Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
fal-platform
Platform APIs for model management, pricing, and usage tracking
majiayu000/claude-skill-registry 163
-
bio-clip-seq-clip-alignment
Align CLIP-seq reads to the genome with crosslink site awareness. Use when mapping preprocessed CLIP reads for peak calling.
majiayu000/claude-skill-registry 163
-
security-implementation-guide
Comprehensive security patterns for authentication, authorization, input validation, and common vulnerability prevention
majiayu000/claude-skill-registry 163
-
data-architecture
Data architecture - models, relationships. Use when designing data structures.
majiayu000/claude-skill-registry 163
-
libsupervision
libsupervision - Process supervision system. Supervisor manages process tree inspired by s6-svscan. LongRunner handles persistent processes with restart. OneShot handles single-execution tasks. ProcessState tracks process lifecycle. LogWriter manages process logging. Use for service management, process control, and graceful shutdown handling.
majiayu000/claude-skill-registry 163
-
RSS Feed Parser Expert
You are the podcast RSS feed parsing specialist for Modcaster.
majiayu000/claude-skill-registry 163
-
rust-coroutine
协程与绿色线程专家。处理 generator, suspend/resume, stackful coroutine, stackless coroutine, context switch, 协程, 绿色线程, 上下文切换, 生成器
majiayu000/claude-skill-registry 163
-
outlier-detective
Detect anomalies and outliers in datasets using statistical and ML methods. Use for data cleaning, fraud detection, or quality control analysis.
majiayu000/claude-skill-registry 163
-
umbraco-dynamic-root
Implement dynamic root origins and query steps in Umbraco backoffice using official docs
majiayu000/claude-skill-registry 163
-
Market Scout (Crypto Rotation)
Scan recent macro/crypto headlines and summarize ONLY market-moving items for BTC, ETH, SOL, ADA, PAXG. Use when the user asks for a market snapshot, catalysts, or rotation context in the last 4–24 hours.
majiayu000/claude-skill-registry 163
-
coderabbit-local-dev-loop
Configure CodeRabbit local development with hot reload and testing.
Use when setting up a development environment, configuring test workflows,
or establishing a fast iteration cycle with CodeRabbit.
Trigger with phrases like "coderabbit dev setup", "coderabbit local development",
"coderabbit dev environment", "develop with coderabbit".
majiayu000/claude-skill-registry 163
-
expo-devtools-cli
Building Expo DevTools Plugins with CLI Interfaces for interacting with running Expo apps using agents.
majiayu000/claude-skill-registry 163
-
insights
Business intelligence expert - creates actionable insights, visualizations, and executive reports from GabeDA model outputs. Identifies data gaps and recommends new features.
majiayu000/claude-skill-registry 163
-
3d-web-experience
Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences. Use when: 3D website, three.js, WebGL, react three fiber, 3D experience.
majiayu000/claude-skill-registry 163
-
design-synthesizer
Auto-activates when synthesizing outputs from multiple parallel sub-agents to create cohesive, integrated design with consistency checking and conflict resolution.
majiayu000/claude-skill-registry 163
-
ltb-application-hearing-procedures
Expert in LTB filing and hearing processes including application filing requirements (landlord L1-L9 applications, tenant T1-T6 applications, filing deadlines), hearing preparation (disclosure, evidence organization, witness prep, legal arguments), hearing procedures (order of proceeding, evidence rules, adjudicator discretion, common defenses), and LTB orders/enforcement (standard eviction 11-day delay, conditional orders, rent abatement, sheriff enforcement). Use when filing LTB applications or preparing for hearings. Key terms include L1 arrears, L2 for-cause, T2 tenant rights, T5 maintenance, disclosure requirements, evidence rules, conditional orders, sheriff enforcement
majiayu000/claude-skill-registry 163
-
MCP Server Generator
Expert guidance for creating, configuring, and deploying Model Context Protocol (MCP) servers. Use when building custom MCP servers, integrating external APIs, or extending Claude with new capabilities.
majiayu000/claude-skill-registry 163
-
validate-test-reality
Meta-validation skill that generates edge cases, production scenarios, and reality gaps not covered by original specifications. Identifies specification-reality mismatches by analyzing what tests claim versus what production data reveals. Creates test deficiency reports showing coverage gaps for Quinn review. Use before quality gate approval to ensure tests reflect production reality, not just specification compliance.
majiayu000/claude-skill-registry 163
-
wp-performance
Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers), database/query optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.
majiayu000/claude-skill-registry 163
-
Visionary Team
Strategic AI council for product vision, innovation, and future planning
majiayu000/claude-skill-registry 163
-
markdowntown-atlas-scan
Atlas Simulator scan flow and next-step guidance for markdowntown. Use when working on folder scanning, tool detection, cwd handling, results panels, or scan-to-workbench CTAs.
majiayu000/claude-skill-registry 163
-
pyodide-exercise
Create browser-based Python exercises using Pyodide. Use for interactive coding without local setup.
majiayu000/claude-skill-registry 163
-
terraform-module-library
Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
majiayu000/claude-skill-registry 163
-
proxy-metric-selection
Use when outcomes are difficult to measure directly - designs proxy metrics that correlate with true outcomes, with clear mathematical formulas and counter-metrics for unintended effects
majiayu000/claude-skill-registry 163