documentation-update
Regenerates documentation files (agents.md, agent-skills.md, plugins.md, usage.md) from marketplace data using Jinja templates. Use when plugins are added, updated, or removed to keep documentation in sync.
What this skill does
# Documentation Update Skill
This skill automatically regenerates documentation files in the `docs/` directory by reading the marketplace catalog and applying Jinja2 templates.
## Purpose
Maintain synchronized documentation by:
- Generating agent reference documentation
- Creating skill catalog documentation
- Building plugin directory
- Updating usage guides
- Ensuring consistency across all docs
## When to Use
Use this skill when:
- A new plugin is added to the marketplace
- An existing plugin is updated (components added/removed)
- Agent or skill metadata changes
- Documentation needs to be regenerated
- Ensuring docs match marketplace state
## Documentation Files
This skill generates four main documentation files:
### 1. agents.md
Complete reference of all agents across all plugins:
- Organized by plugin
- Lists agent name, description, and model
- Includes links to agent files
- Shows agent capabilities and use cases
### 2. agent-skills.md
Catalog of all skills with progressive disclosure details:
- Organized by plugin
- Lists skill name and description
- Shows "Use when" triggers
- Includes skill structure information
### 3. plugins.md
Directory of all plugins in the marketplace:
- Organized by category
- Shows plugin name, description, and version
- Lists components (agents, commands, skills)
- Provides installation and usage information
### 4. usage.md
Usage guide and command reference:
- Getting started instructions
- Command usage examples
- Workflow patterns
- Integration guides
## Template Structure
Templates are stored in `assets/` using Jinja2 syntax:
```
assets/
├── agents.md.j2
├── agent-skills.md.j2
├── plugins.md.j2
└── usage.md.j2
```
### Template Variables
All templates receive the following context:
```python
{
"marketplace": {
"name": "marketplace-name",
"owner": {...},
"metadata": {...},
"plugins": [...]
},
"plugins_by_category": {
"category-name": [plugin1, plugin2, ...]
},
"all_agents": [
{
"plugin": "plugin-name",
"name": "agent-name",
"file": "agent-file.md",
"description": "...",
"model": "..."
}
],
"all_skills": [
{
"plugin": "plugin-name",
"name": "skill-name",
"path": "skill-path",
"description": "..."
}
],
"all_commands": [
{
"plugin": "plugin-name",
"name": "command-name",
"file": "command-file.md",
"description": "..."
}
],
"stats": {
"total_plugins": 10,
"total_agents": 25,
"total_commands": 15,
"total_skills": 30
}
}
```
## Python Script
The skill includes a Python script `doc_generator.py` that:
1. **Loads marketplace.json**
- Reads the marketplace catalog
- Validates structure
- Builds component index
2. **Scans Plugin Files**
- Reads agent/command frontmatter
- Extracts skill metadata
- Builds comprehensive component list
3. **Prepares Template Context**
- Organizes plugins by category
- Creates component indexes
- Calculates statistics
4. **Renders Templates**
- Applies Jinja2 templates
- Generates documentation files
- Writes to docs/ directory
### Usage
```bash
# Generate all documentation files
python doc_generator.py
# Generate specific file only
python doc_generator.py --file agents
# Dry run (show output without writing)
python doc_generator.py --dry-run
# Specify custom paths
python doc_generator.py \
--marketplace .claude-plugin/marketplace.json \
--templates plugins/claude-plugin/skills/documentation-update/assets \
--output docs
```
## Integration with Commands
The `/claude-plugin:create` and `/claude-plugin:update` commands should invoke this skill automatically after marketplace updates:
### Workflow
```
1. Plugin operation completes (add/update/remove)
2. Marketplace.json is updated
3. Invoke documentation-update skill
4. Documentation files regenerated
5. Changes ready to commit
```
### Example Integration
```python
# After creating/updating plugin
print("Updating documentation...")
# Run doc generator
import subprocess
result = subprocess.run(
["python", "plugins/claude-plugin/skills/documentation-update/doc_generator.py"],
capture_output=True,
text=True
)
if result.returncode == 0:
print("✓ Documentation updated")
else:
print(f"❌ Documentation update failed: {result.stderr}")
```
## Template Examples
### agents.md.j2
```jinja2
# Agent Reference
This document lists all agents available across plugins in the marketplace.
{% for category, plugins in plugins_by_category.items() %}
## {{ category|title }}
{% for plugin in plugins %}
### {{ plugin.name }}
{{ plugin.description }}
**Agents:**
{% for agent in all_agents %}
{% if agent.plugin == plugin.name %}
- **{{ agent.name }}** (`{{ agent.model }}`)
- {{ agent.description }}
- File: `plugins/{{ plugin.name }}/agents/{{ agent.file }}`
{% endif %}
{% endfor %}
{% endfor %}
{% endfor %}
---
*Last updated: {{ now }}*
*Total agents: {{ stats.total_agents }}*
```
### agent-skills.md.j2
```jinja2
# Agent Skills Reference
This document catalogs all skills with progressive disclosure patterns.
{% for plugin in marketplace.plugins %}
## {{ plugin.name }}
{{ plugin.description }}
**Skills:**
{% for skill in all_skills %}
{% if skill.plugin == plugin.name %}
### {{ skill.name }}
{{ skill.description }}
- **Location:** `plugins/{{ plugin.name }}/skills/{{ skill.path }}/`
- **Structure:** SKILL.md + assets/ + references/
{% endif %}
{% endfor %}
{% endfor %}
---
*Last updated: {{ now }}*
*Total skills: {{ stats.total_skills }}*
```
## Error Handling
### Marketplace Not Found
```
Error: Marketplace file not found: .claude-plugin/marketplace.json
Suggestion: Ensure marketplace.json exists
```
### Template Not Found
```
Error: Template file not found: assets/agents.md.j2
Suggestion: Ensure all template files exist in assets/
```
### Invalid Plugin Structure
```
Warning: Plugin 'plugin-name' missing components
Suggestion: Verify plugin has agents or commands
```
### Frontmatter Parse Error
```
Warning: Could not parse frontmatter in agents/agent-name.md
Suggestion: Check YAML frontmatter syntax
```
## Best Practices
1. **Always Regenerate After Changes**
- Run after every plugin add/update/remove
- Ensure docs stay synchronized
- Commit documentation with plugin changes
2. **Validate Before Generation**
- Run marketplace validation first
- Fix any errors or warnings
- Ensure all files exist
3. **Review Generated Output**
- Check generated files for correctness
- Verify formatting and links
- Test any code examples
4. **Template Maintenance**
- Keep templates simple and readable
- Use consistent formatting
- Document template variables
5. **Version Control**
- Commit documentation changes
- Include in pull requests
- Document significant changes
## Template Customization
### Adding New Sections
To add a new section to a template:
1. **Modify Template**
```jinja2
## New Section
{% for plugin in marketplace.plugins %}
### {{ plugin.name }}
[Your content here]
{% endfor %}
```
2. **Update Context (if needed)**
- Add new data to template context in doc_generator.py
- Process additional metadata
3. **Test Output**
- Run generator with dry-run
- Verify formatting
- Check for errors
### Creating New Templates
To add a new documentation file:
1. **Create Template**
- Add `assets/newdoc.md.j2`
- Define structure and content
2. **Update Script**
- Add to doc_generator.py template list
- Define output path
3. **Test Generation**
- Run generator
- Verify output
- Commit template and output
## File Structure
```
plugins/claude-plugin/skills/documentation-update/
├── SKILL.md # This file
├── doc_generator.py # Python implementation
├── assets/ # Jinja2 templates
│ ├── agents.md.j2
│ ├── agRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.