prose-audit
Skill15 starsChanged 15 days agoApache-2.0View on GitHub
Diagnose semantic repetition, filler, fake structure, stock AI rhetoric, and avoidable reading load in existing text. Trigger phrases: "/prose-audit", "find the AI filler", "audit this for bloat". Not for rewriting text; use /human-rewrite after diagnosis.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- 0mlkrizzz655335v/claude-skills-zhtheir own version, first seen Oct 15, 2026
- MatthewMair42/claude-configtheir own version, first seen Oct 12, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- 0mlkrizzz655335v/claude-skills-zh★ 2same name
- MatthewMair42/claude-config★ 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 repository95 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agent-mailboxSkill
- agent-outputSkill
- ask-gateSkill
- ask-meSkill
- audit-coupled-constantSkill
- budget-checkSkill
- build-prototypeSkill
- caller-optionsSkill
- cold-reviewSkill
- debug-taskSkill
- define-termsSkill
- defuddleSkill
- design-an-interfaceSkill
- diff-recapSkill
- directives-auditSkill
- domain-checkSkill
- double-checkSkill
- extract-signalSkill
- freshness-contractSkill
- github-syncSkill
- handoff-executeSkill
- handoffSkill
- headless-claudeSkill
- headless-codexSkill
- headless-geminiSkill
- headless-grokSkill
- headless-modelsSkill
- headless-update-modelsSkill
- headless-usageSkill
- human-drawSkill
- human-mergeSkill
- human-outputSkill
- human-rewriteSkill
- implement-taskSkill
- improve-codebase-architectureSkill
- insight-adversarialSkill
- insight-anglesSkill
- insight-assessSkill
- insight-critiqueSkill
- insight-cross-examineSkill
- insight-exploreSkill
- insight-premortemSkill
- insight-reference-classSkill
- insight-retroSkill
- insight-root-causeSkill
- insight-skill-gapSkill
- insight-test-assumptionSkill
- insight-value-of-informationSkill
- investigateSkill
- json-canvasSkill
- map-checkSkill
- map-initSkill
- map-maintainSkill
- map-rulesSkill
- map-thisSkill
- monorepo-depsSkill
- multi-agent-modeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Read references/pattern-catalog.md and the complete references/pattern-index.md before grading.
- Distinctive: line 47
If an element performs none of these jobs, it is removable.
- Distinctive: line 59
Do not call text AI-generated.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
/prose-audit
Find text that consumes attention without changing meaning, action, confidence, or evidence. Diagnose only. Do not rewrite unless the Handler also asks for it.
Read references/pattern-catalog.md and the
complete references/pattern-index.md before
grading. Treat them as search surfaces, not checklists that must appear in the
report. The index is the coverage contract. Every discussed pattern has one
stable ID from P001 through P258.
Unit of analysis
Classify each sentence or structural element by the unique job it performs:
- verdict or answer;
- claim or distinction;
- evidence or example;
- consequence or decision impact;
- necessary uncertainty, scope, or attribution;
- instruction or next action;
- navigation required by a genuinely long artifact.
If an element performs none of these jobs, it is removable. If another element already performs the same job at the same resolution, it is redundant. A style habit is not a defect when it carries deliberate tone or meaning.
Severity
- High: hides the verdict, repeats a claim, obscures evidence, creates false balance, or makes the reader process a structure that carries no distinction.
- Medium: inflates a sentence or section without changing its claim.
- Low: stock texture such as an unnecessary triad, litotes, generic transition, or polished-sounding abstraction.
Do not call text AI-generated. Report only observed patterns. One pattern is weak evidence of authorship. Dense, repeated clusters are stronger evidence of a writing habit, still not proof of origin.
Output
Lead with one verdict and the practical compression opportunity. Then report only the findings that account for most of the load:
VERDICT: <one sentence>
HIGH <pattern> -> <short quoted or located example> -> <why it adds no value>
MED <pattern> -> <example> -> <cost>
LOW <pattern> -> <example> -> <cost>
KEEP: <density or structure that is justified>
UNCHECKED: <material not inspected, or none>Combine repeated instances under one finding. Give counts only when actually counted. Do not reproduce the whole source. If the Handler asks for every hit, append a compact occurrence inventory after the verdict.
Human output. This skill's handler-facing output obeys the human-output contract (
human-output/SKILL.md).
Next skills. On completion, run the Next Skills protocol (
next-skills/SKILL.md): surface thenext-skillsrecommendations from frontmatter for the caller to pick. Offer only. Never auto-invoke.
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.

