readme-writer
Skill0 starsChanged 2 months agoMITView on GitHub
Measure and improve the reading level of any prose — docs, READMEs, emails, proposals, specs, plans. Scores Flesch-Kincaid grade level and top-1000 vocabulary coverage with real scripts instead of estimates. Triggers on 'readability', 'reading level', 'grade level', 'Flesch-Kincaid', 'plain language', 'make this easier to read', 'simplify this writing', 'too dense', 'ESL-friendly', and on 'write readme', 'improve readme', 'readme review', 'documentation writing'.
23 other projects use a version of this.
Adopted by
Most recently taken up by
- sandrinodm/skillstheir own version, first seen Nov 8, 2026
- vigneshm1995personal/skillgatetheir own version, first seen Nov 8, 2026
- andymartinezot/claude-skillstheir own version, first seen Nov 1, 2026
- nseney1/Soma-Governancetheir own version, first seen Nov 1, 2026
- OneByJorah/VirtOfficetheir own version, first seen Nov 1, 2026
- nseney1/Aegis-Guardrailstheir own version, first seen Oct 25, 2026
Used with
Projects with it also use security-audit.
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.
CloudflareSkillsecurity-audit
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.
Also in 3 projects that use this
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- event-driven-io/emmett★ 562same name
- OneByJorah/offivo★ 24same name
- OneByJorah/VirtOffice★ 24same name
- sandrinodm/skills★ 11same name
- nseney1/Aegis-Guardrails★ 4same name
- nseney1/Soma-Governance★ 4same name
- shimo4228/claude-harness★ 4same name
- WST2002/claude-code-skills★ 4same name
- guihai24/openskills★ 2same name
- IdkwhatImD0ing/hackathonstarterkit★ 2same name
13 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 repository10 other files it gives its agents.
- create-pull-requestSkill
- deep-researchSkill
- herdrSkill
- pr-review-loopSkill
- remixSkill
- sandi-metz-rulesSkill
- skill-creatorSkill
- tearing-down-a-merged-worktreeSkill
- test-auditSkill
- worktree-spaceSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
9
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 51
Keep noun phrases short and direct
- Distinctive: line 53
Use simple "if/then" conditionals
- Distinctive: line 66
Start with concepts, then details.
- Distinctive: line 67
Add transitions between major sections so the piece reads as a narrative, not a list of disconnected blocks
- Distinctive: line 68
Create logical progression from high-level to detailed
- Distinctive: line 72
When the document is specifically a README, it flows through these sections:
- Distinctive: line 82
Use GitHub-flavored callout blocks to highlight important information:
- Distinctive: line 90
Use bold for key concepts on first introduction
- Very specific: line 91
Use code for commands, filenames, config keys, and values
- Distinctive: line 92
Use concrete, descriptive names for examples ("Invoice Approval" not "Example 1")
“Common” is measured: kept by at least 6 in 10 of the 18 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
Readability and README Writing
Two jobs. The common one: measure and improve reading level in any prose — a doc, an email, a proposal, a spec, a plan. The narrower one: structure a README.
Always Measure — Never Estimate
Syllable counts cannot be eyeballed accurately across a document. Reporting a Flesch-Kincaid score without running the script is guessing. Run it.
cat FILE | ruby scripts/flesch_kincaid.rbWorks on any text, not just markdown — pipe in an email draft, a section of a doc, a paragraph pasted into a heredoc.
Target: grade level 11 or below. Technical terms inflate the score, and that's fine — the goal is to keep the surrounding prose clear so the technical content stays accessible.
Revise, then re-measure. Focus revision on:
- Shortening sentences (not dumbing down terminology)
- Replacing complex connectors with simple ones
- Breaking multi-clause sentences into two
Report the before and after scores.
Vocabulary Coverage
Many readers of technical writing are not native English speakers.
cat FILE | ruby scripts/vocabulary_profiler.rbAim to raise the percentage of words in the top 1000 most common English words. Technical terms lower this number — expected. Keep the non-technical words simple.
Do:
- Use active voice
- Keep noun phrases short and direct
- Limit embedded clauses to one level of nesting
- Use simple "if/then" conditionals
- Make logical connections explicit with transition words (however, therefore, because)
- Spread information across multiple sentences when needed
Don't:
- Stack multiple modifiers before nouns ("the recently revised standardized testing protocol")
- Rely on mixed or inverted conditionals ("Had she known...")
- Expect readers to infer relationships between ideas
- Pack too many new concepts into a single sentence
- Assume shared knowledge of idioms or cultural references
Flow and Transitions
- Start with concepts, then details. Give readers the "why" before the "how"
- Add transitions between major sections so the piece reads as a narrative, not a list of disconnected blocks
- Create logical progression from high-level to detailed
README Structure
When the document is specifically a README, it flows through these sections:
- What and why — what the package does and why it matters (the "what's in it for me")
- Install and use — how to get started quickly
- Configuration — common options and methods
- Contributing — how to contribute, or a pointer to CONTRIBUTING.md. Notes on the build environment and portability
- Project layout — unusual top-level directories or files, hints for navigating the source
Formatting
Use GitHub-flavored callout blocks to highlight important information:
[!CAUTION] [!IMPORTANT] [!NOTE] [!TIP] [!WARNING]
- Use bold for key concepts on first introduction
- Use
codefor commands, filenames, config keys, and values - Use concrete, descriptive names for examples ("Invoice Approval" not "Example 1")
Quality Checklist
- Flesch-Kincaid grade level measured with the script, at or below 11
- Vocabulary coverage measured; non-technical words kept simple
- Each section flows naturally into the next
- Key concepts are bolded on first use
- Examples use real scenario names, not generic placeholders
- No corporate buzzwords (comprehensive, robust, seamless, leverage, utilize)
- Terminology is consistent throughout (same word for same concept)
- Acronyms and specialized terms are defined on first use
- Active voice is used wherever possible
Bibliography
- GNU Coding Standards, https://www.gnu.org/prep/standards/html_node/Releases.html
- Software Release Practice HOWTO, https://tldp.org/HOWTO/Software-Release-Practice-HOWTO/distpractice.html
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.

