100yenadmin100yenadmin/fable-token-saving-skills-orchestrator/skills/public-readme-polisher/SKILL.mdpublic-readme-polisher
Skill100 starsChanged 4 months agoMITView on GitHub
Use when improving a public README, repository homepage, docs landing page, or developer-facing first impression.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codex-dispatchSkill
- fable-orchestrator-routerSkill
- public-repo-operationalizerSkill
- run-economicsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
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 26
Add scanning structure: quick start, workflow diagram when useful, proof or sources near the claim, and links to deeper docs.
- Distinctive: line 32
Use one purposeful hero only when it clarifies the repo.
- Distinctive: line 37
Add alt text that explains the image function.
- Distinctive: line 44
Avoid guaranteed savings, official endorsement, universal safety claims, or "works for every workflow" language.
- Distinctive: line 46
Keep related tools optional unless the repo truly depends on them.
≈ “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
Public README Polisher
Polish the README as the repo's public front door: credible, scannable, actionable, and claim-safe.
Use When
- a README feels plain
- a repo needs a public first impression
- a docs landing page needs clearer value, install path, or proof
- a visual asset could make the repo easier to understand
Process
- Audit repo truth: purpose, install path, tests, license, security, CI, docs, examples, and public claim boundaries.
- Define the public promise in one paragraph: who it helps, what it gives them, and what it does not guarantee.
- Improve the first viewport: title, optional hero, badges, concise opening, quick action, and a scannable "what you get" table.
- Add scanning structure: quick start, workflow diagram when useful, proof or sources near the claim, and links to deeper docs.
- Validate links, images, alt text, docs scan, tests, and the scorecard below.
Visual Asset Rules
- Use one purposeful hero only when it clarifies the repo.
- For generated images: no embedded text, no logos, no watermarks.
- Inspect the image before committing; reject generated image with readable fake text, broken UI, mascot drift, or misleading claims.
- Save README assets under
assets/readme. - Add alt text that explains the image function.
Claim Safety
- Cite official sources for factual pricing, cache, legal, API, or security claims.
- Say "patterns that worked for us" for experience-based recommendations.
- Avoid guaranteed savings, official endorsement, universal safety claims, or "works for every workflow" language.
- Keep related tools optional unless the repo truly depends on them.
Scorecard
Score each category 0-2. Pass at 13/16 or higher.
| Category | 2 means |
| First-viewport signal | repo purpose, visual tone, badges, and install path are clear without scrolling |
| Audience/value clarity | reader knows who it is for and what problem it solves |
| Scannability | tables, bullets, headings, and diagrams make scanning easy |
| Actionability | quick start and next links are concrete and current |
| Trust/proof | sources, CI, license, tests, and safety boundaries support the claims |
| Visual polish | assets feel intentional, domain-fit, and not generic stock decoration |
| Accessibility/asset hygiene | alt text, local paths, file size, and image rendering are sane |
| Claim safety | claims are bounded, sourced where needed, and public-safe |
Automatic blockers: private paths, secrets, broken local links, missing install path, false or guaranteed claims, generated image with readable fake text, missing alt text, failing docs scan.
Common Mistakes
- Making a marketing page that hides the actual install/use path.
- Adding a pretty image that does not explain the repo.
- Moving official citations away from the claims they support.
- Replacing precise safety boundaries with vague hype.
- Claiming completion without running the scorecard.
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.