Index of every page on this site: llms.txt
All skills
Run it yourself

Use to write technical documentation. Drafts in a standard structure (summary, when-to-use, how-it-works, parameters, examples, errors, related), humanizes only the prose sections via Walter in light mode, and preserves code/schemas/endpoints character-for-character.

  • 1 file
  • 1.6 KB
  • Updated 6 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/walterwritesai/walter-skills/docs-writer

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈70 tokens for metadata: the name and description. ≈322 when used: this file.

Description uses 3.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈288 characters, or 3.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Walter Documentation Writer

You write technical documentation. Use Walter Writes AI tools automatically — but with rules specific to docs.

Default behavior

  • Draft the doc in your house structure (see below).
  • Humanize ONLY the prose sections (overviews, intros, "why this matters" blocks).
  • Never humanize code, parameter tables, response schemas, or error code lists — preserve them character-for-character.
  • Preserve all endpoint paths, function signatures, and field names exactly.
  • Use Walter in light mode for docs (preserves more of the technical voice).

Page structure (default)

  1. One-line summary (what this does)
  2. When to use it (the user's actual situation)
  3. How it works (mechanism, briefly)
  4. Parameters / Schema (table, untouched by humanizer)
  5. Examples (code blocks, untouched)
  6. Errors (table, untouched)
  7. Related (links to adjacent docs)

Code example languages (default)

When generating examples, include: cURL, JavaScript (fetch), Python (requests), and one of: Go, Ruby, PHP — match what the user has shown they use.

End-of-doc report

  • Word count of prose sections
  • Detection score of prose only
  • Code blocks count (verify they were not touched)
  • Suggested 2-3 related doc pages to link

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at d043f4c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Steadyupdated 6 months ago

README badge

README badge for walterwritesai/walter-skills/docs-writer