agentleFS
Sign inStart free
qyndexqyndex/claude-init/.claude/skills/verify/SKILL.md

verify

Skill2 starsChanged 5 months agoMITView on GitHub

Run the actual application end-to-end and exercise the user journey from the spec. Phase 6 of the eight-phase workflow. Delegate to verifier agent. Captures screenshots, logs, HTTP traces. The "did it actually work?" gate.

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 9 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

  • Jurel89Skill

    ai-slop-cleaner

    Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

    Also in 4 projects that use this

  • +1 more from TheKREATORS

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 3

    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. Distinctive:

    Run the app. Exercise the user journey.

    line 15
  2. Distinctive:

    Read the spec's user journey.

    line 19
  3. Very specific:

    Sync living state (M-06 — network boundary): Verify is a network boundary: refresh initiatives/active/<id>.STATE.md so the always-current …

    line 25
  4. Distinctive:

    After save: "Verification PASS — N steps, M negative paths.

    line 60

“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

Run the app. Exercise the user journey. Capture evidence. Mark PASS or FAIL.

Process

  1. Read the spec's user journey.
  2. Boot the app (bash .claude/scripts/run.sh or project-specific).
  3. Walk the journey step by step, capturing evidence at each step.
  4. Walk the negative paths (bad input, missing auth, etc.).
  5. Save artifacts under verify/<date>-<feature>/.
  6. Write the report.
  7. Sync living state (M-06 — network boundary). Verify is a network boundary: refresh initiatives/active/<id>.STATE.md so the always-current answer reflects this run. Grep-gated so it's a no-op when the script is absent:
    grep -ql 'initiative-state.sh sync' .claude/scripts/initiative-state.sh 2>/dev/null \
  && bash .claude/scripts/initiative-state.sh sync || true

Evidence types

  • Screenshots (browser MCP take_screenshot)
  • DOM/a11y snapshots (take_snapshot)
  • HTTP responses (curl -i or Postman collection)
  • Log excerpts (docker compose logs --since 5m)
  • Console messages (list_console_messages)
  • Network requests (list_network_requests)
  • Exit codes (for CLIs)

Hard rules

  • Evidence before assertion. "Looks fine" is not verification.
  • The user journey, not just tests. Unit tests passing ≠ user works.
  • Negative paths too. Try the obvious failure.
  • Real-ish data. Fresh seeded DB or test tenant; no internal mocks.
  • Capture, don't summarize. Save raw artifacts so future you can re-examine.

Output

verify/<date>-<feature>/REPORT.md
verify/<date>-<feature>/*.png
verify/<date>-<feature>/*.json
verify/<date>-<feature>/*.log

REPORT.md format: see .claude/agents/quality/verifier.md.

After save: "Verification PASS — N steps, M negative paths. Ready for /review." OR "Verification FAIL at step K. See verify/<date>/REPORT.md. Hand back to implementer."

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