agentleFS
neijixneijix/AICodeFactory/skills/tech-research/SKILL.md

tech-research

Skill0 starsChanged 15 days agoMITView on GitHub

Use when the user asks to add a dependency or pick a library, framework or tool, before a non-trivial integration (auth, payments, uploads, real-time), when filling a [FRAMEWORK]/[LIBRARY] placeholder, or before coding against an API you haven't verified recently. Produces a recommendation with alternatives, gotchas and doc links, saved to KNOWLEDGE.md.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Never use a library with no commits in the last 12 months without flagging it

    line 41
  2. Distinctive:

    Never use a library with a critical unpatched CVE without flagging it

    line 42
  3. Distinctive:

    Prefer official/first-party over third-party when both solve the problem equally

    line 43
  4. Distinctive:

    Always use the latest stable version unless the project has a documented reason not to

    line 44

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Technology Selection, Best Practices & Documentation Research

Triggers — run this protocol automatically when:

  • User asks to add a library, framework, or tool
  • User asks to implement a non-trivial feature (auth, payments, file uploads, real-time, etc.)
  • A placeholder [framework] or [library] is being filled during bootstrap
  • You are about to write code for an integration you haven't verified recently

Research protocol (execute in order)

  1. Search for the current best options — check GitHub stars, last commit date, open issues, known CVEs, deprecation notices, and community adoption
  2. Fetch the official documentation for the chosen technology — read the quickstart, API reference, and any "gotchas" or migration guides
  3. Search for best practices — official style guides, security hardening docs, performance guides, and patterns recommended by the maintainers
  4. Check for known issues — common pitfalls, breaking changes in recent versions, and unpatched CVEs

Output format — always present to the user

  • Recommended option with rationale (why this one)
  • Alternative with pros/cons comparison
  • Key gotchas discovered during research
  • Links to the docs you read

After research

  • Save findings to .github/KNOWLEDGE.md under the relevant category
  • Include: what was chosen, why, links to official docs, key patterns, and gotchas
  • Commit: git commit -m "docs(knowledge): add [technology] research and best practices"

Quality bar

  • Never use a library with no commits in the last 12 months without flagging it
  • Never use a library with a critical unpatched CVE without flagging it
  • Prefer official/first-party over third-party when both solve the problem equally
  • Always use the latest stable version unless the project has a documented reason not to

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.