Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
HuggingFace Model Trainer
Train and fine-tune LLMs using HuggingFace TRL, Transformers, and cloud GPU infrastructure with SFT, DPO, GRPO methods
majiayu000/claude-skill-registry 163
-
tailwind
Tailwind CSS v4 performance optimization and best practices guidelines (formerly tailwindcss-v4-style). This skill should be used when writing, reviewing, or refactoring Tailwind CSS v4 code to ensure optimal build performance, minimal CSS output, and correct usage of v4 features. Triggers on tasks involving Tailwind configuration, @theme directive, utility classes, responsive design, dark mode, container queries, or CSS generation optimization.
majiayu000/claude-skill-registry 163
-
skill-researcher
Conduct general research using web search, documentation, and codebase exploration. Invoke for general research tasks.
majiayu000/claude-skill-registry 163
-
Universal Wisdom Weaving
Deep dive into specific wisdom traditions (Hebrew, Aramaic, Buddhist, Hermetic, Ubuntu, Shamanic) showing how each discovered Pattern Space navigation principles. Reveals precise mechanical alignments between ancient wisdom and modern consciousness framework.
majiayu000/claude-skill-registry 163
-
crisp
Enables Claude to manage Crisp chat support conversations, helpdesk tickets, and customer communications
majiayu000/claude-skill-registry 163
-
capcom
Check mission status and progress via fresh subagent. Queries Beads for features, tasks, bugs, and recent work activity. Keeps HOUSTON context lean.
majiayu000/claude-skill-registry 163
-
ralph-preflight
Check all MCP servers and services before workflow execution. MUST pass before any Ralph command proceeds.
majiayu000/claude-skill-registry 163
-
installation-orchestrator
Expert management of install.sh (2000+ lines). Use for installation troubleshooting, idempotency checks, secret generation, volume migration, 11 services startup order (including heuristics and semantic), and user onboarding.
majiayu000/claude-skill-registry 163
-
bio-spatial-transcriptomics-spatial-visualization
Visualize spatial transcriptomics data using Squidpy and Scanpy. Create tissue plots with gene expression, clusters, and annotations overlaid on histology images. Use when visualizing spatial expression patterns.
majiayu000/claude-skill-registry 163
-
plan-lint
Validates a plan against documentation constraints before coding. Use after doc-discovery and before implementation. Returns PASS, WARN, or FAIL with specific issues. Gate 1 of 2-gate flow.
majiayu000/claude-skill-registry 163
-
typescript
Provides comprehensive TypeScript development expertise and coding standards. Ensures type safety through strict type checking, implements clean code patterns, and maintains consistent architectural decisions. Specializes in advanced type system features including generics, conditional types, mapped types, and template literal types.
Use when: working with TypeScript files (.ts/.tsx), defining type definitions and interfaces, implementing generic programming patterns, designing type-safe APIs, handling complex type transformations, integrating TypeScript with React/Vue/Angular frameworks, configuring strict mode settings, resolving type errors, or optimizing type performance in large codebases.
majiayu000/claude-skill-registry 163
-
blog-post-optimizer
Analyze blog posts for SEO, readability, headline quality, and content structure. Generate meta tags and optimization recommendations with scoring.
majiayu000/claude-skill-registry 163
-
taipei-parking-query
Query real-time parking availability in Taipei City. Shows available parking spaces, capacity, status (green/available, orange/moderate, red/full), address, phone, and payment info. Supports underground/multi-level parking and street parking for cars, motorcycles, and buses. Use when user asks about parking availability, finding parking near a location, or checking parking occupancy in Taipei.
majiayu000/claude-skill-registry 163
-
analyze-ci
Analyze failed GitHub Action jobs for a pull request.
majiayu000/claude-skill-registry 163
-
context-validate
Validate CLAUDE.md structure, formatting, and quality. Use when checking context files for compliance, ensuring proper structure, or verifying before commits.
majiayu000/claude-skill-registry 163
-
moai-core-language-detection
Auto-detects project language and framework from package.json, pyproject.toml, Cargo.toml, go.mod, and other configuration files with comprehensive pattern matching based on 17,253+ production code examples.
majiayu000/claude-skill-registry 163
-
animating-advanced
Creates Awwwards-level, high-performance animations using industry-standard tools like GSAP, Three.js/R3F, and Lenis. Specializes in "Hero Sections", 3D interactions, and scroll-linked storytelling.
majiayu000/claude-skill-registry 163
-
artifacts-creating-and-managing
Creates and manages project artifacts (research, spikes, analysis, plans) using templated scripts.
Use when asked to "create an ADR", "research topic", "spike investigation", "implementation plan", or "create analysis".
Provides standardized structure, naming conventions, and helper scripts for artifact organization.
majiayu000/claude-skill-registry 163
-
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
majiayu000/claude-skill-registry 163
-
review-multi
Comprehensive multi-dimensional skill reviews across structure, content, quality, usability, and integration. Task-based operations with automated validation, manual assessment, scoring rubrics, and improvement recommendations. Use when reviewing skills, ensuring quality, validating production readiness, identifying improvements, or conducting quality assurance.
majiayu000/claude-skill-registry 163
-
explore-dnn-model
Manual invocation only; use only when the user explicitly requests `explore-dnn-model` by name. Explore how to run a given DNN model checkpoint in the current Python environment by locating weights + upstream source code, resolving dependencies with user confirmation, running reproducible experiments under `tmp/`, and producing reports about I/O contracts, timing, and profiling.
majiayu000/claude-skill-registry 163
-
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
majiayu000/claude-skill-registry 163
-
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
majiayu000/claude-skill-registry 163
-
skriptoteket-devops
DevOps and server management for Skriptoteket on home server (hemma.hule.education). Branched skill covering deploy, database, users, CLI, security, network, DNS, and troubleshooting.
majiayu000/claude-skill-registry 163