verifying-claims
Skill398 starsChanged 8 months agoMITView on GitHub
Check that a document's claims about code are actually true by reading the prose, the code, and the tests and reporting (or fixing) where they disagree. Use whenever the user wants to verify a README, guide, spec, or docstring still matches the code; whenever they mention documentation drift, doc-code sync, "is this still accurate", stale docs, or keeping docs/tests/code consistent; before publishing or merging a docs change; or as a periodic doc-accuracy sweep. The agent reads the prose's meaning directly — there is no claim-comment DSL to maintain. Pairs with TDD — the test suite is the deterministic behavioral gate, this skill is the semantic prose-vs-reality review.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jhutchison0/tacsoptheir own version, first seen Oct 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jhutchison0/tacsop★ 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 repository117 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessing-github-reposSkill
- agent-routingSkill
- animating-with-codeSkill
- api-credentialsSkill
- asking-questionsSkill
- assessing-impactSkill
- atprotoingSkill
- bm25Skill
- browsing-blueskySkill
- building-github-indexSkill
- building-github-index-v2Skill
- capturing-browser-logsSkill
- categorizing-bsky-accountsSkill
- challengingSkill
- chartingSkill
- charting-vega-liteSkill
- check-toolsSkill
- cloning-projectSkill
- closing-issuesSkill
- coding-mojoSkill
- compiling-wgslSkill
- composing-htmlSkill
- configuringSkill
- container-layerSkill
- controlling-spotifySkill
- convening-expertsSkill
- converting-filesSkill
- crafting-instructionsSkill
- creating-bookmarkletsSkill
- creating-kbSkill
- creating-mcp-serversSkill
- creating-skillSkill
- creating-videoSkill
- curating-bsky-listSkill
- deciding-with-confidenceSkill
- declaring-invariantsSkill
- declaudingSkill
- delegating-with-contextSkill
- describing-productsSkill
- detecting-tips-zonesSkill
- developing-preactSkill
- dispatching-subagentsSkill
- down-skillingSkill
- drawing-videoSkill
- drawing-with-pycairoSkill
- dunking-anonymouslySkill
- evolving-with-swarmsSkill
- exploring-codebasesSkill
- exploring-dataSkill
- extracting-keywordsSkill
- featuringSkill
- fetching-blocked-urlsSkill
- finding-skillsSkill
- flowingSkill
- forecasting-reversoSkill
- gatingSkill
- generating-patchesSkill
- generative-thinkingSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Check that what a document *says* about code is true, by reading the document, the code, and the tests together and reporting where they …
- Distinctive: line 51
Do this by reading; there are no claim markers.
- Distinctive: line 76
Run it at moments that matter — pre-publish, post-refactor, on a docs PR — not on every commit.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
verifying-claims
Check that what a document says about code is true, by reading the document, the code, and the tests together and reporting where they disagree.
What changed (v0.1 → v0.2)
v0.1 was a comment-DSL: you hand-wrote <!-- claim: ... --> next to prose and
a script checked the comment against the code. That had a fatal gap — the
comment and the prose were two artifacts stapled together, and only the comment
was checked, while humans read the prose. The prose could lie with a green run.
v0.2 drops the DSL. The reviewer is the agent: it reads the prose's meaning directly and compares it to what the code does and what the tests assert. No shadow copy, because the thing being checked is the thing the human reads. (Existing tools already own the alternatives — Gherkin binds executable scenarios, Lean's Verso transcludes facts into prose, TDD couples code to tests. This fills the remaining slot: free-prose documentation, judged.)
Division of labor — read this first
This skill does NOT gate merges and is NOT a test framework.
- The test suite (TDD/CI) owns the behavioral contract: deterministic, cheap, auditable, gated. A green check is something you can hold CI to.
- This skill owns the prose layer: does the documentation match reality? That needs semantic judgment across artifacts, which is non-deterministic and fallible — so it runs as a triggered review (before docs ship, on request, as a sweep), not as a per-commit gate. "The agent said the docs match" is not a guarantee you gate a merge on; it's a review you act on.
Tests are the anchor. The docs are correct when they agree with what the tests assert about the code. So write/keep good tests first; this skill keeps the prose pinned to them.
Procedure
- Identify the document(s) to check and the code + tests they describe.
- Gather consistent input: run
scripts/gather_context.py --doc DOC --src SRC --tests TESTS. It ast-parses source (no imports, no execution) and bundles the document text, the public API surface, and the test inventory. - Extract the claims the prose makes — every checkable assertion about the code (signatures, behavior, return shapes, defaults, guarantees, examples). Do this by reading; there are no claim markers.
- Judge each claim against the API surface and the tests:
- Does the code actually do what the prose says?
- Is the claim backed by a test, or merely asserted?
- Does it reference something that no longer exists?
- Report drift, ranked by severity, each finding citing the prose claim and the contradicting reality (file/function). Use the verdicts below.
- Optionally fix: rewrite the prose to match reality, and/or flag claims that need a test (an UNSUPPORTED claim is a missing test, not just a doc bug).
Verdicts
- PASS — the prose claim matches the code and is exercised by a test.
- FAIL — the code contradicts the claim (the doc is wrong, or the code regressed and the doc caught it).
- UNSUPPORTED — the claim matches the current code but no test backs it, so nothing protects it from future drift. Surface as a missing test.
- STALE — the claim refers to something removed or renamed.
Invoking
- "Check the README against the code before I publish it."
- "Does
docs/api.mdstill matchpkg/?" - "Sweep the docs for drift after this refactor."
Run it at moments that matter — pre-publish, post-refactor, on a docs PR — not on every commit. The deterministic gate is the test suite; this is the layer tests can't reach.
Honest limits
- Non-deterministic and fallible: a review can miss drift or misjudge. Treat output as a careful review, not a proof.
- Cost/latency: reading three artifacts and reasoning is expensive next to a test run. Don't wire it where a cheap deterministic check belongs.
- It checks prose against code+tests; it does not verify the tests themselves are correct. Garbage tests → confident-but-wrong PASS. TDD discipline upstream still matters.
When NOT to use
- As a CI merge gate (use the test suite).
- To verify behavior (write a test).
- On prose with no factual claims about code (nothing to check).
Files
scripts/gather_context.py— deterministic input bundler (doc + API surface + test inventory), ast-only, no imports.references/drift-report-example.md— what a review report looks like.
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.

