Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
spec-validation
Validates specification quality for technology-agnosticism, testability, and completeness. Automatically invoked when reviewing specs, checking requirements, or before transitioning from specify to plan phase.
majiayu000/claude-skill-registry 163
-
a2a-protocol-impl
Implement Agent-to-Agent (A2A) protocol for inter-agent communication. Use for agent discovery, agent cards, task delegation, and multi-agent orchestration. Triggers on "A2A protocol", "agent-to-agent", "agent discovery", "agent card", "multi-agent", "agent delegation", "agent communication", or when implementing spec/api/017-a2a-protocol.md.
majiayu000/claude-skill-registry 163
-
pal-thinkdeep
Multi-stage deep investigation and reasoning for complex problems using PAL MCP. Use for architecture decisions, complex analysis, performance challenges, or when you need thorough reasoning. Triggers on complex problems requiring deep thought, hypothesis testing, or expert analysis.
majiayu000/claude-skill-registry 163
-
express
Express.js framework patterns including routing, middleware, request/response handling, and Express-specific APIs. Use when working with Express routes, middleware, or Express applications.
majiayu000/claude-skill-registry 163
-
security-prompts
Library of battle-tested security prompt templates for secure feature implementation. Use when implementing forms, endpoints, authentication, authorization, file uploads, or conducting security reviews. Triggers include "security prompt", "secure form", "RBAC", "threat model", "STRIDE", "admin endpoint", "file upload", "security testing", "code review", "OWASP".
majiayu000/claude-skill-registry 163
-
property-testing-guide
Introduces property-based testing with proptest, helping users find edge cases automatically by testing invariants and properties. Activates when users test algorithms or data structures.
majiayu000/claude-skill-registry 163
-
config-auditing
Neovim configuration audit knowledge base. Use when: reviewing config files for issues, checking deprecated APIs, optimizing settings, or performing health checks. Provides checklists, best practices, and version-specific deprecated API detection patterns.
majiayu000/claude-skill-registry 163
-
feature-workflow
Orchestrate complete or partial feature implementation workflow with configurable phases. This skill should be used to run the full workflow (specification → research → plan → implement → test → fix) or specific phases, coordinating between all feature-implementation skills automatically.
majiayu000/claude-skill-registry 163
-
error-coordinator
Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters error correlation, cascade prevention, and automated recovery strategies across multi-agent systems with focus on minimizing impact and learning from failures.
majiayu000/claude-skill-registry 163
-
toolscript
Discover and execute MCP tools via gateway. Use when user asks to "call tool", "list tools", or before performing tasks that might have specialized MCP capabilities.
majiayu000/claude-skill-registry 163
-
testing-trigger
Natural language wrapper for testing commands - automatically triggers /testing:run when users request test execution
majiayu000/claude-skill-registry 163
-
write-test
테스트 코드 작성 및 실행. Use when (1) "테스트 작성해줘",
(2) "테스트 실행해줘", (3) 테스트 커버리지 확인.
⚠️ QA 테스트 요청은 별도 스킬 사용:
- Slack 알림 전송 → request-test
majiayu000/claude-skill-registry 163
-
symmetry-validation-suite
Use when you need to empirically test whether hypothesized symmetries actually hold in your data or model. Invoke when user mentions testing invariance, validating equivariance, checking if symmetry assumptions are correct, debugging symmetry-related model failures, or needs data-driven validation before committing to equivariant architecture. Provides test protocols and metrics.
majiayu000/claude-skill-registry 163
-
authorization-testing
Validate authorization failures including IDOR, privilege escalation, and missing access controls. Test by attempting unauthorized access with lower-privileged credentials. Use when testing CWE-639 (IDOR), CWE-269 (Improper Privilege Management), CWE-862 (Missing Authorization), CWE-863 (Incorrect Authorization), CWE-284 (Improper Access Control), CWE-285 (Improper Authorization), or CWE-425 (Direct Request / Forced Browsing) findings.
majiayu000/claude-skill-registry 163
-
sales-engineer
Expert sales engineer specializing in technical pre-sales, solution architecture, and proof of concepts. Masters technical demonstrations, competitive positioning, and translating complex technology into business value for prospects and customers.
majiayu000/claude-skill-registry 163
-
spike-driven-dev
Guide for spike-driven development methodology. Use when starting new features, testing architecture patterns, integrating unfamiliar APIs/data sources, or validating technical feasibility before full implementation. Emphasizes TDD, real data validation, and risk reduction through minimal proofs-of-concept.
majiayu000/claude-skill-registry 163
-
twilio-testing
Test and validate Twilio Voice API integration with ElevenLabs ConversationRelay for outbound calling. Use when setting up Twilio integration, testing outbound calls, validating audio quality, configuring webhooks, measuring call metrics, or debugging telephony issues. Includes ConversationRelay setup, call execution, and quality validation.
majiayu000/claude-skill-registry 163
-
ai-llm-inference
Operational patterns for LLM inference (recent advances): vLLM with 24x throughput gains, FP8/FP4 quantization (30-50% cost reduction), FlashInfer kernels, advanced fusions, PagedAttention, continuous batching, model compression, speculative decoding, and GPU/CPU scheduling. Emphasizes production-ready performance and cost optimization.
majiayu000/claude-skill-registry 163
-
authorization-testing
Validate authorization failures including IDOR, privilege escalation, and missing access controls. Test by attempting unauthorized access with lower-privileged credentials. Use when testing CWE-639 (IDOR), CWE-269 (Privilege Escalation), CWE-862 (Missing Authorization), CWE-863 (Incorrect Authorization), CWE-284 (Access Control), CWE-285 (Improper Authorization), or CWE-425 (Direct Request/Forced Browsing) findings.
majiayu000/claude-skill-registry 163
-
cui-java-cdi
CDI and Quarkus development standards for CUI projects, including CDI aspects, container configuration, testing, and native optimization
majiayu000/claude-skill-registry 163
-
branch
ブランチ作成Skill。仕様策定用（spec/*）または実装用（impl/*）のブランチを作成。/spec や spec-workflow から呼び出される。
majiayu000/claude-skill-registry 163
-
celery-config-patterns
Celery configuration templates for all frameworks (Django, Flask, FastAPI, standalone). Use when configuring Celery, setting up task queues, creating Celery apps, integrating with frameworks, or when user mentions Celery configuration, task queue setup, broker configuration, or framework integration.
majiayu000/claude-skill-registry 163
-
speckit-generator
Project-focused specification and task management system with 6 individual commands. Each command MUST be invoked separately and requires user approval before proceeding. Commands: /speckit.init, /speckit.plan, /speckit.tasks, /speckit.analyze, /speckit.clarify, /speckit.implement. NEVER chain commands automatically - each produces output that requires user review. Use /speckit.plan when user wants to create plans from specs. Use /speckit.tasks only AFTER user has approved plans.
majiayu000/claude-skill-registry 163
-
deployment-strategies
デプロイ戦略の選定、実装、検証、ロールバック計画を体系化するスキル。
Blue-Green/Canary/Rolling の適用判断と運用設計を整理する。
Anchors:
• Release It! / 適用: デプロイ安定性 / 目的: 本番運用の安全性
• Continuous Delivery / 適用: 段階的リリース / 目的: リスク低減
• Observability / 適用: 検証設計 / 目的: 監視による品質担保
Trigger:
Use when choosing deployment strategies, designing rollout plans, preparing rollback procedures, or validating deployment readiness.
blue green, canary, rolling deployment, rollback, smoke test
majiayu000/claude-skill-registry 163