agentleFS
wedabrowedabro/bro-skills/.agents/skills/speckit.validate/SKILL.md

speckit.validate

Skill3 starsChanged 59 days agoMITView on GitHub

Implementation Validator - Decide whether implementation satisfies spec, governance, build, runtime, and evidence gates.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read spec, plan, tasks, source, constitution, project config, reports, and documented commands.

    line 10
  2. Very specific:

    Write .agents/memory/validation-report.md with a requirement matrix, evidence links, blockers, limitations, and verdict.

    line 11
  3. Distinctive:

    Verify task state and map every success criterion to implementation and evidence.

    line 14
  4. Distinctive:

    Run applicable formatter, type-check, lint, test, build, migration, and security checks in Docker where required.

    line 16
  5. Distinctive:

    Start runtime only when configured, wait on a bounded health/readiness condition, and inspect logs immediately on failure.

    line 17
  6. Distinctive:

    Check constitution, ENV/secret handling, non-root runtime, accessibility/responsive evidence, and rollback/recovery requirements as …

    line 18
  7. Distinctive:

    Read-only. Do not approve unfinished tasks, failed applicable checks, or unsupported assumptions.

    line 25

≈ “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

Mission

Produce the final evidence-based validation verdict before release or handoff.

Inputs and Outputs

  • Read spec, plan, tasks, source, constitution, project config, reports, and documented commands.
  • Write .agents/memory/validation-report.md with a requirement matrix, evidence links, blockers, limitations, and verdict.

Protocol

  1. Verify task state and map every success criterion to implementation and evidence; unchecked tasks or missing evidence are blockers.
  2. Discover project capabilities and mark non-applicable build, runtime, health, Docker, or framework checks as N/A with reason.
  3. Run applicable formatter, type-check, lint, test, build, migration, and security checks in Docker where required; capture exit codes and logs.
  4. Start runtime only when configured, wait on a bounded health/readiness condition, and inspect logs immediately on failure. Never use sleep alone as readiness proof.
  5. Check constitution, ENV/secret handling, non-root runtime, accessibility/responsive evidence, and rollback/recovery requirements as applicable.
  6. Verdict is PASS only when all applicable gates pass and no requirement lacks evidence; otherwise FAIL with severity, owner, and next action. N/A never counts as PASS.

Completion Gate

The report is reproducible, each claim cites evidence, limitations are explicit, and the verdict does not exceed what was actually verified.

Guard Rails

Read-only. Do not approve unfinished tasks, failed applicable checks, or unsupported assumptions. Do not treat a checkbox alone as delivery evidence.

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.