# AI use cases for Sandbase Skills (sandbaseai/sandbase-skills) Repo: [sandbaseai/sandbase-skills](https://github.com/sandbaseai/sandbase-skills) | Use cases: 5 | Page: https://dedupedai.com/use-cases/sandbaseai-sandbase-skills/ SandBase Skills is a Python-based repository of 245 installable Agent Skills, each an instruction file that teaches an AI agent one repeatable research, social, marketing, or business workflow. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Cross-check a market claim against independent sources: https://dedupedai.com/use-cases/sandbaseai-sandbase-skills/cross-check-market-claim-with-sources/ - Check a research report's evidence ledger offline: https://dedupedai.com/use-cases/sandbaseai-sandbase-skills/validate-research-report-offline/ - Install all 245 Skills into Claude Code at once: https://dedupedai.com/use-cases/sandbaseai-sandbase-skills/install-all-skills-in-claude-code/ - Compare brand sentiment on X with source-linked posts: https://dedupedai.com/use-cases/sandbaseai-sandbase-skills/monitor-x-sentiment-for-brands/ - Load the full Skill bundle into DeepSeek Harness: https://dedupedai.com/use-cases/sandbaseai-sandbase-skills/install-deepseek-harness-skill-bundle/ ## How to cross-check a market claim against independent sources with Sandbase Skills Repo: [sandbaseai/sandbase-skills](https://github.com/sandbaseai/sandbase-skills) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Run the multi-source-search Skill to test a claim against web and academic evidence. **Who it is for:** A product manager or analyst who needs to check a market claim before using it in a plan or deck. **The problem:** Single-source answers from an agent can hide disagreement and weak evidence. **The outcome:** A cross-checked findings summary with disagreements called out, using your agent's existing search tools. ### Steps 1. Run `npx skills use sandbaseai/sandbase-skills@multi-source-search` to generate the full Skill prompt, or run `npx skills add sandbaseai/sandbase-skills@multi-source-search --agent codex` to install it. 2. Open your agent in a project folder that has web or search tools enabled. 3. Give the agent the claim to test and ask it to verify the strongest evidence for and against it. 4. Read the disagreements section and check the linked sources yourself before sharing any conclusion. ### Prompt to paste into your agent ```text Use the multi-source-search Skill from the sandbaseai/sandbase-skills repo to fact-check this claim with independent sources: . Return an evidence ledger with supporting and opposing sources, confidence per claim, and any conflicts. Verify that every source in the ledger is a link you actually read. ``` ### Caveat The Skill works with your agent's existing search tools, and SandBase only adds broader provider coverage when you connect it. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. 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/sandbaseai-sandbase-skills/cross-check-market-claim-with-sources/ ## How to check a research report's evidence ledger offline with Sandbase Skills Repo: [sandbaseai/sandbase-skills](https://github.com/sandbaseai/sandbase-skills) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run the bundled validator to catch unknown sources, inflated confidence, and unresolved conflicts. **Who it is for:** A researcher or reviewer who has received an evidence-ledger report and must confirm it is internally consistent before relying on it. **The problem:** Synthesis from an agent can look rigorous while citing unused sources or overstating confidence. **The outcome:** A pass or fail result from the validator that flags structural problems in the report. ### Steps 1. Clone the repository with `git clone https://github.com/sandbaseai/sandbase-skills.git` and open the folder. (inferred, check the README) 2. Open examples/branch-protection-research.md to see the worked example and what a checked claim looks like. 3. Run `python3 research/multi-source-search/scripts/validate_report.py examples/verifiable-research-report.json`. (inferred, check the README) 4. Compare your own report JSON against the same structure and fix any rejected sources or claims. ### Prompt to paste into your agent ```text In the sandbaseai/sandbase-skills repo, run research/multi-source-search/scripts/validate_report.py on . Report the VALID or rejection messages, list each rejected source or claim, and verify that the validator checked internal consistency only, not whether any source is true. ``` ### Caveat The validator checks internal consistency only and does not claim that any source is true, so you still need to read the sources. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. 