agentleFS
speakeasy-apispeakeasy-api/kit/.agents/skills/user-docs/SKILL.md

user-docs

Skill45 starsChanged 24 days agoMITView on GitHub

Use when writing, editing, or reviewing customer-facing documentation, including docs/user pages, setup guides, feature instructions, and troubleshooting guidance.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. letehaha/moneymatter★ 221same name
    2. fullymiddleaged/Clawness★ 5same name
    3. garthcodes/claude-skills★ 2same 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 repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 6

    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
  1. Distinctive:

    Read the existing page and relevant linked guidance.

    line 11
  2. Distinctive:

    Use descriptive task headings and explicit product, command, setting, and error names so a retrieved section stands on its own.

    line 16
  3. Distinctive:

    Put limitations beside the affected action.

    line 20
  4. Distinctive:

    Keep scope focused. Do not add speculative advice, unsupported guarantees, promotional claims, or exhaustive lists of internals.

    line 21
  5. Distinctive:

    Check that examples, defaults, limits, warnings, and interface contracts remain accurate.

    line 30
  6. Distinctive:

    Check local links and changed heading anchors, code fences, and repository documentation conventions.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 3 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.

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

Problem-focused user documentation

Before editing

  • Identify the reader's problem and the action or decision the page must support. Assume the reader may be an LLM retrieving this page to solve a specific problem, without development history or surrounding conversation.
  • Read the existing page and relevant linked guidance. Check current behavior in source or CLI help when changing factual claims. Do not infer new behavior from a prose cleanup.

Write for the task

  1. Lead with the problem or desired outcome, then give the shortest useful path to the solution: prerequisites, concrete steps or a runnable example, expected result, and relevant failure recovery.
  2. Use descriptive task headings and explicit product, command, setting, and error names so a retrieved section stands on its own. Link to related tasks instead of duplicating their instructions. Preserve existing anchors or update links when renaming headings.
  3. Keep technical details that affect a reader's choice, action, safety, cost, compatibility, or troubleshooting. Exact schemas and protocol rules belong when the reader must implement that interface. Do not turn useful reference tables into vague prose or force every section into a literal problem/solution template.
  4. Remove implementation inventories, internal execution sequences, storage bookkeeping, development issue references, and descriptions of how a patch was built. Translate a mechanism into its observable consequence when that consequence matters. Move maintainer-only material to an appropriate developer reference only when it has a concrete audience and use.
  5. Describe the current supported behavior, not the chronology of its implementation. Avoid diary or changelog framing such as "now", "new", "previously", or "the existing form" unless a specific migration task requires a version distinction and an action.
  6. Put limitations beside the affected action. For troubleshooting, connect a recognizable symptom to a cause and a remedy. Retain warnings and recovery constraints; do not erase important caveats merely to shorten a page.
  7. Keep scope focused. Do not add speculative advice, unsupported guarantees, promotional claims, or exhaustive lists of internals. Prefer one canonical explanation for each task.

Example of the distinction

For resuming delegated work, explain which parent session to reopen, how to find and continue a child, whether interrupted work retries, and what to do if recovery fails. The names of stored transcript fields and the reconnect handshake do not help that reader. An adapter author may need the handshake in a separate protocol reference.

Review before finishing

  • For each paragraph, ask: what can the reader decide or do with this information? Remove or relocate material with no answer.
  • Check that examples, defaults, limits, warnings, and interface contracts remain accurate. Review deletions as carefully as additions.
  • Check local links and changed heading anchors, code fences, and repository documentation conventions. Run the smallest relevant checks.
  • For a broad audit, account for every requested page, including pages that need no changes. Report coverage and unresolved factual questions without adding the audit diary to user docs.

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.