agent-ops-docs
Documentation management for README, CHANGELOG, API docs, and user-facing documentation. Use when creating or updating project documentation.
Best use case
agent-ops-docs is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Documentation management for README, CHANGELOG, API docs, and user-facing documentation. Use when creating or updating project documentation.
Teams using agent-ops-docs should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-ops-docs/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-ops-docs Compares
| Feature / Agent | agent-ops-docs | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Documentation management for README, CHANGELOG, API docs, and user-facing documentation. Use when creating or updating project documentation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Documentation Workflow
## Purpose
Manage user-facing documentation (README, CHANGELOG, API docs) with consistency and traceability. Ensures documentation stays synchronized with code changes.
## When to Use
- After implementing a feature that affects public API or usage
- When creating a new project (initial README)
- Before release (CHANGELOG update)
- When user requests documentation updates
- During critical review (docs consistency check)
## Documentation Types
### README.md
**Purpose**: First point of contact for new users/developers
**Required Sections**:
- Project title and description
- Installation/setup instructions
- Basic usage examples
- Configuration options (if applicable)
- Contributing guidelines (or link)
- License
**Update Triggers**:
- New feature that changes usage
- Installation process changes
- Dependencies change significantly
- Project scope/purpose evolves
### CHANGELOG.md
**Purpose**: Track notable changes between versions
**Format** (Keep a Changelog standard):
```markdown
# Changelog
All notable changes to this project will be documented in this file.
## [Unreleased]
### Added
- New feature X
### Changed
- Modified behavior Y
### Fixed
- Bug fix Z
### Removed
- Deprecated feature W
## [1.0.0] - YYYY-MM-DD
### Added
- Initial release features
```
**Update Triggers**:
- Any user-facing change
- Bug fixes
- Breaking changes (MUST document)
- Deprecations
### API Documentation
**Purpose**: Technical reference for developers
**Formats**:
- Inline docstrings (for code-level docs)
- OpenAPI/Swagger (for REST APIs)
- TypeDoc/JSDoc (for TypeScript/JavaScript)
- Sphinx/MkDocs (for Python)
**Update Triggers**:
- New public function/method/endpoint
- Parameter changes
- Return type changes
- Behavior changes
## Procedure
### Creating Documentation
1. **Identify audience**: Who will read this?
2. **Determine scope**: What must be covered?
3. **Check constitution**: Any doc-related constraints?
4. **Draft content**: Use appropriate template
5. **Review for accuracy**: Cross-check with code
6. **Update focus.md**: Note what was documented
### Updating Documentation
1. **Identify what changed**: Feature, API, behavior?
2. **Find affected docs**: README? CHANGELOG? API docs?
3. **Make minimal update**: Only what's necessary
4. **Verify examples work**: Run any code snippets
5. **Update CHANGELOG**: If user-facing change
6. **Update focus.md**: Note the update
### Documentation Review Checklist
- [ ] Accurate: Matches current code behavior
- [ ] Complete: Covers all public interfaces
- [ ] Clear: Understandable by target audience
- [ ] Examples: Working code samples included
- [ ] Up-to-date: No references to removed features
- [ ] Consistent: Terminology matches codebase
## Templates
### README Section Template
```markdown
## Feature Name
Brief description of what this feature does.
### Usage
\`\`\`language
// Example code showing basic usage
\`\`\`
### Configuration
| Option | Type | Default | Description |
|--------|------|---------|-------------|
| option1 | string | "default" | What it does |
### Notes
Any important caveats or tips.
```
### CHANGELOG Entry Template
```markdown
## [Version] - YYYY-MM-DD
### Added
- **Feature name**: Brief description ([#issue](link))
### Changed
- **Component**: What changed and why ([#issue](link))
### Fixed
- **Bug description**: How it was fixed ([#issue](link))
### Breaking Changes
- **What broke**: Migration instructions
```
## Integration with AgentOps Workflow
### During Planning
- Identify docs that will need updates
- Add doc tasks to plan if significant
### During Implementation
- Update inline docs as code is written
- Note doc updates needed in focus.md
### During Critical Review
- Verify README accuracy
- Verify CHANGELOG is updated
- Check for stale documentation
### After Completion
- Final CHANGELOG entry
- README updates if needed
- API doc regeneration if applicable
## Location Rules
| Doc Type | Location | Notes |
|----------|----------|-------|
| README | Project root | Always `README.md` |
| CHANGELOG | Project root | Always `CHANGELOG.md` |
| API docs | `docs/` or `doc/` | Follow project convention |
| Agent docs | `.agent/docs/` | Internal agent documentation only |
## Anti-Patterns
- ❌ Documentation in code comments only (not discoverable)
- ❌ Outdated examples that don't work
- ❌ Documenting implementation details (unstable)
- ❌ Duplicating info across multiple docs
- ❌ Empty CHANGELOG entries ("various fixes")
- ❌ Version numbers without dates
```Related Skills
crawl-docs-skill
Run a Crawl4AI-based doc crawler and save internal pages as Markdown using page titles as filenames. Use when the user provides a docs URL and wants all internal subpages saved as .md files. Environment setup should only use uv.
coder-docs
Index + offline snapshot of coder/coder documentation (progressive disclosure).
cgr-docs-governance
Use this skill when updating project documentation after backend/frontend operational changes, incidents, workflow behavior changes, or new runbooks.
athlete-docs
Documentation guidance for competition athletes and volunteers in WODsmith. Use when writing, reviewing, or improving athlete-facing documentation including registration, scheduling, workout viewing, leaderboards, check-in, and volunteer coordination.
assistant-ui-docs
Extra documentation for `assistant-ui`. Use this to find offline resources about `assistant-ui`.
api-docs
Expert API documentation including OpenAPI specs, endpoint documentation, and SDK guides
anydocs
Generic Documentation Indexing & Search. Index any documentation site (SPA/static) and search it instantly.
ancplua-docs
Search and answer questions about the ANcpLua ecosystem documentation. Use when users ask about ANcpLua.NET.Sdk features, ANcpLua.Analyzers rules, ANcpLua.Roslyn.Utilities APIs, or any configuration/usage questions about these packages.
agentic-docs
Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation like file headers, function docs, architectural decisions, or explanatory comments. Works well for both human readers and AI coding assistants who see one file at a time.
agent-ops-mkdocs
MkDocs documentation site management: initializing, updating, building, and deploying
agent-ops-create-technical-docs
Create focused, specific technical documentation for codebase sections. Analyzes code, identifies topics, presents options before writing. Supports code blocks with line numbers.
add-neon-docs
Use this skill when the user asks to add documentation, add docs, add references, or install documentation about Neon. Adds Neon best practices reference links to project AI documentation (CLAUDE.md, AGENTS.md, or Cursor rules). Does not install packages or modify code.