Skills Directory
A high-quality directory of capabilities for your AI agents. Standardized, portable, and ready to use with Claude Code.
Skill CLI
The package manager for AI agent skills
plan-critic
Critica planos e propostas identificando falhas, complexidade desnecessária, e alternativas mais simples. Use SEMPRE após criar um plano ou proposta.
agentic-orchestrating
Provides the "how-to" for workflow / task execution orchestration. Defines methods for planning multi-phase task/workflows, implementing them through agent delegation, managing ...
caching
Enforces Head Shakers caching conventions when implementing cache layers using React cache(), Next.js unstable_cache, Upstash Redis, and Cloudinary. This skill ensures consisten...
client-components
Enforces Head Shakers client component conventions for interactive React components with hooks, event handlers, Radix UI integration, and server action consumption. Extends reac...
cloudinary-media
Enforces Head Shakers Cloudinary media conventions when working with image uploads, URL generation, transformations, social sharing images, and photo management components. This...
server-actions
Enforces Head Shakers server actions coding conventions when creating or modifying server actions using next-safe-action, and ensures consistent client-side consumption patterns...
server-components
Enforces Head Shakers server component conventions for async data fetching, caching integration, streaming with Suspense, and SEO metadata generation. Extends react-coding-conve...
ui-components
Enforces Head Shakers UI component conventions when creating or modifying React components, forms, dialogs, and other UI elements. This skill ensures consistent patterns for Rad...
validation-schemas
Enforces Head Shakers Zod validation schema conventions when creating or modifying validation schemas. This skill ensures consistent patterns for drizzle-zod integration, custom...
database-schema
Enforces Head Shakers database schema conventions when creating or modifying Drizzle ORM table definitions, including constraints, indexes, relations, and column patterns. This ...
design-qa-skill
Skill providing design QA checklists and principles for visual review across lanes. Used by design-review agents to enforce hierarchy, spacing, color, and responsiveness.
flask-setup-for-beginners
Set up Python Flask development environment for beginners with step-by-step guidance, virtual environment creation, and troubleshooting
phoenix-ash
Phoenix + Ash Framework patterns for Werktrieb. Use when creating resources, actions, policies, or LiveViews in an Ash-based Phoenix app.
postgresql-integration
Guide developers through PostgreSQL setup, connection configuration, query patterns, and best practices
react-coding-conventions
Enforces Head Shakers React coding conventions automatically when creating or modifying React components. This skill should be used proactively whenever working with .tsx/.jsx f...
sentry-server
Enforces Head Shakers server-side Sentry monitoring conventions when implementing error tracking, performance monitoring, and breadcrumb logging in server actions, facades, midd...
sequential-thinking
Use when complex problems require systematic step-by-step reasoning with the ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal f...
code-reviewer
Performs comprehensive code reviews with customizable checklists, identifying bugs, security issues, performance problems, and style violations
conductor
Context-driven development methodology. Understands projects set up with Conductor (via Gemini CLI or Claude Code). Use when working with conductor/ directories, tracks, specs, ...
ios-testing-skill
Skill describing modern iOS testing patterns: Swift Testing vs XCTest, XCUITest best practices, and OS 3.0 expectations for coverage and flakiness.
liquid-quick
Quick Liquid syntax reference and help. Use for fast Liquid questions without full project context loading.
long-task-harness
Maintains continuity across long-running tasks that span multiple Claude Code sessions. This skill should be used when starting a complex project that will require multiple sess...
metaprompt-factory
This skill should be used when generating structured metaprompts for repeatable tasks. Triggers include "create a metaprompt for X", "generate a review prompt", "make a prompt t...
nextjs-knowledge-skill
Skill providing structured Next.js knowledge: App Router patterns, RSC usage, rendering/data strategies, and modern Next.js best practices.
serena-symbols
Symbol-based refactoring via MCP for TypeScript/JavaScript. Use for finding references, renaming symbols, safe refactoring, and type updates. Trigger with "find usages", "rename...
shopify-theme
Shopify theme development expertise (Liquid, sections, snippets, JS components). Use when working on Shopify themes or asking about Liquid syntax.
acceptance-testing
Guides product owner through systematic acceptance testing. Use when verifying acceptance criteria, checking story completion, or conducting final review before marking a story ...
blockchain-captain
Blockchain Captain - Smart contracts, DeFi, Web3, and decentralized systems specialist
broken-links
Check for broken links in documentation, markdown files, and website pages. Use when maintaining documentation, before releases, or investigating 404 errors.
