Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
onboarding-start
Create comprehensive onboarding documentation for a codebase or feature. Use when user asks to "create an onboarding document for X".
majiayu000/claude-skill-registry 163
-
hook-creator
Create Claude Code hooks with proper schemas, RBAC integration, and performance requirements. Use when implementing PreToolUse, PostToolUse, SessionStart, or any of the 10 hook event types for automation, validation, or security enforcement.
majiayu000/claude-skill-registry 163
-
fof-qc-summarizer
Aggregate-only summarizer for K18 QC artifacts; produces summary outputs and appends manifest rows when format is confirmed.
majiayu000/claude-skill-registry 163
-
design-with-traceability
Create technical solution architecture from requirements with REQ-* traceability. Designs components, APIs, data models, and interactions. Tags all design artifacts with requirement keys. Use after requirements are validated, before coding starts.
majiayu000/claude-skill-registry 163
-
carousels-sliders
Use when animating carousels, sliders, image galleries, or horizontally scrolling content for smooth navigation
majiayu000/claude-skill-registry 163
-
data-systems-architecture
Use when designing databases for data-heavy applications, making schema decisions for performance, choosing between normalization and denormalization, selecting storage/indexing strategies, planning for scale, or evaluating OLTP vs OLAP trade-offs. Also use when encountering N+1 queries, ORM issues, or concurrency problems.
majiayu000/claude-skill-registry 163
-
proof-weighted-optimization
Optimize decisions using proof-weighted scoring.
majiayu000/claude-skill-registry 163
-
user-file-ops
Simple operations on user-provided text files including summarization.
majiayu000/claude-skill-registry 163
-
handbook-sync
Sync central handbook from ~/.claude/AmplifyHandbook/ to current project's resources/handbook/
majiayu000/claude-skill-registry 163
-
cancel-ralph
Cancel active Ralph loop
majiayu000/claude-skill-registry 163
-
structural-physics
Structural validation and damage systems for Three.js building games. Use when implementing building stability (Fortnite/Rust/Valheim style), damage propagation, cascading collapse, or realistic physics simulation. Supports arcade, heuristic, and realistic physics modes.
majiayu000/claude-skill-registry 163
-
financial-goal-planner
Create timelines for house down payment, retirement, college fund. Monthly savings targets, investment strategies, milestone tracking.
majiayu000/claude-skill-registry 163
-
prospect-research
Creates comprehensive prospect profiles and knowledge capsules for sales preparation. Use this skill when researching new prospects, preparing for calls, onboarding to new accounts, or updating prospect intelligence.
majiayu000/claude-skill-registry 163
-
ux-waiting-audit
Audit UX waiting states for web applications with long-running operations (30+ seconds). Use when asked to evaluate, audit, or analyze a product's loading states, wait times, progress indicators, or user experience during slow operations. Requires browser automation (Chrome MCP tools). Generates comprehensive reports with screenshots, checklist evaluation, and prioritized recommendations.
majiayu000/claude-skill-registry 163
-
obsidian-markdown-structure
Validate and enforce markdown document structure including frontmatter positioning, heading hierarchy, and content organization. Use when creating or validating markdown files.
majiayu000/claude-skill-registry 163
-
3d-spatial
Use when working in Blender, Unity 3D, Unreal Engine, Cinema 4D, VR/AR applications, or any three-dimensional animation work.
majiayu000/claude-skill-registry 163
-
nginx-configuration
Configure Nginx web server for high-performance reverse proxy, load balancing, SSL/TLS, caching, and API gateway functionality.
majiayu000/claude-skill-registry 163
-
hypothesis-debugging
Structured code debugging through hypothesis formation and falsification planning. Use when diagnosing bugs, unexpected behaviour, or system failures where the root cause is unclear. Produces a hypothesis document for execution by another agent rather than performing the investigation directly. Triggers on requests to debug issues, diagnose problems, investigate failures, or create debugging plans.
majiayu000/claude-skill-registry 163
-
algorithms
Master algorithm design, common patterns, optimization techniques, and problem-solving strategies. Learn to solve any computational challenge efficiently.
majiayu000/claude-skill-registry 163
-
gsd-execute-phase
Execute all plans in a phase with wave-based parallelization
majiayu000/claude-skill-registry 163
-
rust-async-concurrency
Manage concurrent operations with channels, semaphores, locks, and streams. Use when coordinating parallel work or limiting resource usage.
majiayu000/claude-skill-registry 163
-
loop-breaker
Scaffold middleware to detect and block Worker self-recursion, infinite fetch chains, and runaway loops. Use this skill when designing Workers that call other Workers, implement webhooks, or handle events that might trigger themselves. Also use when encountering "recursion", "infinite loop", "self-call", "fetch chain", or "denial of wallet" scenarios.
majiayu000/claude-skill-registry 163
-
hpc-dev-testing-workflow
Efficient development testing workflow for HPC environments with VS Code tunneling. Trigger: testing code changes on HPC, development workflow with external data directories, VS Code Remote SSH development
majiayu000/claude-skill-registry 163
-
multi-agent-coordination
Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized agents, or managing agent selection. Trigger keywords - "parallel agents", "sequential workflow", "delegate", "multi-agent", "sub-agent", "agent switching", "task decomposition".
majiayu000/claude-skill-registry 163