Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
claude-codex-collaboration
Enable automated collaboration between Claude Code and Codex CLI using Byterover as shared memory. This skill should be used when architectural review or code validation from Codex is desired before or after implementation. Claude creates plans, directly invokes Codex for expert review via Bash, and implements based on feedback - all automatically without manual user intervention. All context persists in Byterover.
majiayu000/claude-skill-registry 163
-
git-message-guide
コミットメッセージとPRメッセージのガイドライン。Conventional Commits形式での日本語コミットメッセージ作成、PRの概要・レビュー観点・関連Issue記載をサポート。git commit、PR作成、コミットメッセージの書き方を聞かれた時に使用する。
majiayu000/claude-skill-registry 163
-
subagent-development
Central authority for Claude Code subagents (sub-agents). Covers agent file format, YAML frontmatter, tool access configuration, model selection (inherit, sonnet, haiku, opus), automatic delegation, agent lifecycle, resumption, command-line usage (/agents), Agent SDK programmatic agents, priority resolution, and built-in agents (Plan subagent). Assists with creating agents, configuring agent tools, understanding agent behavior, and troubleshooting agent issues. Delegates 100% to docs-management skill for official documentation.
majiayu000/claude-skill-registry 163
-
hybrid-search
Use when building search systems that need both semantic similarity and keyword matching - covers combining vector and BM25 search with Reciprocal Rank Fusion, alpha tuning for search weight control, and optimizing retrieval quality
majiayu000/claude-skill-registry 163
-
graphql-fundamentals
Master GraphQL core concepts - types, queries, mutations, and subscriptions
majiayu000/claude-skill-registry 163
-
content-publisher
Handles the publication workflow for AndesRC blog articles. Creates markdown files, triggers builds, submits to Google Search Console, and initiates promotion. Use as the final step in the content pipeline.
majiayu000/claude-skill-registry 163
-
refactor-risk-assess
[Code Quality] Evaluates risk level of proposed refactoring changes. Use to assess dependencies, blast radius, rollback difficulty, and determine if changes are safe to proceed.
majiayu000/claude-skill-registry 163
-
NX Monorepo TypeScript Backend Project Setup
Sets up NX monorepo for TypeScript backend projects optimized for AI-assisted development. Delegates to NX commands where possible, patches configs as last resort. Triggers on: 'set up typescript backend project', 'create backend project', 'initialize typescript backend', 'create monorepo', or when working in an empty project folder.
majiayu000/claude-skill-registry 163
-
policyengine-aggregation
PolicyEngine aggregation patterns - using adds attribute and add() function for summing variables across entities
majiayu000/claude-skill-registry 163
-
nerves-patterns
Nerves embedded development patterns for Elixir/Nerves systems
majiayu000/claude-skill-registry 163
-
mcp-narsil
Deep code intelligence via Narsil MCP providing 76 tools for security scanning (OWASP, CWE, taint analysis), call graph analysis (CFG, DFG, callers/callees), structural queries (symbols, definitions, references), and supply chain security (SBOM, license compliance). Accessed via Code Mode for token efficiency.
majiayu000/claude-skill-registry 163
-
agent-sandboxes-disler-agent-sandbox-skill
majiayu000/claude-skill-registry 163
-
skill-a
A fake skill for testing
majiayu000/claude-skill-registry 163
-
Testing Skills With Subagents
RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
majiayu000/claude-skill-registry 163
-
session-logs
Search and analyze your own session logs (older/parent conversations) using jq.
majiayu000/claude-skill-registry 163
-
shared-name
A skill with a name that might conflict. Use for testing conflict detection.
majiayu000/claude-skill-registry 163
-
camsnap
Capture frames or clips from RTSP/ONVIF cameras.
majiayu000/claude-skill-registry 163
-
pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
majiayu000/claude-skill-registry 163
-
anthropic-streaming-patterns
Use when integrating Claude API with streaming responses, implementing tool execution in streams, tracking API costs, or encountering streaming errors - provides Anthropic SDK 0.30.1+ patterns with mandatory cost monitoring
majiayu000/claude-skill-registry 163
-
agent-communication
majiayu000/claude-skill-registry 163
-
building-chat-interfaces
Build AI chat interfaces with custom backends, authentication, and context injection.
Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context,
or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns.
NOT when building simple chatbots without persistence or custom agent integration.
majiayu000/claude-skill-registry 163
-
architecture-evolution-tracking
Track architectural decisions and detect drift from ADRs (Architecture Decision Records). Calculate alignment score (0.00-1.00) showing code-to-design conformance. Auto-detect architectural violations and suggest refactoring. Integrate with Serena for architectural health monitoring. Use when: maintaining architectural integrity, reviewing large changes, documenting decisions, detecting drift, enforcing standards.
majiayu000/claude-skill-registry 163
-
GatekeeperAgent
入口検証Agent - 不適格な問題を門前払いし、決策系の質問のみを後続Agentに渡す
majiayu000/claude-skill-registry 163
-
harness-runner
Run WaveCap-SDR test harness with automated parameter sweeps and validation. Use when regression testing, validating audio quality across configurations, testing SDR hardware, or benchmarking demodulation performance.
majiayu000/claude-skill-registry 163