Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
code-analysis
Standardized code reading and analysis workflow with attention-driven focus. Provides clear objectives, deliverables, content outline, and token cost estimation.
majiayu000/claude-skill-registry 163
-
better-auth
Authentication patterns with Better Auth for this Next.js application.
Covers session authentication, API key authentication, dual auth, OAuth, and testing.
Use this skill when implementing or modifying authentication features.
majiayu000/claude-skill-registry 163
-
Standup
Multi-agent collaborative decision-making for complex problems. USE WHEN you need multiple specialist perspectives on high-stakes decisions (architecture, prioritization, security, compliance). Orchestrates conversation between custom agent rosters, synthesizes perspectives into actionable decisions. Finds 2-3x more issues than solo agent mode.
majiayu000/claude-skill-registry 163
-
meeting-notes-and-actions
Turn meeting transcripts or rough notes into crisp summaries with decisions, risks, and owner-tagged action items; use for Zoom/Meet/Teams transcripts, call notes, or long meeting chats to generate share-ready outputs.
majiayu000/claude-skill-registry 163
-
github
Use the `gh` CLI for issues, pull requests, Actions runs, and GitHub API queries.
majiayu000/claude-skill-registry 163
-
AgentDB Performance Optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
majiayu000/claude-skill-registry 163
-
prototype-strategy
Plan prototyping approach - fidelity levels, tool selection, prototype types, testing strategies, and design-to-development handoff.
majiayu000/claude-skill-registry 163
-
code-generator
Generate code implementation from design documents following structured phase-based workflow with token cost estimation and modification previews.
majiayu000/claude-skill-registry 163
-
blast-radius
Analyze the blast radius of code changes with risk scoring. Shows affected nodes, untested functions, and review priorities using the code knowledge graph.
majiayu000/claude-skill-registry 163
-
architecture-specialist
提供系统架构设计、技术选型、架构审查和组件设计能力。当需要设计新系统、重构现有架构或进行架构审查时使用。
majiayu000/claude-skill-registry 163
-
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
majiayu000/claude-skill-registry 163
-
1k-sentry-analysis
Analyze and fix production errors from Sentry crash reports (AppHang, ANR, crashes, stacktraces).
majiayu000/claude-skill-registry 163
-
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
majiayu000/claude-skill-registry 163
-
apify-influencer-discovery
Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.
majiayu000/claude-skill-registry 163
-
fix-issue
Fix a GitHub issue by analyzing, implementing, testing and creating a PR
majiayu000/claude-skill-registry 163
-
magento-checkout
Customize Magento 2 checkout — payment methods, shipping carriers, totals collectors, and checkout UI. Use when building custom payment/shipping integrations or modifying the checkout flow.
majiayu000/claude-skill-registry 163
-
checkpoint
Save mid-session state for recovery without clearing context. Use after major milestones, before risky operations, or periodically during long sessions.
majiayu000/claude-skill-registry 163
-
similarity-led
Use when working with LED similarity calculations - comparing LED MPNs, understanding color bins, brightness bins, families, or LED-specific similarity logic.
majiayu000/claude-skill-registry 163
-
code-review
Automated PR code review with multi-agent analysis
majiayu000/claude-skill-registry 163
-
erc8004
Register AI agent identity on Ethereum via ERC-8004 Trustless Agents standard
majiayu000/claude-skill-registry 163
-
rule-optimize
Workflow for modifying and benchmarking detection rules
majiayu000/claude-skill-registry 163
-
nw-review-workflow
Detailed review process, v2 validation checklist, and scoring methodology for agent definition reviews
majiayu000/claude-skill-registry 163
-
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
majiayu000/claude-skill-registry 163
-
verifying-layer-documentation
Use after layer analysis to detect gaps in documentation. Outputs a work list for completing-layer-documentation.
majiayu000/claude-skill-registry 163