Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
factory-qa
Phase DEBRIEF - Tests + QA + Release
majiayu000/claude-skill-registry 163
-
tdd-workflow
Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.
majiayu000/claude-skill-registry 163
-
gate-6-build-zerobias-org-module-f82eeaab
majiayu000/claude-skill-registry 163
-
discovering
Use when idea is vague, multiple interpretations exist, scope is undefined, or stakeholders need alignment before technical work begins
majiayu000/claude-skill-registry 163
-
auditing-permission-ux
Audits notification permission request flows. Use when reviewing or improving permission prompts, settings paths, or denial handling.
majiayu000/claude-skill-registry 163
-
AI Safety Auditor
Audit AI systems for safety, bias, and responsible deployment
majiayu000/claude-skill-registry 163
-
delivery-checklist-and-handoff
Ensure artifacts, validation, and rollout readiness for handoff.
majiayu000/claude-skill-registry 163
-
azure-ai
Comprehensive Azure AI skill for building, configuring, troubleshooting, and managing all Azure AI services. Covers Azure AI Foundry, Azure OpenAI Service, Azure AI Search, Azure AI Agents, Document Intelligence, Cognitive Services (Vision, Speech, Language), Azure Machine Learning, Content Safety, and Responsible AI. Use when working with AI workloads, LLM deployments, vector search, RAG patterns, multi-agent orchestration, or any Azure AI service.
majiayu000/claude-skill-registry 163
-
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
majiayu000/claude-skill-registry 163
-
test-resume
Test subagent resumption - call agent twice, verify context preserved
majiayu000/claude-skill-registry 163
-
intent-router
Route user intent to optimal skill sequences. Use when the user request is ambiguous, requires multiple skills, or needs skill sequencing. Disambiguates intent, suggests skill workflows, and handles complex multi-step tasks. Integrates with testing, linting, and quality gates. Triggers on "which skill", "what to do", "sequence", "workflow", "ambiguous request", "combine skills".
majiayu000/claude-skill-registry 163
-
currency-converter
Convert currencies with real-time exchange rates, historical data, and multi-currency calculations.
majiayu000/claude-skill-registry 163
-
simpy
Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.
majiayu000/claude-skill-registry 163
-
github_utils
Imported skill github_utils from openai
majiayu000/claude-skill-registry 163
-
review-workflow-design
Design spec-based review workflows with visual proof and issue classification. Use when setting up review processes, validating against specifications, or implementing screenshot-based visual validation.
majiayu000/claude-skill-registry 163
-
validating-design-tokens
Ensures CSS and components only use approved design tokens. Use when the user asks about design system enforcement, hardcoded colors, spacing values, or wants to validate token usage across files.
majiayu000/claude-skill-registry 163
-
adversarial-validator
Adversarial audit system for SDLC phases. Finds problems that self-validation missed.
Uses challenge mindset to identify CRITICAL to LIGHT issues.
majiayu000/claude-skill-registry 163
-
serialization
majiayu000/claude-skill-registry 163
-
using-skillpack-maintenance
Use when maintaining, enhancing, or modifying existing Claude Code plugins - handles skills, commands, agents, hooks, and reference sheets through systematic domain analysis, structure review, behavioral testing, and quality improvements
majiayu000/claude-skill-registry 163
-
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
majiayu000/claude-skill-registry 163
-
argo-expert-martinholovsky-claude-skills-genera-2
majiayu000/claude-skill-registry 163
-
viral-video-short-form-josiahsiegel-claude-plugin-market-9a9051c0
majiayu000/claude-skill-registry 163
-
fact-checker
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.
majiayu000/claude-skill-registry 163
-
tdd
Test-Driven Development enforcement skill - write tests first, always
majiayu000/claude-skill-registry 163