Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
packmind-create-skill
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends CoPilot's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
rippling
Manage workforce operations with Rippling's unified HR, IT, and Finance platform.
majiayu000/claude-skill-registry 163
-
utm-builder
Generate UTM-tagged URLs for campaign tracking. Create consistent, organized tracking links for Google Analytics, HubSpot, and other analytics platforms. Supports bulk generation, naming conventions, and campaign documentation. Use when creating tracking links, campaign URLs, or organizing marketing attribution.
majiayu000/claude-skill-registry 163
-
quality-documentation-manager
Senior Quality Documentation Manager for comprehensive documentation control and regulatory document review. Provides document management system design, change control, configuration management, and regulatory documentation oversight. Use for document control system implementation, regulatory document review, change management, and documentation compliance verification.
majiayu000/claude-skill-registry 163
-
dojo-entities
Use when querying, fetching, or subscribing to game entities in dojo.js.
Triggers: entity query, fetch entities, useModel, useEntityQuery, ToriiQueryBuilder,
subscribe entities, getEntities, entity subscription, model data
majiayu000/claude-skill-registry 163
-
opentargets-database
Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.
majiayu000/claude-skill-registry 163
-
ralph-prompt-single-task
Generate Ralph-compatible prompts for single implementation tasks. Creates prompts with clear completion criteria, automatic verification, and TDD approach. Use when creating prompts for bug fixes, single features, refactoring tasks, or any focused implementation that can be completed in one session.
majiayu000/claude-skill-registry 163
-
interactive-portfolio
Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities. Use when: portfolio, personal website, showcase work, developer portfolio, designer portfolio.
majiayu000/claude-skill-registry 163
-
wcag-perceivable
Principio 1 de WCAG - contenido perceptible por todos los usuarios. Use cuando diseñe contenido multimedia, imágenes, o cualquier información visual o auditiva.
majiayu000/claude-skill-registry 163
-
nb
Manage notes, bookmarks, and notebooks using the nb CLI. Create, list, search, and organize notes across multiple notebooks with Git-backed versioning.
majiayu000/claude-skill-registry 163
-
axiom-background-processing-diag
Symptom-based background task troubleshooting - decision trees for 'task never runs', 'task terminates early', 'works in dev not prod', 'handler not called', with time-cost analysis for each diagnosis path
majiayu000/claude-skill-registry 163
-
transaction-signing-and-feedback
majiayu000/claude-skill-registry 163
-
security-hardening
Review code for application-level security hardening issues beyond framework checklists. Focuses on abuse prevention, API protection, business logic exploitation, rate limiting, input validation, and early request rejection. Use when auditing code for security, reviewing endpoints for abuse potential, or checking application resilience to real-world attacks.
majiayu000/claude-skill-registry 163
-
when-reviewing-pull-request-orchestrate-comprehensive-code-review
Use when conducting comprehensive code review for pull requests across multiple quality dimensions.
Orchestrates 12-15 specialized reviewer agents across 4 phases using star topology coordination.
Covers automated checks, parallel specialized reviews (quality, security, performance, architecture,
documentation), integration analysis, and final merge recommendation in a 4-hour workflow.
majiayu000/claude-skill-registry 163
-
security-hardening
Review code for application-level security hardening issues beyond framework checklists. Focuses on abuse prevention, API protection, business logic exploitation, rate limiting, input validation, and early request rejection. Use when auditing code for security, reviewing endpoints for abuse potential, or checking application resilience to real-world attacks.
majiayu000/claude-skill-registry 163
-
skill-reviewer
既存スキルの品質をレビューし、改善提案を行うスキル。
以下の状況で使用:
(1) ユーザーが「[スキル名]をレビューして」「[スキル名]の品質を確認して」「[スキル名]を評価して」と依頼した時
(2) ユーザーが明示的に「/skill-reviewer [スキル名]」を実行した時
(3) スキル開発完了後、「公開前にチェックして」「最終確認して」と求められた時
(4) スキル改善時、「どこを直すべきか教えて」「改善点を提案して」と相談された時
(5) スキル設計時、「このスキルの設計をレビューして」と依頼された時
majiayu000/claude-skill-registry 163
-
creative-image-generator
Генерация рекламных изображений через Gemini. Используй для создания креативов с текстом.
majiayu000/claude-skill-registry 163
-
use-plan-execute
Use when you have a written implementation plan to execute in a separate session with review checkpoints
majiayu000/claude-skill-registry 163
-
agent-evals
Design and implement evaluation frameworks for AI agents. Use when testing agent reasoning quality, building graders, doing error analysis, or establishing regression protection. Framework-agnostic concepts that apply to any SDK.
majiayu000/claude-skill-registry 163
-
clojure-coffi
Coffi FFI library for calling native C code from Clojure via Panama FFM API (JDK 22+). Use when: wrapping native C libraries, calling native functions, working with off-heap memory and arenas, etc.
majiayu000/claude-skill-registry 163
-
aptos-expert
Expert on Aptos blockchain, Move language, smart contracts, NFTs, DeFi, and Aptos development. Triggers on keywords aptos, move, blockchain, smart contract, nft, defi, web3, mainnet, testnet, devnet
majiayu000/claude-skill-registry 163
-
ai-problems-detection
Protocolo de autodiagnostico contra os 5 problemas mais comuns da IA ao programar. Detecta overengineering, codigo duplicado, reinvencao da roda, falta de documentacao e arquivos monoliticos. Use SEMPRE antes de implementar, ao planejar mudancas, quando criar funcoes novas, ao escrever codigo, para revisar implementacoes. Palavras-chave - simples, duplicado, repetido, existe, separar, modular, documentacao, complexo, refatorar, engenharia demais, roda, reutilizar.
majiayu000/claude-skill-registry 163
-
dspy-output-refinement-constraints
This skill should be used when the user asks to "refine DSPy outputs", "enforce constraints", "use dspy.Refine", "select best output", "use dspy.BestOfN", mentions "output validation", "constraint checking", "multi-attempt generation", "reward function", or needs to improve output quality through iterative refinement or best-of-N selection with custom constraints.
majiayu000/claude-skill-registry 163
-
omc-setup
Setup and configure oh-my-gemini (the ONLY command you need to learn)
majiayu000/claude-skill-registry 163