agentleFS
alex-voloshin-devalex-voloshin-dev/ai-skills/.agents/skills/docs/SKILL.md

docs

Skill2 starsChanged 6 months agoMITView on GitHub

Documentation workflow — edit markdown docs, technical writing, blog content, release notes without touching source code. Applies Content Writer role. Includes SEO review branch for public-facing content.

170 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use import-memory, perf and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • amirbironSkill

    import-memory

    Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data.

    Also in 3 projects that use this

  • MicrosoftSkill

    perf

    Speed and memory performance rules for Rust crates, the Node addon, webui-framework, and webui-delivery.

    Also in 4 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 3 projects that use this

  • JkudjoSkill

    incident

    Production incident response — structured triage, hypothesis tree, safe remediation, incident record

    Also in 4 projects that use this

  • vbrevikSkill

    work

    Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

    Also in 7 projects that use this

  • mbwsimsSkill

    impact

    This skill should be used when the user asks to "check the impact", "what will break if I change this", "blast radius", "impact analysis", "what depends on this", "who imports this", "is it safe to change this", mentions "/impact", or wants to understand the consequences of modifying a specific file or function before making changes.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 134 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user (or extract from parent workflow):

    line 23
  2. Distinctive:

    Action: Create new / update existing / restructure

    line 29
  3. Very specific:

    Follow content-writer role standards:

    line 56

“Common” is measured: kept by at least 6 in 10 of the 134 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

Documentation

Safe documentation-only workflow. Edit markdown files without touching application source code, configs, or infrastructure. Applies content-writer role for all writing tasks.

**⚠️ CONSTRAINT: This workflow NEVER modifies source code (*.java, *.ts, *.tsx, .py, .go), configs (.yaml, .yml, .json), infrastructure (.tf, Dockerfile, Helm), or dependency files (pom.xml, package.json, requirements.txt).

1. Define Scope

Ask the user (or extract from parent workflow):

  • What documentation? (technical docs, API reference, README, PRD, design doc, ADR, blog post, release notes, UI copy)
  • Content type:
    • Internal (technical docs, design docs, ADRs) → content-writer role only
    • Public-facing (blog, landing page, marketing) → content-writer role + seo-engineer role
  • Action: Create new / update existing / restructure
  • Target files: Which .md files will be affected

2. Apply Roles

Content TypePrimary RoleAdditional Role
Technical documentationcontent-writer role—
API referencecontent-writer roleStack-specific role for accuracy
Blog / landing page contentcontent-writer roleseo-engineer role
PRD / acceptance criteriaproduct-manager role—
Architecture / ADRsolution-architect role—
Release notescontent-writer role—
UI microcopycontent-writer rolefrontend-engineer role for context
Page content (landing, product)content-designer roleseo-engineer role, ui-ux-designer role

3. Gather Context

Before writing:

  1. Read project's AGENTS.md — terminology, conventions, tech stack
  2. Read existing docs — understand structure, tone, terminology already in use
  3. Identify Diátaxis mode — Tutorial, How-to, Reference, or Explanation
  4. Check related code (read-only) — verify technical accuracy of claims

4. Write Content

Follow content-writer role standards:

  • Diátaxis framework for documentation structure
  • English only unless explicitly requested otherwise
  • Progressive disclosure — overview first, details on demand
  • Tested examples — all code snippets must be accurate
  • Consistent terminology — match existing project conventions

For Blog / Public Content

Apply geo-writer skill first — macro/meso/micro structure, answer-first sections, entity clarity, schema requirements. Then apply humanizer skill — scan for and remove AI writing patterns. Then follow seo-engineer role standards:

  • Title tag: Descriptive, matches search intent
  • Meta description: Compelling summary
  • Heading hierarchy: One H1, logical H2→H3 flow
  • Internal links: Descriptive anchor text to related content
  • Images: Descriptive alt text
  • Structured data: Article/BlogPosting schema (JSON-LD) where applicable
  • No keyword stuffing — write for users, not crawlers

5. Verify

  • All internal links are valid (no broken references)
  • Code examples are accurate and match current implementation
  • Terminology is consistent with project conventions
  • Formatting follows existing documentation patterns
  • No secrets, PII, or internal-only information in public content
  • No source code, config, or infrastructure files were modified

For Public Content — GEO/AEO Checklist

  • Text passed through geo-writer skill — structure, answer-first sentences, entity clarity
  • Schema requirements identified and JSON-LD prepared (Article, Person, Organization, FAQPage, HowTo)
  • geo-content rule satisfied

For Public Content — Humanization Checklist

  • Text scanned for AI writing patterns (humanizer skill)
  • Anti-AI audit performed for text longer than 2 paragraphs
  • Text sounds natural when read aloud

For Public Content — SEO Checklist

  • Title and meta description present and unique
  • Heading hierarchy is logical (H1→H2→H3)
  • Internal links with descriptive anchors added
  • Images have alt text
  • Page is indexable (no accidental noindex)
  • Canonical URL is correct
  • Structured data validates (Rich Results Test)

6. Summary

## Documentation Summary
- **Type**: [technical docs / blog / API reference / release notes / etc.]
- **Content mode**: [Tutorial / How-to / Reference / Explanation]
- **Files changed**:
  - [file1.md]: [created/updated — what changed]
  - [file2.md]: [created/updated — what changed]
- **Role(s) applied**: [`content-writer` role, `seo-engineer` role if public]
- **SEO review**: [pass / N/A for internal docs]
- **Verification**: [links valid, formatting correct, no code files modified]
- **Next steps**: [if any]

Integration

  • Roles: content-writer role (primary), seo-engineer role (public-facing content), product-manager role (PRDs)
  • Skills: geo-writer skill (GEO/AEO structure pass for public-facing content), humanizer skill (AI writing pattern removal for public-facing content)
  • Rules: geo-content (auto-enforces GEO structure and schema on public-facing text), humanize-content (auto-enforces humanizer pass)
  • Follow-up: seo-review skill (for public content), pre-commit skill, create-pr skill
  • Related: feature-dev skill (inline docs during development), release skill (release notes)

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.