work-with-proof/ ## How to review nightly lessons from your own sessions before they stick with Sno Station Skills Repo: [sno-ai/sno-station-skills](https://github.com/sno-ai/sno-station-skills) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Let the nightly loop propose lessons and skill changes, and accept only the ones you want. **Who it is for:** A developer who repeats the same corrections to agents across days and wants those corrections recorded as rules. **The problem:** Agents make the same mistake tomorrow that they made today because no one tells them otherwise. **The outcome:** Each morning you see proposed lessons drawn from that day's Claude Code and Codex sessions, and only the ones you accept become live rules. ### Steps 1. Install the skills with the one-line installer, then run `sno setup`. 2. Let the nightly loop run on its own after your sessions. 3. In the morning, review the proposed lessons and skill changes. 4. Accept the ones you like with `sno rem-reflect accept `. Nothing changes without that accept. (inferred, check the README) ### Prompt to paste into your agent ```text In the repo , run the rem-reflect skill from Sno Station Skills over the last days of Claude Code and Codex sessions. Output a list of proposed lessons and skill changes, each with the session evidence. Verify that no change is applied until it is explicitly accepted. ``` ### Caveat The loop reads your session history, so review what it reads before you run it on shared or sensitive machines. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/sno-ai-sno-station-skills/nightly-lessons-you-approve/