agentleFS
redhat-developerredhat-developer/rhdh-skills/skills/refinement/openspec-verify-change/SKILL.md

openspec-verify-change

Skill20 starsChanged 20 days agoApache-2.0View on GitHub

Verifies that an implementation matches its OpenSpec change's artifacts — completeness (tasks, spec coverage), correctness (requirement and scenario coverage), and coherence (design adherence, pattern consistency) — post-implementation, before archiving. Use for "verify this change", "does the code match the spec", or "is this ready to archive". For pre- implementation artifact-to-artifact consistency, use openspec-audit-change instead.

78 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use draft-openspec-docs, release-openspec and 7 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.
  • goernSkill

    draft-openspec-docs

    Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then drafts one section per approved step and cleans up after itself. Use when a page needs a from-scratch rewrite or a new page is being shaped with the user in the loop.

    Also in 3 projects that use this

  • goernSkill

    release-openspec

    Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is complete, what the next release step is, or to continue a release paused for human approval.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    openspec-update-change

    Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.

    Also in 20 projects that use this

  • SentrySkill

    code-simplifier

    Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.

    Also in 3 projects that use this

  • GitHubSkill

    prd

    Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

    Also in 3 projects that use this

  • OpenAISkill

    requesting-code-review

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    Also in 3 projects that use this

  • +2 more from goern

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 76 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check that code actually satisfies a change's specs, tasks, and design — after implementation, before archiving — and report gaps with …

    line 16
  2. Very specific:

    Select the change: If not given, run openspec list --json, show changes with implementation tasks, mark ones with incomplete tasks "(In …

    line 22
  3. Very specific:

    Verify coherence: If design.md exists, extract key decisions and check the implementation follows them.

    line 38
  4. Very specific:

    Only tasks.md exists -> verify task completion only.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 76 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 an OpenSpec implementation

Check that code actually satisfies a change's specs, tasks, and design — after implementation, before archiving — and report gaps with actionable, file-referenced recommendations.

Steps

  1. Select the change. If not given, run openspec list --json, show changes with implementation tasks, mark ones with incomplete tasks "(In Progress)", and let the user choose. Never guess.
  2. Check the schema: openspec status --change "<name>" --json.
  3. Load artifacts: openspec instructions apply --change "<name>" --json returns contextFiles (artifact ID -> paths); read everything available.
  4. Verify completeness. Tasks: parse - [ ]/- [x] in every contextFiles.tasks file; each incomplete task is CRITICAL with a recommendation ("Complete task: <description>" or "Mark done if already implemented"). Spec coverage: for each requirement in delta specs, search the codebase for implementation evidence; an apparently-unimplemented requirement is CRITICAL ("Requirement not found: <name>").
  5. Verify correctness. For each requirement, search for implementation evidence and assess whether it matches intent; a divergence is WARNING with a file/line-referenced recommendation. For each scenario, check whether code and tests cover it; an uncovered scenario is WARNING.
  6. Verify coherence. If design.md exists, extract key decisions and check the implementation follows them; a contradiction is WARNING. No design.md means skipping this check and noting it. Check new code against project naming/structure/style conventions; a significant deviation is SUGGESTION.
  7. Generate the report: a summary scorecard (Completeness / Correctness / Coherence), issues grouped CRITICAL / WARNING / SUGGESTION each with a specific recommendation and file.ts:123-style references, and a final assessment — "X critical issue(s) found, fix before archiving" / "No critical issues, Y warning(s) to consider, ready for archive" / "All checks passed, ready for archive".

Heuristics

Completeness leans on objective checklist items; correctness and coherence use keyword search and reasonable inference, not certainty. When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL. Every issue needs a specific, actionable recommendation — never "consider reviewing".

Graceful degradation

Only tasks.md exists -> verify task completion only. Tasks + specs exist -> skip design coherence. Full artifacts -> verify all three dimensions. Always state which checks were skipped and why.

Completion

Complete when all three dimensions were assessed (or their skip was stated and why), every issue has a severity, a file reference, and an actionable recommendation, and the final assessment names whether the change is ready to archive.

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.