skill-development
Comprehensive 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.
What this skill does
# Skills Meta
## ๐จ MANDATORY: Invoke docs-management First
> **STOP - Before providing ANY response about Claude Code skills or slash commands:**
>
> 1. **INVOKE** `docs-management` skill
> 2. **QUERY** using keywords: skills, skill creation, YAML frontmatter, progressive disclosure, skill best practices, slash commands, command frontmatter, or related topics
> 3. **BASE** all responses EXCLUSIVELY on official documentation loaded
>
> **Skipping this step results in outdated or incorrect information.**
### Verification Checkpoint
Before responding, verify:
- [ ] Did I invoke docs-management skill?
- [ ] Did official documentation load?
- [ ] Is my response based EXCLUSIVELY on official docs?
If ANY checkbox is unchecked, STOP and invoke docs-management first.
## Overview
This meta-skill provides workflows, templates, keyword registries, and patterns for working with Claude Code skills and slash commands. Since v2.1.3+, slash commands and skills are unified -- both are invoked via the `Skill` tool. This skill covers both. It does NOT duplicate official documentation - instead, it teaches you how to efficiently query the `docs-management` skill for any skills or commands-related information you need.
**What this skill provides:**
- Skill template (5 structural patterns to choose from)
- Creation and validation workflows
- Keyword registry for efficient documentation lookups (skills and commands)
- Naming conventions and common patterns
- Quick decision trees for navigation
- Slash command keyword registry, decision tree, and troubleshooting
**What this skill does NOT provide:**
- Duplicated official documentation (use `docs-management` skill instead)
- YAML frontmatter specifications (query `docs-management`)
- Progressive disclosure details (query `docs-management`)
- Complete best practices lists (query `docs-management`)
## When to Use This Skill
This skill should be used when:
- **Creating a new skill** โ Provides template and creation workflow
- **Validating an existing skill** โ Provides validation workflow and patterns
- **Auditing skill quality** โ Provides comprehensive audit checklist and workflow
- **Understanding skill architecture** โ Directs you to right official docs
- **Needing skill templates** โ Provides 5 structural pattern options
- **Learning YAML frontmatter** โ Shows you how to query docs-management
- **Troubleshooting activation** โ Provides diagnostic patterns
- **Distributing skills** โ Provides distribution workflow
- **Creating custom slash commands** โ Provides command keyword registry and decision tree
- **Configuring command frontmatter** โ Directs to docs-management with correct keywords
- **Using command arguments** โ Provides keyword lookups for $ARGUMENTS, $1, $2
- **Working with plugin/MCP commands** โ Provides keyword registry for command types
- **Choosing skills vs commands** โ Provides comparison keyword lookups
## Quick Decision Tree
**What do you want to do?**
1. **Create a new skill from scratch** โ See [workflows/creating-skills-workflow.md](references/workflows/creating-skills-workflow.md)
2. **Validate an existing skill** โ See [workflows/validating-skills-workflow.md](references/workflows/validating-skills-workflow.md)
3. **Audit skill quality and compliance** โ See [quality/skill-audit-guide.md](references/quality/skill-audit-guide.md) or use `/audit-skills` command
4. **Test skill activation** โ See [workflows/testing-skills-workflow.md](references/workflows/testing-skills-workflow.md)
5. **Share or distribute a skill** โ See [workflows/distributing-skills-workflow.md](references/workflows/distributing-skills-workflow.md)
6. **Understand skill architecture** โ Query `docs-management` for "agent skills architecture progressive disclosure"
7. **Fix activation issues** โ See Troubleshooting section below
8. **Create a custom slash command** โ Query `docs-management`: "slash commands", "skill commands"
9. **Configure command frontmatter** โ Query `docs-management`: "command frontmatter", "allowed-tools"
10. **Use arguments in commands** โ Query `docs-management`: "$ARGUMENTS", "command arguments"
11. **Choose skills vs commands** โ Query `docs-management`: "skills vs slash commands"
12. **Work with plugin/MCP commands** โ Query `docs-management`: "plugin commands", "MCP slash commands"
