plugin-development
Use when creating Claude Code plugins, writing skills, building commands, developing agents, or asking about "plugin development", "create skill", "write command", "build agent", "SKILL.md", "plugin structure", "progressive disclosure"
What this skill does
# Claude Code Plugin Development
Guide for creating effective Claude Code plugins with skills, commands, and agents.
## Plugin Structure
```
my-plugin/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata
├── skills/
│ └── skill-name/
│ ├── SKILL.md # Required
│ ├── references/ # Detailed docs
│ ├── examples/ # Working code
│ └── scripts/ # Utilities
├── commands/
│ └── command-name.md
├── agents/
│ └── agent-name.md
└── hooks/
└── hooks.json
```
## Skill Development
### SKILL.md Structure
```yaml
---
name: skill-name
description: This skill should be used when the user asks to "specific phrase 1", "specific phrase 2", or mentions "keyword". Be specific about triggers.
version: 1.0.0
---
# Skill Title
Core content here (1,500-2,000 words ideal).
## Additional Resources
- **`references/detailed.md`** - Detailed patterns
- **`examples/working.sh`** - Working example
```
### Progressive Disclosure
| Level | Content | When Loaded |
|-------|---------|-------------|
| **Metadata** | name + description | Always (~100 words) |
| **SKILL.md** | Core content | When triggered (<5k words) |
| **References** | Detailed docs | As needed (unlimited) |
### Description Best Practices
**Good:**
```yaml
description: This skill should be used when the user asks to "create a hook", "add PreToolUse hook", "validate tool use", or mentions hook events.
```
**Bad:**
```yaml
description: Provides hook guidance. # Too vague
description: Use this skill for hooks. # Not third person
```
### Writing Style
Use **imperative form**, not second person:
```markdown
# Good
Start by reading the configuration.
Validate the input before processing.
# Bad
You should start by reading...
You need to validate the input...
```
## Command Development
### Command Structure
```yaml
---
name: command-name
description: What the command does
argument-hint: "[optional args]"
---
# Command Title
Instructions for executing the command.
```
### Example Command
```yaml
---
name: review-pr
description: Review a GitHub PR with detailed code analysis
argument-hint: "[PR number or URL]"
---
# Review PR Command
1. Fetch PR details using `gh pr view`
2. Get changed files with `gh pr diff`
3. Analyze each file for issues
4. Provide summary with recommendations
```
## Agent Development
### Agent Structure
```yaml
---
agent: agent-name
description: |
When to use this agent with examples:
<example>
Context: User situation
user: "User request"
assistant: "How assistant responds"
<commentary>Why this agent is appropriate</commentary>
</example>
model: sonnet
tools:
- Read
- Glob
- Grep
- Bash
color: cyan
---
# Agent Instructions
Detailed instructions for the agent's behavior.
```
### Agent Colors
Valid colors: `red`, `green`, `yellow`, `blue`, `magenta`, `cyan`, `white`
## Hooks Development
### hooks.json Structure
```json
{
"hooks": [
{
"event": "PreToolUse",
"matcher": "Write|Edit",
"type": "prompt",
"prompt": "Validate code before writing...",
"timeout": 10000
}
]
}
```
### Hook Events
| Event | When Fired |
|-------|-----------|
| `SessionStart` | Session begins |
| `PreToolUse` | Before tool execution |
| `PostToolUse` | After tool execution |
| `Stop` | Session ends |
| `Notification` | Background task complete |
## Validation Checklist
**Skills:**
- [ ] SKILL.md has valid YAML frontmatter
- [ ] Description uses third person with trigger phrases
- [ ] Body is 1,500-2,000 words (detailed content in references/)
- [ ] Uses imperative writing style
- [ ] Referenced files exist
**Commands:**
- [ ] Has name and description in frontmatter
- [ ] Clear instructions for execution
- [ ] argument-hint if accepts parameters
**Agents:**
- [ ] Has description with examples
- [ ] Specifies model and tools
- [ ] Valid color specified
- [ ] Detailed behavioral instructions
## Common Mistakes
1. **Weak skill descriptions** - Be specific with trigger phrases
2. **Too much in SKILL.md** - Use progressive disclosure
3. **Second person writing** - Use imperative form
4. **Missing resource references** - Point to references/examples
5. **Vague agent examples** - Include concrete user/assistant pairs
Related 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.