claude-plugin-distribution
Packages and distributes Claude Code plugins with proper structure, documentation, and release management. Creates distribution-ready packages, generates documentation, and sets...
claude-plugin-marketplace-setup
Creates and manages plugin marketplaces for Claude Code, enabling plugin discovery, distribution, and team sharing. Generates marketplace.json files with proper schema, configur...
committing-and-publishing
Guides commit, push, and draft PR creation for stories. Use when ready to commit changes, pushing to remote, or creating a pull request for review.
compiler-development
为ANTLR4编译器项目提供专业开发指导,包括语法分析、语义分析、IR生成、代码优化和虚拟机实现。当用户需要编译器开发、ANTLR4语法设计、类型系统实现、中间代码生成或编译器优化相关帮助时使用此技能。
debugging
Systematic debugging methodology using evidence-based investigation to identify root causes. Use when encountering bugs, errors, unexpected behavior, failing tests, or intermitt...
design-captain
Design Captain - Pattern expert, architecture advisor, and scalability planner
devops-captain
DevOps Captain - Infrastructure-as-code, Kubernetes, CI/CD, and automation specialist
digdag
Expert assistance for designing, implementing, and debugging Treasure Workflow (digdag) for Treasure Data. Use this skill when users need help with workflow YAML configuration, ...
extraction-execution
Intelligent POC-to-production code extraction with architectural awareness. Analyzes dependencies, adapts patterns, makes extraction strategy decisions (copy/adapt/rewrite), mai...
feels-indexer-operations
Production-ready Feels Protocol indexer with PostgreSQL, Redis, RocksDB, complete REST API, OHLCV generation, real-time statistics, and frontend integration
jwt-oauth2
Revisar segurança OAuth2 Resource Server com JWT (issuer/jwk), escopos e conversores, garantindo aderência a Key Vault e Traefik.
kangaroo-solver
Pollard's Kangaroo algorithm for solving ECDLP on secp256k1. Use when searching for Bitcoin private keys in a known range, solving discrete log problems, or running the main puz...
manifest
MANIFEST_IO file-first execution contract. Use when: running any tool/script and you need reproducible artifacts. Triggers: manifest, manifest io, file-first, strict mode, MANIF...
master-archivist
Master Archivist - Documentation keeper, knowledge organizer, and institutional memory
mintlify-docs
Write and maintain documentation using Mintlify for developer docs, API references, and guides. Use when creating new documentation, updating existing docs, or organizing docume...
mlops-captain
MLOps Captain - Model training, deployment, monitoring, and ML lifecycle management
mobile-platforms-captain
Mobile Platforms Captain - iOS, Android, React Native, Flutter specialist
nix-justfile-development
Work with Feels Protocol Nix flake system and justfile task runner for reproducible builds, multi-shell environments, and automated workflows
qa-specialist-captain
QA Specialist Captain - Advanced testing, UAT coordination, and compliance validation
repomix-codebase-explorer
PROACTIVELY use when exploring unfamiliar codebases, analyzing remote repositories, generating reference skills from code, or needing AI-optimized context for code review. Trigg...
review-beads
Review, proofread, and refine filed Beads epics and issues
ripgrep-search
Use ripgrep (rg) for fast, intelligent code and text searching across projects. Triggers on search, ripgrep, rg, grep, find patterns, locate code, code search, find functions, f...
sales-call-scorer
Sales coaching CRM with call analysis, coaching effectiveness tracking, and ICP intelligence. Uses 3 Whys methodology (Why Buy Anything, Why Buy Us, Why Buy Now) to score calls ...
security-chief
Security Chief - Vulnerability detection, security validation, and protection enforcement
slack
This skill should be used for Slack CLI operations including workspace audits, messaging patterns, and agent communication. Triggers include "audit slack", "slack report", "send...
tacit-chaos
TacitChaos AI Agent Crew System - Pirate-themed orchestration with 23 officers and 90+ sailors
test-map-with-args
Tests map primitive with additional operation arguments
tzurot-operations
Common development operations for Tzurot v3 - Adding personalities, checking health, debugging production. Use when performing routine operations or troubleshooting issues.
architecture-guidelines
High-level system architecture including module systems, project structure, architectural decision records (ADRs), and testing strategies. Use when designing systems, reviewing ...
automation-language-selection
Choose between Shell and Python for generated automation code based on task traits. Use when automation language selection guidance is required.
axum-rust-template
Rust Axum API with Diesel ORM and DDD architecture.