## Official Documentation Discovery
### How to Query docs-management for Skills Documentation
The `docs-management` skill contains all official Claude Code skills documentation. Use natural language queries to access it:
**For creation guidance:**
```text
Find documentation about creating skills with best practices
```
**For YAML frontmatter requirements:**
```text
Locate the official YAML frontmatter specification for skills
```
**For progressive disclosure patterns:**
```text
Get the official progressive disclosure documentation for skills
```
**For tool restrictions:**
```text
Find documentation about allowed-tools configuration for skills
```
### Keyword Registry for Efficient Searches
Use these keyword combinations with the `docs-management` skill for specific topics:
**Creation & Structure:**
- Keywords: `skills`, `skill creation`, `skill structure`, `YAML frontmatter`
- Use case: Understanding how to create skills and required structure
**Validation & Quality:**
- Keywords: `skill validation`, `skill best practices`, `skill patterns`
- Use case: Ensuring skill quality and following conventions
**Architecture & Patterns:**
- Keywords: `progressive disclosure`, `skill composition`, `agent skills`
- Use case: Understanding architectural patterns and advanced topics
**Tool Configuration:**
- Keywords: `allowed-tools`, `tool restrictions`, `skills`
- Use case: Configuring which tools Claude can use within a skill
**Activation & Discovery:**
- Keywords: `skill description`, `skill activation`, `skill triggers`
- Use case: Ensuring Claude discovers and uses your skill correctly
**Distribution & Sharing:**
- Keywords: `plugin skills`, `skill locations`, `personal skills`, `project skills`
- Use case: Understanding where skills live and how to share them
**Execution Context (v2.1.x):**
- Keywords: `context fork`, `forked context`, `skill context`, `agent type skill`
- Use case: Running skills in isolated sub-agent context
**Lifecycle Hooks (v2.1.x):**
- Keywords: `skill hooks`, `hooks frontmatter`, `PreToolUse skill`, `PostToolUse skill`
- Use case: Adding hooks scoped to skill lifecycle
**Visibility Control (v2.1.x):**
- Keywords: `user-invocable`, `skill visibility`, `disable-model-invocation`, `skill menu`
- Use case: Controlling how skills appear in menus and can be invoked
**Variable Substitution (v2.1.9+):**
- Keywords: `CLAUDE_SESSION_ID`, `variable substitution`, `skill variables`, `session ID substitution`
- Use case: Using `${CLAUDE_SESSION_ID}` in skill frontmatter for session-aware configuration
- Query pattern: `docs-management: "skills.md CLAUDE_SESSION_ID variable substitution"`
**Nested Skills Discovery (v2.1.6+):**
- Keywords: `nested skills`, `.claude/skills discovery`, `skill directory nesting`, `recursive skill loading`
- Use case: Skills in nested `.claude/skills/` directories are discovered and loaded
- Query pattern: `docs-management: "skills.md nested skills discovery directories"`
**Slash Commands - Core:**
- Keywords: `slash commands`, `command overview`, `built-in commands`, `custom slash commands`
- Use case: Understanding command types, creating custom commands, viewing built-in commands
**Slash Commands - Types:**
- Keywords: `project commands`, `.claude/commands`, `personal commands`, `~/.claude/commands`, `plugin commands`, `MCP slash commands`, `mcp__server__prompt`
- Use case: Understanding project vs personal vs plugin vs MCP command locations and patterns
**Slash Commands - Configuration:**
- Keywords: `command frontmatter`, `allowed-tools`, `argument-hint`, `description`, `command model`, `model frontmatter`
- Use case: ConfigurinRelated in AI Agents
reprompter
IncludedTransform messy prompts into well-structured, effective prompts โ 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 โฅ 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.
skill-creator
IncludedCreate production-grade agent skills aligned with the 2026 AgentSkills.io spec and Anthropic best practices (2026). Also validates existing skills against the Intent Solutions 100-point rubric. Use when building, testing, validating, or optimizing Claude Code skills. Trigger with "/skill-creator", "create a skill", "validate my skill", or "check skill quality". Make sure to use this skill whenever creating a new skill, slash command, or agent capability.