Docs writer
Free Claude skills for SEO content: AI humanizer, AI detection bypass, keyword preservation, agency QC, local SEO, programmatic SEO, content repurposing. Drop-in markdown for Claude projects. MIT licensed.
npx -y skills add walterwritesai/walter-skills --skill docs-writerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
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.
SKILL.md
1.6 KB, as published. Nobody here has run it
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)
- One-line summary (what this does)
- When to use it (the user's actual situation)
- How it works (mechanism, briefly)
- Parameters / Schema (table, untouched by humanizer)
- Examples (code blocks, untouched)
- Errors (table, untouched)
- 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