agentleFS
takleb3rrytakleb3rry/claude-global-appbuilding-skills/skills/verify/SKILL.md

verify

Skill6 starsChanged 8 months agoMITView on GitHub

Lightweight verification gate — prove a claim before making it. Use when finishing ad-hoc work, one-off fixes, or any time you're about to say "done" or "fixed" outside of /execute-phase. Trigger on "verify this works", "prove it", "check your work", "does this actually work". Also referenced inline by /diagnose (Phase 4) and /execute-phase (completion criteria) as an embedded methodology.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use instinct-export, instinct-import and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TheKREATORSSkill

    instinct-export

    Export instincts from project/global scope to a file

    Also in 3 projects that use this

  • TheKREATORSSkill

    instinct-import

    Import instincts from file or URL into project/global scope

    Also in 3 projects that use this

  • AviadPSkill

    risk-assess

    Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).

    Also in 3 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 6 projects that use this

  • AaravChadhaSkill

    secure

    Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.

    Also in 3 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 10 projects that use this

  • +1 more from TheKREATORS

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Test suite: npm test, pytest, vitest run [file]

    line 16
  2. Distinctive:

    If you can't name a command that proves it, you can't claim it.

    line 19
  3. Distinctive:

    Read the full output. Don't skim.

    line 25
  4. Distinctive:

    No:: Do not restate the claim with caveats.

    line 33
  5. Distinctive:

    If you can't point to command output that proves the claim, the claim isn't ready.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 167 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

Verify

Prove it works. Then say it works. Never the other way around.


The Checklist

1. IDENTIFY

What command(s) would prove the claim you're about to make? Name them explicitly.

  • Test suite: npm test, pytest, vitest run [file]
  • Build: npx tsc --noEmit, npm run build
  • Specific behavior: curl, browser check, database query
  • If you can't name a command that proves it, you can't claim it.

2. RUN

Execute the command(s). No dry runs. No "I would run." Actually run it.

3. READ

Read the full output. Don't skim. Don't stop at the first green line. Look for:

  • Partial failures buried in passing output
  • Warnings that indicate the test isn't testing what you think
  • Skipped tests that cover the relevant behavior

4. CHECK

Does the output confirm the claim?

  • Yes: State the claim with the evidence. "Fixed — vitest run src/auth passes 12/12 tests including the new regression test."
  • No: Do not restate the claim with caveats. Investigate. Return to the work.

Language Rules

Instead of...Use...
"Should work now"[run the command, show the output]
"I believe this resolves it"[run the test, cite the result]
"That should be fine"[verify it, state what you verified]
"This probably fixes it"[prove it fixes it]
"Done!" (before evidence)[show evidence, then state completion]

If you can't point to command output that proves the claim, the claim isn't ready.

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.