agent-audit
Validates agent configurations for model selection, tool permissions, focus areas, and approach quality. Use when reviewing, auditing, improving agents, or learning agent best practices.
agent-authoring
Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practices.
audit-coordinator
Orchestrates comprehensive audits of Claude Code customizations using specialized auditors. Use when auditing multiple components, asking about naming/organization best practices, or needing thorough validation before deployment.
bash-audit
Audits shell scripts for security, quality, and best practices using defensive programming and ShellCheck. Use when reviewing, linting, or improving bash/sh/zsh scripts for vulnerabilities, portability, or errors.
bash-authoring
Expert in production-grade Bash scripting with defensive programming, error handling, and portability. Use when writing, creating, or improving shell scripts for automation, CI/CD, or system utilities.
command-audit
Audits command files for correctness and best practices. Use when reviewing, improving, or validating commands, checking frontmatter, assessing structure, or learning command quality standards.
command-authoring
Guide for authoring slash commands. Use when creating, building, reviewing, or improving commands, learning command best practices, or deciding when to use commands vs skills.
editing-assistant
Text editing assistant with specialized modes for typos, grammar, flow, headings, citations, and more. Use when editing, proofreading, or improving written content including documentation and markdown files.
git-workflow
Automates git workflows with branch management, atomic commits, history cleanup, and PRs. Use when committing, pushing, creating PRs, cleaning up commits, or organizing git changes with best practices.
hook-audit
Audits Claude Code hooks for correctness, safety, and performance. Use when reviewing, validating, or debugging hooks, checking exit codes, error handling, or learning hook best practices.
map-codebase
Analyze codebase with parallel Explore agents to produce .planning/codebase/ documents. Use for brownfield project onboarding, refreshing codebase understanding after significant changes, before major refactoring, or when onboarding to unfamiliar codebases. Creates structured documentation of stack, architecture, structure, conventions, testing, integrations, and concerns.
organize-folders
Provides guidance on organizing folder structures and file system layouts for any project. Use when planning project organization, reorganizing messy directories, setting up folder hierarchies, designing directory layouts, structuring repositories, cleaning up files, suggesting folder structures, establishing naming conventions, or when you need help with folder structure or file organization. Helps with writing projects, code projects, document collections, or any file organization task.
output-style-audit
Validates output-style persona definitions, behavior specifications, and keep-coding-instructions decisions. Use when auditing, reviewing, or improving output-styles, checking persona clarity, validating behavior concreteness, or verifying scope alignment (user vs project). Triggers when user asks about output-style best practices or needs help with persona definition.
output-style-authoring
Guide for authoring output-styles that transform Claude's behavior and personality. Use when creating, writing, designing, building, reviewing, or improving output-styles, persona modes, or behavior modifications. Helps with style files, keep-coding-instructions decisions, persona design, and choosing between output-styles, agents, and skills. Expert in style best practices.
skill-audit
Audits skills for discoverability and triggering effectiveness. Use when reviewing skill descriptions, checking trigger coverage, validating progressive disclosure, fixing invocation issues, or learning skill best practices.
skill-authoring
Guide for authoring effective skills that extend Claude's capabilities. Use when creating, updating, or improving skills, learning skill structure, progressive disclosure, or troubleshooting skill issues.