agentleFS
Sign inStart free
axrmxvaxrmxv/claude-config/skills/research-reuse/SKILL.md

research-reuse

Skill1 starsChanged 4 months agoMITView on GitHub

Search for existing implementations, libraries, and patterns before writing new code. Use before starting any new feature, utility, or integration — GitHub code search, vendor docs, and package registries first, net-new code last.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Broader web search: Only when the steps above came up short.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research whether $ARGUMENTS already exists before anything is written. Do not propose an implementation — report what can be reused.

Search order

Work through these in order and stop early only when you have a strong match.

  1. This codebase first. Grep and Glob for existing functions, utilities, base classes, and patterns that already solve part of the problem. A helper that is 60% right and already tested beats a fresh one.
  2. GitHub code search. gh search repos for projects solving the whole problem, then gh search code for concrete implementations of the tricky part. Note stars, last commit, and licence.
  3. Package registries. npm / PyPI / crates.io for a maintained library. Prefer battle-tested packages over hand-rolled utilities.
  4. Vendor documentation. Confirm API behaviour and version-specific details against the primary docs (or Context7) before assuming an interface.
  5. Broader web search. Only when the steps above came up short.

Report

  • Reuse from this repo — file paths and what each already does.
  • Candidate libraries — name, what it covers, maintenance signal, licence, and the gap you would still have to fill.
  • Adaptable implementations — repos that solve 80%+ of the problem and could be ported or wrapped.
  • Recommendation — one option, with the reason. If net-new code really is the answer, say so explicitly and state what you ruled out.

Name file paths and URLs concretely. A recommendation the reader cannot verify is not useful.

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.

Check your setup, free