Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
agent-sdk
Expert in Claude Agent SDK development. Use when users ask about SDK API, agent configuration, MCP servers, hooks, permissions, file checkpointing, or when they mention @AGENT_SDK_DOCS.md. Provides accurate API reference, code examples with TypeScript types, and best practices.
majiayu000/claude-skill-registry 163
-
git-finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
majiayu000/claude-skill-registry 163
-
operations
Operations excellence expertise for supply chain optimization, process improvement (Lean, Six Sigma), capacity planning, vendor management, quality assurance, and operational efficiency. Use when optimizing processes, managing supply chains, or improving operational performance.
majiayu000/claude-skill-registry 163
-
adynato-seo
Handles SEO requirements for all web content including blogs, landing pages, and documentation. Covers LD+JSON schema.org structured data, internal backlinks strategy, further reading sections, meta tags, and Open Graph. Use when creating or editing any public-facing web content, blog posts, or pages that need search visibility.
majiayu000/claude-skill-registry 163
-
building-clis
Build professional command-line interfaces in Python, Go, and Rust using modern frameworks like Typer, Cobra, and clap. Use when creating developer tools, automation scripts, or infrastructure management CLIs with robust argument parsing, interactive features, and multi-platform distribution.
majiayu000/claude-skill-registry 163
-
system-design
Use when designing system architecture, APIs, components, or data models - provides a structured design workflow with validation and documentation outputs.
majiayu000/claude-skill-registry 163
-
core-ux-detective
Discover, define and canonicalize the core user tasks and user paths of the application. Use when (1) mapping what users can actually do in the app, (2) defining canonical user journeys/flows, (3) creating the AI-readable user model (core-user-model.json), (4) reviewing whether a new feature introduces a new core path, (5) other skills (help, marketing, onboarding) need authoritative task/path definitions to consume. Triggers: "core tasks", "user paths", "user journeys", "UX model", "what can users do", "core flows", "user model", "canonical tasks", file types: core-user-model.json.
majiayu000/claude-skill-registry 163
-
context-preservation-protocol-execution
Execute context preservation protocols for session continuity.
majiayu000/claude-skill-registry 163
-
anvil-conflict-resolution
Multi-model committee conflict resolution with weighted voting, multisig arbitration, and escalation cascade.
majiayu000/claude-skill-registry 163
-
kernel-debug-loop
This skill should be used when performing fast iterative kernel debugging, running time-bound kernel sessions to detect specific log signals or test kernel behavior. Use for rapid feedback cycles during kernel development, boot sequence analysis, or feature verification.
majiayu000/claude-skill-registry 163
-
mcp-pydantic-tool-definition
Pydantic V2 models are the single source of truth for MCP tool schemas. PROACTIVELY activate for: (1) defining tool input/output schemas, (2) strict mode validation, (3) JSON schema generation. Triggers: "pydantic schema", "tool schema", "strict mode"
majiayu000/claude-skill-registry 163
-
guardrails-contracts
Follow these patterns when designing guardrails validation contracts in OptAIC. Use for signal bounds, dataset schemas, portfolio constraints, PIT validation, and other domain-specific validation rules. Covers the "Law vs Police" architecture where Definitions contain contracts and the Engine enforces them.
majiayu000/claude-skill-registry 163
-
context-engineering
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
majiayu000/claude-skill-registry 163
-
prd-v04-screen-flow-definition
Connect user journeys to screens, defining the UI structure and navigation paths during PRD v0.4 User Journeys. Triggers on requests to define screens, design screen flows, map UI structure, plan navigation, or when user asks "what screens do we need?", "define screens", "screen flow", "UI structure", "information architecture", "navigation design", "wireframe planning". Consumes UJ- (User Journey Mapping), FEA- (Feature Value Planning), BR- (constraints). Outputs SCR- entries for screens and DES- entries for design system elements. Feeds v0.5 Red Team Review.
majiayu000/claude-skill-registry 163
-
pro
Professional engineering skill combining senior engineer thinking patterns, adaptive task assessment, and Google-grade standards. Invoke with /pro before any coding task to ensure production-quality work with proper planning, testing, and verification.
majiayu000/claude-skill-registry 163
-
dockerfile-optimizer
Optimizes Dockerfiles for smaller images, faster builds, better caching, and security hardening using multi-stage builds and best practices. Use when users request "optimize Dockerfile", "reduce Docker image size", "Docker best practices", or "containerize application".
majiayu000/claude-skill-registry 163
-
ansible-playbook
Write and review Ansible playbooks following best practices. Use when the user says "write ansible", "ansible playbook", "review playbook", "automate with ansible", or asks to configure servers with Ansible.
majiayu000/claude-skill-registry 163
-
git-hex-pr-workflow
Complete pull request workflow combining git-hex (local craft) with remote collaboration (GitHub plugin or CLI). This skill should be used when the user wants to prepare, submit, and iterate on a PR with clean commit history. Trigger phrases include: "prepare a PR", "open a pull request", "address review feedback", "update my PR", "clean up commits for PR".
majiayu000/claude-skill-registry 163
-
read-arxiv-paper
Use this skill when when asked to read an arxiv paper given an arxiv URL
majiayu000/claude-skill-registry 163
-
Command Palette Developer
This skill should be used when the user asks to "create a command palette", "build a command palette", "add command palette", "implement ⌘K search", "create search modal", "build keyboard navigation", "add command menu", "create Raycast-style interface", "build spotlight search", or mentions cmdk, command bar, command menu, or keyboard-first navigation. Provides comprehensive guidance for building professional command palettes with React, TypeScript, Tailwind, and modern tooling including cmdk, Floating UI, Zustand, Tanstack Query, and Tanstack Virtual.
majiayu000/claude-skill-registry 163
-
cloudflare-ai-gateway
Cloudflare AI Gateway for unified interface to AI providers with caching, rate limiting, and analytics
majiayu000/claude-skill-registry 163
-
gluestack-accessibility
Use when ensuring accessible gluestack-ui implementations. Covers WAI-ARIA patterns, screen reader support, keyboard navigation, focus management, and WCAG 2.1 AA compliance.
majiayu000/claude-skill-registry 163
-
pubmed-database
Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.
majiayu000/claude-skill-registry 163
-
community-feed
Social feed with batch queries, cursor pagination, trending algorithms, and engagement tracking. Efficient database queries for infinite scroll feeds.
majiayu000/claude-skill-registry 163