revise
Skill19 starsChanged 32 days agoMITView on GitHub
Edit prose in place — restructure article drafts (reorder sections, tighten arguments) or polish markdown/text (typos, dashes, filler). Use when asked to "revise", "edit my draft", "improve my article", "fix typos", or "fix dashes" in a doc or post. Don't use for code style or linting (/check), commit messages (/commit), or writing a new doc (/to-doc).
6 other projects use a version of this.
Adopted by
Most recently taken up by
- stormlightlabs/miretheir own version, first seen Nov 1, 2026
- korya/swd-skillstheir own version, first seen Nov 1, 2026
- hsantanna88/clo-authortheir own version, first seen Oct 9, 2026
- hugosantanna/clo-authortheir own version, first seen Oct 8, 2026
- bloxy-studios/shorts-studiotheir own version, first seen Oct 1, 2026
- stormlightlabs/thunderustheir own version, first seen Sep 19, 2026
Used with
Projects with it also use submit and analyze.
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.
H-mmerSkillsubmit
Draft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.
Also in 3 projects that use this
AnthropicSkillanalyze
Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- hsantanna88/clo-author★ 262same name
- hugosantanna/clo-author★ 262same name
- stormlightlabs/thunderus★ 4same name
- korya/swd-skills★ 2same name
- stormlightlabs/mire★ 1same name
- bloxy-studios/shorts-studio★ 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 repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-auditSkill
- architecture-auditSkill
- buildSkill
- checkSkill
- codebase-designSkill
- code-reviewSkill
- commitSkill
- create-skillSkill
- debateSkill
- debugSkill
- deps-auditSkill
- domain-modelingSkill
- feedbackSkill
- frontend-ui-engineeringSkill
- grillSkill
- guideSkill
- handoffSkill
- hardenSkill
- i18nSkill
- perf-auditSkill
- prototypeSkill
- refactorSkill
- researchSkill
- retroSkill
- reviewSkill
- safe-repoSkill
- setupSkill
- source-drivenSkill
- tddSkill
- teachSkill
- to-adrSkill
- to-docSkill
- to-prSkill
- to-releaseSkill
- to-specSkill
- to-stackSkill
- to-ticketsSkill
- triageSkill
- visual-reviewSkill
- wait-whatSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
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
- Distinctive: line 17
Ask for the one takeaway the reader should remember, unless the draft already states it.
- Very specific: line 49
Run grep -nE '—| – | -- ' before and after to confirm none remain outside code.
- Distinctive: line 64
Remove filler ("very", "just", "really", "basically", "actually")
“Common” is measured: kept by at least 6 in 10 of the 5 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
Revise
Edit prose in place without changing the author's voice or meaning. Preserve code blocks, code references, technical terms, and proper nouns exactly. If no file is given, ask which.
Two depths:
- Full revise — an article draft: steps 1–4.
- Polish only — the ask is typos, dashes, AI tells, or formatting, or the file isn't an article: step 4.
1. Context
Ask for the one takeaway the reader should remember, unless the draft already states it. Assume engineers reading a public post unless told otherwise.
2. Analyze structure
Map the sections as an information DAG — each concept depends on prior concepts. Identify dependency violations (concept used before introduced), redundant sections, missing bridges, a weak intro (hook + expectations) or weak conclusion (does it reinforce the takeaway?).
Present the current outline and a proposed reordering. Wait for confirmation before rewriting. Already well-structured → skip to step 4.
3. Rewrite section by section
Edit in place, one section at a time:
- Lead with the point — first sentence states what the section proves or teaches
- Max 240 characters per paragraph — split longer ones
- Cut ruthlessly — drop sentences that don't serve the section's point
- Smooth transitions — each opening connects to the previous conclusion
- Show, don't tell — concrete examples over abstract claims
Re-read the whole for flow: intro promises what the article delivers, conclusion reinforces the takeaway.
4. Polish
One pass per category, in order: formatting → typos → AI tells → clarity. This pass only removes or substitutes; it never adds words, and never rewrites a sentence that is already clear.
Formatting
| Issue | Replace with |
—, –, or -- (with spaces) | Period, comma, colon, or parentheses depending on context |
Em dash — (no spaces) | Split into two sentences or use comma |
| Double spaces | Single space |
Run grep -nE '—| – | -- ' before and after to confirm none remain outside code.
Typos: misspellings, wrong word form ("teh", "dont"), missing apostrophes in contractions.
AI tells: cut or swap when vague, keep when it's the precise term ("robust estimator").
- "leverage", "utilize" → "use"; "delve into" → "look at"
- Cut "robust", "seamless", "powerful"
- Cut throat-clearing: "it's worth noting that", "let's dive in", "in conclusion"
- "It's not X, it's Y" → state Y
- Cut a closing sentence that only restates its paragraph
- Bold mid-sentence, emoji in headings → plain text
Clarity:
- Remove filler ("very", "just", "really", "basically", "actually")
- Split run-on sentences
- Flatten weak constructions ("is able to" → "can", "in order to" → "to")
Report structural changes (full revise), then polish changes by category.
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.