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/sandbaseai-sandbase-skills/validate-research-report-offline/ ## How to install all 245 Skills into Claude Code at once with Sandbase Skills Repo: [sandbaseai/sandbase-skills](https://github.com/sandbaseai/sandbase-skills) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Add the marketplace and install the full Skill bundle as a Claude Code plugin. **Who it is for:** A Claude Code user who wants the whole Skill library available without copying folders by hand. **The problem:** Copying 245 Skill directories manually is slow and easy to get wrong. **The outcome:** All listed Skills available to Claude Code, discovered on demand. ### Steps 1. Open Claude Code in your terminal. 2. Run `/plugin marketplace add sandbaseai/sandbase-skills` inside Claude Code. 3. Run `/plugin install sandbase-skills@sandbase-agent-skills` inside Claude Code. 4. Ask Claude Code to list the research Skills it can use, then pick one from the catalog to test. ### Prompt to paste into your agent ```text Install the sandbase-skills plugin marketplace in Claude Code and confirm it lists the research Skills from sandbaseai/sandbase-skills. Return the names of three Skills you can use for research and say which one fits a fact-checking task. ``` ### Caveat The marketplace lists every Skill explicitly, but the specialized social and data Skills need a SANDBASE_API_KEY before they will run against providers. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. 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/sandbaseai-sandbase-skills/install-all-skills-in-claude-code/ ## How to compare brand sentiment on X with source-linked posts with Sandbase Skills Repo: [sandbaseai/sandbase-skills](https://github.com/sandbaseai/sandbase-skills) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Install the Twitter intelligence Skill and run a sentiment comparison with linked evidence. **Who it is for:** A brand or marketing analyst who needs to see how customers talk about two brands on X this month. **The problem:** Sentiment summaries without linked posts are hard to check or defend. **The outcome:** A structured comparison with source-linked posts, trends, and recurring complaints. ### Steps 1. Preview the Skill with `gh skill preview sandbaseai/sandbase-skills research/twitter-intelligence` before installing it. (inferred, check the README) 2. Install it for your agent with `gh skill install sandbaseai/sandbase-skills research/twitter-intelligence --agent codex --scope user`. (inferred, check the README) 3. Set SANDBASE_API_KEY in your environment, not in the prompt or any committed file. 4. Ask the agent for the comparison and open several linked posts to confirm the sentiment labels. ### Prompt to paste into your agent ```text Use the twitter-intelligence Skill from sandbaseai/sandbase-skills to compare sentiment and recurring complaints for and on X this month. Return source-linked posts, trends, and a structured comparison. Verify by opening at least five linked posts and confirming each matches the sentiment assigned to it. ``` ### Caveat The README describes specialized social Skills as needing a configured SandBase provider, so results depend on that setup rather than on the Skill alone. Risk, credentials: The Skill needs SANDBASE_API_KEY, so store it in your environment and never paste it into a prompt or commit it to a file. Risk, reverse engineering: Monitoring user accounts and posts at scale can cross platform terms or privacy expectations, so limit the collection to what your use needs. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. 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/sandbaseai-sandbase-skills/monitor-x-sentiment-for-brands/ ## How to load the full Skill bundle into DeepSeek Harness with Sandbase Skills Repo: [sandbaseai/sandbase-skills](https://github.com/sandbaseai/sandbase-skills) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Add the repository as a DSH plugin and start the web interface with all Skills mounted. **Who it is for:** A DeepSeek Harness user who wants the full research and marketing Skill set available in one step. **The problem:** Setting up the Skill directories by hand for each project takes time. **The outcome:** The packaged marketing and research Skill directories mounted in DSH. ### Steps 1. Run `dsh plugin --profile web add github:sandbaseai/sandbase-skills`. 2. Run `dsh web`. 3. Confirm that the research Skills appear in the DSH Skill list. 4. If you only want one project to have the flagship Skill, run `npx --yes github:sandbaseai/sandbase-skills add multi-source-search` inside that project. ### Prompt to paste into your agent ```text Install the sandbaseai/sandbase-skills bundle in DeepSeek Harness and confirm that the multi-source-search Skill is available. Return the Skill name and one sample research question you can run with it, and verify that the Skill appears in the DSH Skill list. ``` ### Caveat The DSH bundle runs directly from GitHub, so no npm publication or SandBase account is required for the Skills themselves. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. 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/sandbaseai-sandbase-skills/install-deepseek-harness-skill-bundle/