agentleFS
clideyclidey/whodb/.agents/skills/research-proof/SKILL.md

research-proof

Skill5.1k starsChanged 3 days agoApache-2.0View on GitHub

Prove claims about external tools, APIs, libraries, services, standards, or current behavior

Trending

Less talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 3 mentionsMar 2026: 8 mentionsApr 2026: 4 mentionsMay 2026: 5 mentionsJun 2026: 6 mentionsJul 2026: 5 mentionsAug 2026: 6 mentionsSep 2026: 6 mentionsOct 2026: 9 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the clidey/whodb repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about clidey/whodb

The biggest 5 of 60 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 60

Talked about on GitHub, Bluesky and Hacker News (60 times).

On GitHub · 50

45 more on GitHub

On Bluesky · 7

2 more on Bluesky

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Use this workflow when making claims about behavior outside this repository, especially third-party APIs, dependencies, hosted services, …

    line 8
  2. Distinctive:

    Avoid relying on blogs, forum answers, AI summaries, or stale issue comments when an official source or source code is available.

    line 25
  3. Distinctive:

    Prefer the narrowest source that proves the exact behavior.

    line 31
  4. Distinctive:

    Use local evidence when the behavior can be verified directly:

    line 38
  5. Distinctive:

    Do not vendor-copy large external snippets into the repo.

    line 48
  6. Distinctive:

    Do not present guesses as verified facts.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Proof

Use this workflow when making claims about behavior outside this repository, especially third-party APIs, dependencies, hosted services, standards, current pricing, product capabilities, or agent tooling.

When Proof Is Required

  • The claim affects implementation, security, billing, auth, deployments, compatibility, or user-facing behavior.
  • The claim is about a third-party library, framework, CLI, cloud service, database, browser API, or protocol.
  • The claim may have changed recently.
  • The user asks whether something is true, current, supported, recommended, or safe.
  • A repo rule explicitly says to show proof.

Preferred Sources

  1. Official documentation from the vendor or standards body.
  2. Actual source code from the dependency, SDK, or CLI implementation.
  3. Release notes, changelogs, or migration guides from the project owner.
  4. Reproducible local evidence from this repository or a minimal command.

Avoid relying on blogs, forum answers, AI summaries, or stale issue comments when an official source or source code is available.

Workflow

  1. State the specific external claim that needs proof.
  2. Find an official source or actual implementation that answers that claim.
  3. Prefer the narrowest source that proves the exact behavior.
  4. Record the source link, version, date, or command used.
  5. Apply the finding to the repo with the smallest necessary change.
  6. In the final response, cite the proof or summarize the exact local evidence.

Local Evidence

Use local evidence when the behavior can be verified directly:

# Examples only. Choose commands relevant to the task.
go doc package.Symbol
pnpm why package-name
pnpm exec tool --help
rg -n "functionName|exportName" node_modules package-lock.json pnpm-lock.yaml

Do not vendor-copy large external snippets into the repo. Quote only the minimum needed to justify the implementation.

Output Expectations

  • Name the source of truth.
  • Include the exact version when version affects behavior.
  • Explain how the evidence changes the implementation decision.
  • Say when proof could not be found and what assumption remains.
  • Do not present guesses as verified facts.

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.