agentleFS
yasuyukiyasuyuki/agent-skills/skills/optimize-human-docs/SKILL.md

optimize-human-docs

Skill0 starsChanged 14 days agoMITView on GitHub

Create or revise human-facing READMEs, manuals, and procedures around the reader's decisions and actions, removing unnecessary explanation while preserving usable conditions. Use for human-facing portions of mixed documents, not agent execution rules.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep a README as an entry point: purpose, shortest usable start, and links to needed detail.

    line 14
  2. Distinctive:

    Remove redundant background, equivalent statements, and branches the reader does not need.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Optimize human documentation

Identify what the reader needs to decide or do from the request and available document. Preserve its language. Read relevant source or help only when needed to resolve a factual claim; sufficient supplied information needs no extra questions or investigation.

Keep a README as an entry point: purpose, shortest usable start, and links to needed detail. Put necessary goal-oriented explanations in the appropriate manual, reusing an existing one when possible. A procedure needs an identifiable target, separately testable prerequisites, ordered actions, and observable success. Do not assume the reader has the original conversation.

Remove redundant background, equivalent statements, and branches the reader does not need. Preserve the conditions that distinguish targets or outcomes: packing several prerequisites into one sentence, replacing concrete objects with vague nouns, or inventing a path is not simplification. Resolve unknowns from available evidence; leave a material gap explicit or ask for the missing fact instead of making it up.

Retain explanations that help a person choose and use a feature even when its implementation is readable. For specification values, arguments, and defaults, refer to the accessible authoritative source or help instead of maintaining a second handwritten catalogue. Keep enough context to make the reference useful.

Return the smallest sufficient document change, or no change when the document already serves its reader. Do not add a document, report, template, or word-count target merely to show work. A documentation request does not authorize executing the documented operations. When actually handing work to a person and human-handoff is available, use it for the handoff details; its absence does not prevent this document edit.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.