quality
Skill233 starsChanged 5 months agoMITView on GitHub
E-E-A-T, Trust and Readability fixes. Leaves only what you alone can give.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-toolword for word, first seen Nov 8, 2026
- menot-you/n-soultheir own version, first seen Nov 1, 2026
- DataWithBaraa/claude-code-data-engineering-skillstheir own version, first seen Nov 1, 2026
- tam159/next-roletheir own version, first seen Nov 1, 2026
- google-gemini/gemini-clitheir own version, first seen Oct 13, 2026
- boostsecurityio/poutinetheir own version, first seen Oct 8, 2026
Used with
Projects with it also use debug, review and 1 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.
AnthropicSkilldebug
Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
Also in 4 projects that use this
SentrySkillreview
Fixture review skill.
Also in 5 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 1
Edited · 0
None found.
Wrote their own version · 11
- google-gemini/gemini-cli★ 109ksame name
- H-mmer/pentest-agents★ 815same name
- boostsecurityio/poutine★ 533same name
- DataWithBaraa/claude-code-data-engineering-skills★ 84same name
- tam159/next-role★ 67same name
- ariaxhan/kernel-claude★ 15same name
- stevehansen/eidet★ 4same name
- websublime/mister-anderson★ 3same name
- GlamgarOnDiscord/claude-saas-blueprint★ 2same name
- menot-you/n-soul★ 0same name
1 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 repository33 other files it gives its agents.
- analyzeSkill
- ansvisor-aeo-coachSkill
- ansvisor-aeo-coach-standaloneSkill
- answerfirstSkill
- audit-fixSkill
- auditSkill
- beatSkill
- compareSkill
- createSkill
- factsSkill
- fanoutSkill
- faqSkill
- featuresSkill
- gapsSkill
- imageSkill
- listingsSkill
- marketsSkill
- new-reportSkill
- opportunitiesSkill
- optimizeSkill
- promptsSkill
- publishSkill
- questionsSkill
- refreshSkill
- reportSkill
- rivalsSkill
- setupSkill
- shoppingSkill
- startSkill
- tasksSkill
- translateSkill
- winbackSkill
- wrongclaimSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
4
Distinctive
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 29
E-E-A-T: no author, no first-hand experience, no examples.
- Distinctive: line 41
Don't invent quotes, authors, credentials, studies, customers or figures to pass a check.
- Distinctive: line 42
Keep the passages AI quotes word for word.
- Distinctive: line 43
Don't change what a passage claims: only how it says it.
“Common” is measured: kept by at least 6 in 10 of the 9 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
Quality pass
Make the fixes a draft's Quality checks ask for (E-E-A-T, Trust and Readability), and leave a short list of what only the person can add.
When to use
- "Run a quality pass on the drafts under 60", "Fix this draft's readability", "What does this draft still need?"
- The Quality tab in the Content Editor shows each draft's scores. When the person names no drafts, ask which ones, or list the drafts and let them pick.
What to read
list_drafts: the brand's drafts, latest changed first.get_draftfor each draft you work on, at most three in one run: its passages, its sources, and which passages AI quotes (locked).
Steps
- For each draft, find what the checks look for:
- Readability: sentences over about 25 words, paragraphs over about 5 sentences, jargon without a definition.
- Trust: claims without a source, figures without a date, a missing disclosure where the brand compares itself or recommends its own product.
- E-E-A-T: no author, no first-hand experience, no examples.
- Structure: headings that don't say what the section answers, a missing FAQ or schema.
- Fix what you can fix from the draft itself: split sentences, reorder, add headings, define terms, mark claims that need a source.
- Give the fixes as Before and After for each passage. When the person wants them kept as a new draft, save it with
create_draft; the app asks them first when it should. In an agent's run nobody is there to ask: always save it with its tool, and the app holds it for approval where the agent's mode needs it. - List what only the person can give: quotes, first-hand data, customer examples, the author and their credentials, sources for marked claims.
Output
For each draft: the fixes made, then "Only you can add" as a short to-do list.
Don't
- Don't invent quotes, authors, credentials, studies, customers or figures to pass a check.
- Keep the passages AI quotes word for word.
- Don't change what a passage claims: only how it says 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.

