Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
launch-a-swarm
Spawn 5 parallel agents applying quality principles across planning, building, and validating code. Use when designing features, making decisions, or checking work. Triggers on "launch a swarm" or when ensuring solid, maintainable, secure software.
majiayu000/claude-skill-registry 163
-
create-clickup-task
Create ClickUp tasks with proper formatting, task types, custom fields, and assignment. Use when the user wants to create a task, bug, feature, or ticket in ClickUp, or when they mention Sprint planning or task tracking.
majiayu000/claude-skill-registry 163
-
nostrstack-nostr
Nostr-specific workflows in nostrstack: identifier parsing, event/profile landing pages, relay fetch/caching rules, NIP-05 identity resolution, and reference rendering. Use when working on Nostr event handling, NIP-05 lookups, or /nostr/:id UI/API behavior.
majiayu000/claude-skill-registry 163
-
Design System Architecture
Build consistent, scalable design systems with proper token architecture
majiayu000/claude-skill-registry 163
-
volcanic-check
Check if a speleothem anomaly correlates with volcanic eruptions. Use when ruling out volcanic false positives, checking eVolv2k/VSSI records, or validating seismic interpretations. Triggers on "volcanic check", "eruption correlation", "rule out volcanic", "eVolv2k".
majiayu000/claude-skill-registry 163
-
natural-language-generation-flight505-storybook-assistant
Use this skill when the user describes a component in natural language, says "create a component with...", "I need a card that has...", "build a form with fields for...", "generate component from description", or provides detailed component requirements in plain English. Enables non-technical stakeholders to generate production-ready components through natural language descriptions.
majiayu000/claude-skill-registry 163
-
design-postgres-tables
Comprehensive PostgreSQL-specific table design reference covering data types, indexing, constraints, performance patterns, and advanced features
majiayu000/claude-skill-registry 163
-
bedrock-agentcore-policy
Amazon Bedrock AgentCore Policy for defining agent boundaries using natural language and Cedar. Deterministic policy enforcement at the Gateway level. Use when setting agent guardrails, access control, tool permissions, or compliance rules.
majiayu000/claude-skill-registry 163
-
security-integration-tests
Use this agent when working with prompt injection detection integration tests, including running tests, debugging failures, or adding new test samples.
majiayu000/claude-skill-registry 163
-
keyword-research
Use when expanding seed topics into intent-based clusters and prioritizing opportunities.
majiayu000/claude-skill-registry 163
-
Video Generation
Create videos for demos and marketing
majiayu000/claude-skill-registry 163
-
moai-workflow-thinking
Sequential Thinking MCP and UltraThink mode for deep analysis, complex problem decomposition, and structured reasoning workflows
majiayu000/claude-skill-registry 163
-
tiptap
Build rich text editors with Tiptap - headless editor framework with React and Tailwind v4. Covers SSR-safe setup, image uploads, prose styling, and collaborative editing.
Use when creating blog editors, comment systems, or Notion-like apps, or troubleshooting SSR hydration errors, typography issues, or image upload problems.
majiayu000/claude-skill-registry 163
-
privacy-email-review
メール取得を伴う機能のプライバシー設計レビューを行う。メールアドレスを保存する機能を実装する前、PII取得の設計確認時に使う。
majiayu000/claude-skill-registry 163
-
write-action
Write server actions following the Epic architecture patterns. Use when creating server-side logic for behaviors, including authentication, validation, and model calls. Triggers on "create an action", "add an action", or "write an action for".
majiayu000/claude-skill-registry 163
-
private-vs-shared-components
Rules for determining if a component should be private or shared, and where to place them based on their use-case.
majiayu000/claude-skill-registry 163
-
agent-tool-builder
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa
majiayu000/claude-skill-registry 163
-
extract-dependencies
Analyze imports and identify all module dependencies. Use when mapping project structure.
majiayu000/claude-skill-registry 163
-
managing-docs
Expert at organizing and managing documentation structure across projects. Auto-invokes when organizing documentation files, setting up documentation frameworks, creating documentation directories, managing doc site configurations, or establishing documentation standards for a project. Provides guidance on documentation architecture and tooling.
majiayu000/claude-skill-registry 163
-
database-administrator
Copilot agent that assists with database operations, performance tuning, backup/recovery, monitoring, and high availability configuration
Trigger terms: database administration, DBA, database tuning, performance tuning, backup recovery, high availability, database monitoring, query optimization, index optimization
Use when: User requests involve database administrator tasks.
majiayu000/claude-skill-registry 163
-
happiness-dashboard
Evidence framework data dashboard with DuckDB. Write SQL in markdown to create visualizations.
majiayu000/claude-skill-registry 163
-
reverse-engineering-protocols
Reverse engineers network protocols through packet analysis, dissection, and documentation. Use when analyzing network traffic, understanding proprietary protocols, or debugging communication. Triggers include "pcap", "packet capture", "protocol analysis", "Wireshark", or "tcpdump".
majiayu000/claude-skill-registry 163
-
vtm-expert
Virtual Task Manager domain expert.
Knows about:
- Next, Context, Task, Start, Complete, Stats, List operations
Use when:
- User asks about task management operations
- Context needed before starting work
- Reviewing task status
- Managing task workflow
majiayu000/claude-skill-registry 163
-
rspress-api-docs
Generate API documentation from TypeScript source code for RSPress. Use when documenting package APIs, extracting types from source code, or creating function/class reference pages.
majiayu000/claude-skill-registry 163