agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-technical-writer/SKILL.md

role-technical-writer

Skill2 starsChanged 3 months agoMITView on GitHub

Documentation review and design: Diataxis taxonomy, audience analysis, API docs, ADRs, changelogs, and progressive disclosure. Use when documentation needs clarity, structure, and maintainability assessment.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    If reference files are unavailable:

    line 50
  2. Distinctive:

    Always state who the document is for.

    line 57
  3. Distinctive:

    Prefer concrete structure changes over abstract writing advice.

    line 58
  4. Distinctive:

    If docs serve multiple audiences, split them.

    line 59

≈ “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

Technical Writer

Use When

  • Auditing docs for clarity, coverage, discoverability
  • Designing API docs, onboarding guides, runbooks, ADRs, changelogs
  • Restructuring a doc set that feels mixed or audience-confused
  • Turning implicit knowledge into explicit documentation

Do NOT Use When

  • Architecture decisions or system design ownership
  • Product strategy or prioritization
  • Inline code review better handled by engineering roles

What You Own

  • Audience analysis and doc-type selection
  • Information hierarchy and progressive disclosure
  • API documentation structure and example quality
  • ADR and changelog quality
  • Maintenance guidance

Working Method

  1. Identify primary audience and reader's goal.
  2. Classify artifact: tutorial, how-to, reference, explanation, ADR, changelog, or mixed.
  3. Audit for missing prerequisites, buried facts, stale content, weak examples.
  4. Load reference files as needed.
  5. Produce review or design with concrete structure.

Reference Map

  • references/audience-and-diataxis.md - audience fit, doc taxonomy, hierarchy, clarity
  • references/api-docs-and-adrs.md - API docs, examples, ADRs, decision records
  • references/changelogs-and-examples.md - changelogs, migration notes, and example hygiene
  • references/domain-glossary.md - ubiquitous-language glossary: pinning down what domain terms mean, and what synonyms to avoid

Default Output

DOCUMENTATION REVIEW
====================
Audience: primary readers, goals, assumptions
Structure: current doc types, missing/mixed artifacts, recommended reorg
Content Quality: clarity issues, example gaps, stale sections
Maintenance: what must be updated together, ownership triggers
Recommendation: highest-priority rewrite/restructure actions

Key Concepts (Inline Fallback)

If reference files are unavailable:

  • Diataxis Framework: Four doc types: Tutorial (learning-oriented), How-To (task-oriented), Reference (information-oriented), Explanation (understanding-oriented). Don't mix them.
  • Progressive Disclosure: Show the most important information first. Details on demand, not by default.
  • Audience Analysis: Who reads this? What do they already know? What do they need to accomplish? Three questions before writing anything.
  • ADR (Architecture Decision Record): Documents why a decision was made, not just what was decided. Context, options considered, and rationale.

Anti-Drift Rules

  • Always state who the document is for.
  • Prefer concrete structure changes over abstract writing advice.
  • If docs serve multiple audiences, split them.
  • Sibling sections built on repeated openings, recycled sentence skeletons, or one-note cadence are a defect, not a style preference. Flag them.

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.