inspect
Skill0 starsChanged 2 months agoMITView on GitHub
Review documentation quality against its audience lens, find contradictions between documents, and check whether another agent could safely act on a document. Use for "review my docs", documentation quality checks, contradiction hunting, or before publishing.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- sanityops-org/sanityops-frameworktheir own version, first seen Nov 4, 2026
- cyrilichti/agent-workflowstheir own version, first seen Oct 17, 2026
- chalk-lab/Mooncake.jltheir own version, first seen Oct 8, 2026
- saleh-alhaddad/itqan-engineeringtheir own version, first seen Sep 29, 2026
- timelapsetech/mediaskillstheir own version, first seen Aug 15, 2026
- adezdev/blueprinttheir own version, first seen Aug 11, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- chalk-lab/Mooncake.jl★ 413same name
- Arman-Kudaibergenov/1c-ai-development-kit★ 163same name
- bluzir/claude-code-design★ 102same name
- NakaokaRei/swift-mcp-gui★ 61same name
- howardpen9/cc-inspect★ 17same name
- saleh-alhaddad/itqan-engineering★ 10same name
- HaipingShi/coderail★ 8same name
- cyrilichti/agent-workflows★ 3same name
- sanityops-org/sanityops-framework★ 3same name
- blackwell-systems/agentskills-code-inspector★ 1same name
3 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.
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 11 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 21
Read the lens for the document's class in lenses/<lens>.md and judge against it, not against your general taste.
- Very specific: line 29
Run docgov inspect contradictions --json.
- Very specific: line 49
Run docgov inspect quality --json for the deterministic dimensions (structure, grounding, cross-references, freshness).
“Common” is measured: kept by at least 6 in 10 of the 11 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
Review documentation
Deterministic findings (already decided, do not re-litigate)
!docgov check --json --compact 2>&1 | head -c 10000
What to review
Everything above is settled by software. Your job is the part software cannot decide. Work only on these four questions, and say plainly when the answer is "this is fine".
1. Audience fit — apply the right lens
Read the lens for the document's class in lenses/<lens>.md and judge against it, not
against your general taste. The lenses are: readme, developer, architecture,
security, user, agent, operations. A document that is excellent under the wrong
lens is a defect: an architecture essay inside a getting-started guide fails even if every
sentence is true.
2. Contradictions
Run docgov inspect contradictions --json. You get narrowed candidate pairs with excerpts,
not a verdict. For each:
- Genuine contradiction — two documents state incompatible facts. The higher-authority document is presumed right; name which one must change and why.
- Equal authority — no tie-break exists. This is the dangerous case. Escalate it to the user rather than picking.
- Acceptable overlap — different audiences saying the same thing differently. Leave it.
Quote the conflicting sentences. A contradiction report without the two sentences in it is unactionable.
3. Agent readiness
Could a different agent act on this document without making a wrong assumption? Check for:
unstated prerequisites, TBD/TODO that reads as fact, examples that cannot run as
written, stale version numbers, and claims with no source. This lens matters more every
month and is the one humans skip.
4. Quality scores — advisory, and say so
Run docgov inspect quality --json for the deterministic dimensions (structure, grounding,
cross-references, freshness). Add your judgement on clarity, completeness, audience fit and
security reasoning. Present the result as advice with the reasoning attached, never as a
pass/fail. Do not tell the user a document "scores 87" without saying what the missing 13
actually is.
Output
Findings ordered by what you would fix first, each with the file, the line or section, and the concrete edit. No scores without reasons. No praise padding.
Record them, so they survive the session
docgov judge --file - --agent inspect <<'JSON'
[{"check": "contradiction",
"path": "docs/getting-started.md",
"severity": "high",
"message": "States a 7-day trial; docs/product/PRD.md states 14",
"confidence": "high",
"evidence": ["docs/getting-started.md:31", "docs/product/PRD.md:88"]}]
JSONconfidence and evidence are both required — evidence is the quotes this skill already
tells you to include, and a verdict without them is rejected rather than stored. DocGov keeps
these as model-derived: docgov check prints them under JUDGEMENT, --json carries
deterministic: false, and they never change an exit code. Nothing you conclude here can
block anyone, which is what makes it safe to conclude it.
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.

