agentleFS
XakkiXakki/ai-agents-skills/skills/research-prior-art-find/SKILL.md

research-prior-art-find

Skill6 starsChanged 3 months agoMITView on GitHub

Find and compare existing implementations before designing or changing software. Use before building something that may already exist. RU: готовые решения, аналоги.

The file

Files
SKILL.md

Prior-art research

Identify the desired behavior and acceptance boundaries before searching. Discover relevant public or authorized existing implementations through available source interfaces; repository names or search results alone do not prove a capability exists or ships in the selected release.

Inspect authoritative implementation, version, documentation and compatibility evidence. Compare input/output and integration boundaries, deployment requirements, maintenance state, license and real limitations. Distinguish a feature already shipped from a proposal, historical branch, unsupported claim or missing integration seam. Record relevant source links and uncertainty, and recommend reuse, adaptation or new work only to the extent the evidence supports it.

Finding a candidate does not authorize installing, cloning private code, changing dependencies, forking, executing untrusted code or publishing. Follow the user's actual scope and runtime interfaces; never infer product or network access from an example command.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.