Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Routing
Standards for Angular Router, Lazy Loading, and Guards.
majiayu000/claude-skill-registry 163
-
appellant-brief
Drafts the appellant's opening brief challenging a lower court decision in federal or state appellate courts. Covers issue selection, standard of review framing, record citation, argument structure, and procedural compliance under FRAP 28/32 or state equivalents. Use when preparing an appellant's opening brief, selecting appellate issues, structuring appellate arguments, or demonstrating reversible error on appeal.
majiayu000/claude-skill-registry 163
-
taboola-launcher
Launch complete Taboola native ad campaigns with AI-generated creative assets. Use when user wants to create a new Taboola campaign, launch native ads for mortgage (or other verticals), or run "/launch-taboola". Orchestrates Taboola, RedTrack, Presales, and Gemini Image MCP tools to generate headlines, images, landing pages, set up tracking, and create campaigns. All campaigns start PAUSED until explicit "/taboola-unpause".
majiayu000/claude-skill-registry 163
-
inboxzero
Autonomous email triage powered by AI. Connects to any email provider via IMAP, auto-labels, archives, drafts replies, and surfaces only what matters. Use when: drowning in email, want smart filtering beyond Gmail filters, or need automated triage. NOT for: sending bulk email, newsletter management, or email marketing campaigns.
majiayu000/claude-skill-registry 163
-
clay-sdk-patterns
Apply production-ready Clay SDK patterns for TypeScript and Python.
Use when implementing Clay integrations, refactoring SDK usage,
or establishing team coding standards for Clay.
Trigger with phrases like "clay SDK patterns", "clay best practices",
"clay code patterns", "idiomatic clay".
majiayu000/claude-skill-registry 163
-
review-standard
Systematic code review skill checking documentation quality and promoting code reuse
majiayu000/claude-skill-registry 163
-
capture-tasks-from-meeting-notes
Analyze meeting notes to find action items and create Jira tasks for assigned work. When Claude needs to: (1) Create Jira tasks or tickets from meeting notes, (2) Extract or find action items from notes or Confluence pages, (3) Parse meeting notes for assigned tasks, or (4) Analyze notes and generate tasks for team members. Identifies assignees, looks up account IDs, and creates tasks with proper context.
majiayu000/claude-skill-registry 163
-
testing-library
Enforces best practices for unit testing with Jest, @testing-library/react-native, and jest-expo in Expo projects. This skill should be used when writing, reviewing, or debugging unit tests to ensure tests are accessible, maintainable, and follow Testing Library guiding principles. Use this skill for test file creation, query selection, async handling, mocking patterns, and Expo Router testing.
majiayu000/claude-skill-registry 163
-
lp-weekly
S10 weekly orchestration wrapper. Coordinates the full weekly decision, audit/CI, measurement compilation, and experiment lane flows into one deterministic sequence. Additive-first; never replaces canonical S10 authorities. No new hard stage blocks in first iteration.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills, adding skill references, skill scripts or optimizing existing skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, frameworks, libraries or plugins usage, or API and tool integrations.
majiayu000/claude-skill-registry 163
-
COMPLIANCE_CHECK
Apply the OpenAI SDK compliance checklist to audit files or directories and produce a Markdown report with findings and suggested fixes. Use when asked to "check compliance", "run compliance check", or "audit against OpenAI SDK rules".
majiayu000/claude-skill-registry 163
-
team-ultra-analyze
Deep collaborative analysis team skill. All roles route via this SKILL.md. Beat model is coordinator-only (monitor.md). Structure is roles/ + specs/. Triggers on "team ultra-analyze", "team analyze".
majiayu000/claude-skill-registry 163
-
Defense-in-Depth Validation
Validate at every layer data passes through to make bugs impossible
majiayu000/claude-skill-registry 163
-
gemini-files
Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".
majiayu000/claude-skill-registry 163
-
python
Python skill router. Use when planning, implementing, or reviewing Python changes and you need to select focused skills for workflow, design, typing/contracts, reliability, testing, data/state, concurrency, integrations, runtime operations, or notebook async behavior.
majiayu000/claude-skill-registry 163
-
ai-schema
Use when designing schemas, writing migrations, optimizing queries, or managing data lifecycle across PostgreSQL, MySQL, SQLite, and MongoDB.
majiayu000/claude-skill-registry 163
-
weather
Get current weather and forecasts (no API key required).
majiayu000/claude-skill-registry 163
-
bugfix
Execute a complete bugfix workflow for wouterwisse.com using Opus subagents. Investigates root cause, implements fix, and verifies no regressions.
majiayu000/claude-skill-registry 163
-
HTML Injection Testing
This skill should be used when the user asks to "test for HTML injection", "inject HTML into web pages", "perform HTML injection attacks", "deface web applications", or "test content injection vulnerabilities". It provides comprehensive HTML injection attack techniques and testing methodologies.
majiayu000/claude-skill-registry 163
-
planetscale
Operate MySQL-compatible databases on PlanetScale with branching workflows, safe migrations, and production rollouts.
majiayu000/claude-skill-registry 163
-
langchain-agents
LangChain & AI Agent Frameworks expert. Covers LCEL chains, ReAct/Plan-and-Execute/Multi-Agent architectures, tool calling, memory systems, LangGraph, CrewAI, prompt engineering, streaming, LangSmith tracing, RAG integration, and production deployment patterns.
majiayu000/claude-skill-registry 163
-
git-worktree
Create, inspect, and clean up Git worktrees for parallel TermLink branch development. Use when starting isolated feature or bugfix work in a separate directory, checking which branches already have attached worktrees, removing stale worktrees after merge, or pruning orphaned worktree metadata.
majiayu000/claude-skill-registry 163
-
interzoid-automation
Automate Interzoid tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
nw-review
Dispatches an expert reviewer agent to critique workflow artifacts. Use when a roadmap, implementation, or step needs quality review before proceeding.
majiayu000/claude-skill-registry 163