verify-task
Skill54 starsChanged 4 months agoMITView on GitHub
Verify a work item is actually done by running the V-* validation rows its issue cites. Maps V-* IDs to the CI step / test command via VALIDATION.md, runs them, reports pass/fail per row.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Tgoldi/claude-skillstheir own version, first seen Oct 13, 2026
- precise-alloy/ritustheir own version, first seen Oct 11, 2026
- flurdy/agent-skillstheir own version, first seen Aug 9, 2026
- Phoenixrr2113/ediththeir own version, first seen Apr 1, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- flurdy/agent-skills★ 9same name
- precise-alloy/ritus★ 1same name
- Phoenixrr2113/edith★ 0same name
- Tgoldi/claude-skills★ 0same name
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 repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- matrix/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- pick-next-taskSkill
- promote-ideaSkill
- pr-review-gateSkill
- re-extractSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
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
- Very specific: line 66
If a row is currently GAP in VALIDATION.md:
- Very specific: line 67
If the work item under review is the one named in Tracked by, verify that the PR adds the missing proof and updates the row away from GAP.
- Very specific: line 97
Run release.yml — the user has to dispatch that themselves.
“Common” is measured: kept by at least 6 in 10 of the 4 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 Task
Closes the loop between a work item's claimed acceptance and what's actually proven. Reads
the V-* rows cited in the issue's ## Validation section (per the work-item template),
looks each up in VALIDATION.md, runs the proof, reports green/red.
When to use
- A PR is about to claim
Closes #Nand you want to confirm the cited validation rows are actually green. - A user asks "is this issue really finished?"
When NOT to use
- For an issue that cites no
V-*rows (pure-doc work). There's nothing to run. - As a substitute for code review.
Procedure
- Resolve the work item. An issue number →
gh issue view <n>and pull theV-*IDs from its## Validationsection — falling back to scanning acceptance bullets for older issues that predate the template (also check any archivedtasks/done/T-*.mdfile the issue names as its full spec).T-0037→ readtasks/T-0037-npm-prerelease-dist-tag-channel.mdfrontmatter directly (the one still-in-flight file-based task). - Look up each
V-*inVALIDATION.md. Pull theProven by,Status, andTracked bycolumns. This tells you whether the invariant is already enforced, non-blocking, CI-only, or still a declared gap. Run the proof.
Run
make verify— it covers V-typecheck, V-lint, V-unit, V-tool-registry, and V-retrieval-floor in one command (requires a populated DB). It runsbun test src/mcp-contract.test.tswithoutROSETTA_REAL_DB_TESTS=1, so the real-DB blocks behind V-tool-shapes and V-tool-budget are skipped — run those separately withROSETTA_REAL_DB_TESTS=1 bun test src/mcp-contract.test.tsagainst a populated DB. For CI-only invariants (V-db-min-content, V-bunx-*) there is no local equivalent; those are only proven by a release run.For more targeted checks, map common
V-*IDs to commands:V-* ID Command V-typecheck bun run typecheckV-lint bun run lintV-unit bun testV-tool-registry bun test src/mcp-contract.test.ts(Block A, always runs)V-tool-shapes ROSETTA_REAL_DB_TESTS=1 bun test src/mcp-contract.test.ts(Block C, needs populated DB)V-tool-budget ROSETTA_REAL_DB_TESTS=1 bun test src/mcp-contract.test.ts(Block B, needs populated DB)V-retrieval-floor bun run src/eval/retrieval.tsV-retrieval-self bun run src/eval/self-supervised.tsV-canonicalize bun test src/canonicalize.test.ts src/canonicalize.fuzz.test.tsV-classifier bun test src/classify.test.tsV-schema-roundtrip bun test src/schema-roundtrip.test.tsV-extract-videos bun test src/extract-videos.test.tsV-http-handshake bun test src/mcp-http.test.tsV-stdio-handshake bun test src/mcp-stdio-client.test.tsV-tui-mcp-parity bun test src/browse-parity.test.tsV-cli-flag-uniformity bun test src/cli-help.test.tsV-db-wipe-guard bun test src/query.test.tsV-release-structure bun test src/release.test.tsFor
V-bunx-*andV-db-min-contentrows, the proof lives inrelease.yml— these can't be cleanly run locally. Note that explicitly: "this V-* is verified by CI on the next release run."If a row is currently
GAPinVALIDATION.md:- If the work item under review is the one named in
Tracked by, verify that the PR adds the missing proof and updates the row away fromGAP. - Otherwise report the row as an unresolved gap and do not recommend closing the issue.
- If the work item under review is the one named in
- Report. For each
V-*:- ✓ pass — quote the relevant
Proven bydescription so the user knows what just ran. - ✗ fail — surface the test output's failure summary.
- ⊘ CI-only — explain that this row is verified on
workflow_dispatchof release.yml; can't be checked locally. - ⚠ GAP — explain that the invariant is not yet proven, quote
Tracked by, and only consider it satisfied if the current work item is the one closing that gap.
- ✓ pass — quote the relevant
- Conclusion. Recommend merging (and letting
Closes #Nfire) only if every row is green or legitimately CI-only. If any row is failing or still GAP, don't recommend it — point at the missing proof or failing acceptance criterion. If acceptance is only partially met, remind that follow-up issues must be opened before merge (issue-pr-linking.instructions.md).
Output format
Issue: #19 — extractor safe import pattern
Validation rows: V-db-wipe-guard
V-db-wipe-guard: ✓ pass
Proven by: bun test src/query.test.ts (wipe-guard block)
Conclusion: rows green. PR may claim Closes #19 once acceptance bullets are all delivered.What this skill does NOT do
- Close issues or open/merge PRs.
- Run
release.yml— the user has to dispatch that themselves.
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.

