agentleFS
AdityaZxxxAdityaZxxx/skills/verify/SKILL.md

verify

Skill1 starsChanged 25 days agoMITView on GitHub

Run a full verification pass over work claimed done. Trace every requirement to its code path, audit the test suite for tests that pin wrong behaviour, build an independent script harness that exercises the requirements by observation, and audit lifecycle edges for what the requirements do not say. Use when a task or feature is claimed done, before shipping, when inheriting work from another agent, or when asked to verify or sign off.

188 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

Files
SKILL.md

Verify

A done-claim is a hypothesis. Verification is the experiment. This skill structures the pass in four moves, in order, then merges everything into one deduplicated verdict. The judgment underneath is shown-work: nothing counts as verified because it was narrated. For a single claim mid-work, the shown-work gate is the whole procedure; this pass is for the work boundary.

1. Requirement trace

Walk the requirements (or the spec) item by item. For each, name the code path that satisfies it, or state plainly that none does. A requirement with no code path is a defect even if the tests pass. Verify the clean requirements too: saying which ones check out guards against false confidence.

2. Independent harness

Write a fresh script that exercises every requirement against the real functions by observation: boundaries, repeated operations, revoked and expired paths, and legacy data. Import the real code; never copy it. Run it and let the output decide. The harness is the deliverable a reviewer reruns, so commit it when the work will be trusted later. An implementer's passing suite is one source of evidence, never the verdict: a suite can be green while pinning the wrong spec.

3. Test audit

For each existing test, ask what it actually pins, and whether it could pass while the requirement it names is violated. Watch for three liars: tests whose setup makes the assertion true by construction, tests that assert the opposite of the requirements, and named requirements with no test at all. A green suite that pins wrong behaviour is worse than no suite: it launders the defect into "proven".

4. Lifecycle audit

Trace what the requirements do not say: boundaries, repeated operations, revoked and expired paths, legacy and persisted state, restarts, and cross-defect compounding (two minors can compose into a blocker). Where state crosses a process boundary, run real processes.

Merge

One deduplicated defect list: requirement number (or "other"), file and symbol, severity, one line of observed evidence, and which move found it. Two or more moves finding the same defect independently is the highest signal; a single-move finding gets weighed accordingly. Then the verdict: ship or don't ship, with the blocking set named.

Completion criterion: every requirement traced to a path or flagged missing; a harness exists, runs, and its output is recorded; every test classified as pinning right or pinning wrong; the merged list deduplicated; the verdict names its blockers.

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.