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
- ValorVie/custom-skillstheir own version, first seen Nov 8, 2026
- FuDesign2008/open-skillstheir own version, first seen Nov 6, 2026
- theoden8/webspace_apptheir own version, first seen Nov 2, 2026
- xsyetopz/claudettotheir own version, first seen Nov 1, 2026
- xsyetopz/dotclaudetheir own version, first seen Nov 1, 2026
- 200iqlabs/shared-skillstheir own version, first seen Nov 1, 2026
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.
goernSkilldraft-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
goernSkillrelease-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 AzureSkillopenspec-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
SentrySkillcode-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
GitHubSkillprd
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
OpenAISkillrequesting-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
Other versions78 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 78
- Fission-AI/OpenSpec★ 74ksame name
- alibaba/druid★ 28ksame name
- studyzy/imewlconverter★ 10ksame name
- PBH-BTN/PeerBanHelper★ 6.4ksame name
- fengshao1227/ccg-workflow★ 6ksame name
- owncloud/android★ 4.2ksame name
- Soju06/codex-lb★ 3.3ksame name
- Draculabo/AntigravityManager★ 2.5ksame name
- arabold/docs-mcp-server★ 1.8ksame name
- arkflow-rs/arkflow★ 1.3ksame name
68 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository73 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- rhdh-base-imagesSkill
- rhdh-konflux-rpaSkill
- rhdh-konflux-tasksSkill
- rhdh-plugin-catalog-index-status-and-update-flowSkill
- rhdh-pr-mrSkill
- rhdh-prow-jobsSkill
- rhdh-prow-release-branchSkill
- rhdh-prow-triggerSkill
- rhdh-yarn-bumpSkill
- rhdh-feature-docsSkill
- rhdh-jira-createSkill
- rhdh-jira-linkSkill
- rhdh-jira-refineSkill
- rhdh-jira-sprint-planSkill
- rhdh-jira-sprint-reportSkill
- rhdh-jira-updateSkill
- rhdh-prepare-refinementSkill
- agent-readinessSkill
- ask-rhdhSkill
- clean-proseSkill
- setup-rhdh-skillsSkill
- skill-authoringSkill
- rhdh-backportSkill
- rhdh-backstage-upgradeSkill
- rhdh-localSkill
- rhdh-operator-pr-testSkill
- rhdh-overlaySkill
- rhdh-playwrightSkill
- rhdh-plugin-authoringSkill
- rhdh-plugin-bug-fixSkill
- rhdh-plugin-exportSkill
- rhdh-plugin-midstream-propagateSkill
- rhdh-plugin-nfs-migrationSkill
- rhdh-plugin-wiringSkill
- rhdh-pr-createSkill
- rhdh-pr-reviewSkill
- rhdh-test-placementSkill
- backstage-api-changesSkill
- mutation-gateSkill
- openspec-journalSkill
- prose-editingSkill
- rhdh-contextSkill
- rhdh-forgeSkill
- rhdh-jira-apiSkill
- rhdh-jira-authoringSkill
- rhdh-spec-driven-schemaSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-audit-changeSkill
- openspec-bulk-archive-changeSkill
- openspec-continue-changeSkill
- openspec-exploreSkill
- openspec-ff-changeSkill
- openspec-new-changeSkill
- openspec-onboardSkill
- openspec-sync-specsSkill
- rhdh-overlay-cve-exportSkill
- rhdh-platform-lifecycleSkill
- The first 60 shown.
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
- Distinctive: line 16
Check that code actually satisfies a change's specs, tasks, and design — after implementation, before archiving — and report gaps with …
- Very specific: line 22
Select the change: If not given, run openspec list --json, show changes with implementation tasks, mark ones with incomplete tasks "(In …
- Very specific: line 38
Verify coherence: If design.md exists, extract key decisions and check the implementation follows them.
- Very specific: line 59
Only tasks.md exists -> verify task completion only.
“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.
Files
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
- 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. - Check the schema:
openspec status --change "<name>" --json. - Load artifacts:
openspec instructions apply --change "<name>" --jsonreturnscontextFiles(artifact ID -> paths); read everything available. - Verify completeness. Tasks: parse
- [ ]/- [x]in everycontextFiles.tasksfile; 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>"). - 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.
- Verify coherence. If
design.mdexists, extract key decisions and check the implementation follows them; a contradiction is WARNING. Nodesign.mdmeans skipping this check and noting it. Check new code against project naming/structure/style conventions; a significant deviation is SUGGESTION. - 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.
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
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.

