Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Zod Schema Management
Create and modify Zod schemas for runtime validation with proper type inference.
majiayu000/claude-skill-registry 163
-
nextjs
Next.js specific patterns including App Router, React Server Components, Server Actions, streaming, caching, and Vercel deployment.
majiayu000/claude-skill-registry 163
-
frontend-testing
Testa aplicacoes web usando Playwright. Captura screenshots, executa E2E tests,
analisa logs do browser. Integrado com qa-analyst para Phase 6.
Use quando: testar frontend, capturar screenshots, validar UI, executar E2E.
majiayu000/claude-skill-registry 163
-
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing features for parallel development, establishing file ownership boundaries, or managing integration between parallel work streams.
majiayu000/claude-skill-registry 163
-
skill-git-workflow
Create scoped git commits for task operations. Invoke after task status changes or artifact creation.
majiayu000/claude-skill-registry 163
-
ai-engineer
MASTER AI: LLM Apps, Advanced RAG, Agents (ReAct/Plan), Prompting (CoT/Few-shot), LangGraph, VectorDBs, RAGAS Eval. Use for ANY AI/LLM task.
majiayu000/claude-skill-registry 163
-
stylex-styling
StyleX styling patterns using design tokens, breakpoints, and custom css prop. Use when working with styles, CSS, design tokens, breakpoints, responsive design, themes, styling components, css prop, stylex.create, or when the user mentions StyleX, tokens.stylex, controlSize, color tokens, or breakpoints.
majiayu000/claude-skill-registry 163
-
skill-builder
Creates and refines Claude Code skills via structured workflows with YAML frontmatter, typed folders, and depth-gated LOC limits. Use when authoring SKILL.md files, organizing references/, or validating skill structure.
majiayu000/claude-skill-registry 163
-
specsafe
Show SpecSafe project status and workflow guidance
majiayu000/claude-skill-registry 163
-
image-generation
Generate AI image prompts for website assets using Imagen (infographics, diagrams, icons, maps).
majiayu000/claude-skill-registry 163
-
end-to-end-testing
End-to-end testing workflow for gh-pr-linear-issue-linker. Tests GitHub webhook integration with Linear ticket matching and Slack notifications.
majiayu000/claude-skill-registry 163
-
cuda-graphs
Expert skill for CUDA Graph capture and optimization for reduced launch overhead. Capture CUDA operations into graphs, instantiate and execute graph instances, update graph node parameters, profile graph vs stream execution, design graph-friendly kernel patterns, and optimize launch latency for inference.
majiayu000/claude-skill-registry 163
-
auto
Autonomous AI coding loop (Ralph Wiggum methodology). Use when running AI agents
in unattended/autonomous mode to independently select and complete tasks from a
structured task list (prd.json). Enables AFK development across multiple context windows.
majiayu000/claude-skill-registry 163
-
project-orchestrator:finishing-branch
Use when implementation is complete and ready to merge/PR — handles git repos, auto-deploy awareness, multi-service PR ordering, and changelog.
majiayu000/claude-skill-registry 163
-
diffdock
Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.
majiayu000/claude-skill-registry 163
-
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
majiayu000/claude-skill-registry 163
-
visual-qa
Use vision models to self-review screenshots against design intent. Catches spacing issues, alignment problems, color inconsistencies, responsive bugs, and accessibility gaps. Use when reviewing designs, comparing implementations to mockups, or doing pre-ship QA.
majiayu000/claude-skill-registry 163
-
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
majiayu000/claude-skill-registry 163
-
coordination-model
AI-native agent coordination model — defines abstract operations (spawn, fork, merge, observe, convergence, prune), coordination primitives (speculative swarm, context mesh, fractal decomposition, generative-adversarial, stigmergic), and composable playbooks for agent fleet orchestration. Use when designing multi-agent systems, composing coordination patterns, writing playbook configurations, validating runtime conformance, or any task involving agent fleet architecture. Also use when the user mentions agent swarms, agent fleets, coordination primitives, agent orchestration patterns, or multi-agent composition.
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
-
big-data-cloud-automation
Automate Big Data Cloud tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
cpp
C++ modern C++17/20/23 with STL, smart pointers, and performance optimization. Use for .cpp files.
majiayu000/claude-skill-registry 163
-
reverse-engineer
Expert reverse engineer specializing in binary analysis, disassembly, decompilation, and software analysis. Masters IDA Pro, Ghidra, radare2, x64dbg, and modern RE toolchains. Handles executable analysis, library inspection, protocol extraction, and vulnerability research. Use PROACTIVELY for binary analysis, CTF challenges, security research, or understanding undocumented software.
majiayu000/claude-skill-registry 163
-
prd
Generate an ML-centric PRD for ML-Ralph. Use when planning an ML project, experiment plan, or when asked to create an ML PRD. Triggers on: create a prd, write prd for, plan this ML feature, requirements for, spec out.
majiayu000/claude-skill-registry 163