agentleFS
Sign inStart free
wedabrowedabro/bro-skills/.agents/skills/speckit.checklist/SKILL.md

speckit.checklist

Skill3 starsChanged 45 days agoMITView on GitHub

Requirements Validator - Build an evidence-linked checklist from a specification and verify its status.

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read spec.md, plan.md, tasks.md, implementation evidence, and test/review reports when available.

    line 10
  2. Very specific:

    Write .agents/specs/[feature]/checklist.md with quoted requirement text, links, status, evidence, and gaps.

    line 11
  3. Distinctive:

    Check for duplicate IDs, orphan tasks, contradictory acceptance criteria, and requirements omitted from tasks or tests.

    line 17
  4. Distinctive:

    Every extracted requirement appears exactly once, mappings reconcile, statuses cite evidence, and unverified items are explicit.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 3 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

Mission

Turn approved requirements and success criteria into a traceable checklist that exposes partial and unverified delivery.

Inputs and Outputs

  • Read spec.md, plan.md, tasks.md, implementation evidence, and test/review reports when available.
  • Write .agents/specs/[feature]/checklist.md with quoted requirement text, links, status, evidence, and gaps.

Protocol

  1. Extract each user scenario, functional/non-functional requirement, constraint, and success criterion with stable IDs and exact source quotes.
  2. Map each item to plan sections, task IDs, implementation paths, tests, and acceptance evidence; report missing links instead of guessing.
  3. Set status only from evidence: Met, Partial, Not Met, Blocked, or Unverified. A checkbox alone is not proof.
  4. Check for duplicate IDs, orphan tasks, contradictory acceptance criteria, and requirements omitted from tasks or tests.
  5. Summarize coverage by category and list the smallest next action for every gap.

Completion Gate

Every extracted requirement appears exactly once, mappings reconcile, statuses cite evidence, and unverified items are explicit.

Guard Rails

Quote rather than rewrite requirements, do not modify spec/tasks/source, and do not mark an item Met without verifiable 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.

Reviews can't be read right now.

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