Regenerate agent, skill, and knowledge catalog documentation from disk
Scanned 2/12/2026
Install via CLI
openskills install gitwalter/cursor-agent-factory---
name: auto-doc-catalog
description: Regenerate agent, skill, and knowledge catalog documentation from disk
type: skill
category: documentation
agents: [doc-maintainer]
knowledge: []
mcp_servers: [filesystem]
axioms: [A1, A3]
---
# Auto-Doc Catalog
## Purpose
Scan `.cursor/agents/`, `.cursor/skills/`, and `knowledge/` directories to regenerate catalog documentation. Outputs updated catalogs with current metadata extracted from frontmatter.
## When to Use
- After adding, removing, or modifying agents
- After adding, removing, or modifying skills
- After adding, removing, or modifying knowledge files
- When documentation catalogs become stale or inaccurate
## Prerequisites
- Python 3.10+ with PyYAML installed
- Access to `.cursor/agents/`, `.cursor/skills/`, and `knowledge/` directories
- Write access to documentation output directory
## Process
1. **Scan directories**: Traverse `.cursor/agents/`, `.cursor/skills/`, and `knowledge/` directories
2. **Extract metadata**: Parse YAML frontmatter from each file to extract name, description, type, category, agents, knowledge, MCP servers, and axioms
3. **Organize by category**: Group entries by category (documentation, development, testing, etc.)
4. **Generate markdown**: Create formatted markdown catalogs with table of contents, categorized listings, and cross-references
5. **Write output files**: Update catalog files in appropriate documentation location
## Example Usage
```bash
# Regenerate all catalogs
python scripts/tools/doc-maintainer.py --catalog
# Regenerate specific catalog
python scripts/tools/doc-maintainer.py --catalog --type agents
```
## Output
- `agent-catalog.md`: Complete listing of all agents with metadata
- `skills-reference.md`: Complete listing of all skills organized by category
- `knowledge-base-guide.md`: Complete listing of knowledge files with descriptions
## Best Practices
- Run catalog generation after any agent, skill, or knowledge file changes
- Use `--dry-run` to preview changes before applying
- Verify generated catalogs have correct cross-references
- Include catalog regeneration in pre-commit hooks for consistency
No comments yet. Be the first to comment!
Create Mermaid diagrams for flowcharts, sequences, ERDs, and
Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
Review a pull request or contribution deeply, explain it tutorial-style for a maintainer, and produce a polished report artifact such as HTML or Markdown. Use when asked to analyze a PR, explain a contributor's design decisions, compare it with similar systems, or prepare a merge recommendation.
Generate the stable Paperclip release changelog at releases/vYYYY.MDD.P.md by reading commits, changesets, and merged PR context since the last stable tag.