Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
superclaude-rules
Behavioral rules when development keywords detected (implement, build, fix, test, commit) - covers workflow patterns, quality standards, tool optimization, organization protocols
majiayu000/claude-skill-registry 163
-
new-machine-setup-snkrheadz-laptop-68e63efa
新マシンセットアップガイド。macOS初期設定からdotfiles適用までの手順案内。トリガー: 新マシン, setup, 移行, 新しいMac, セットアップ
majiayu000/claude-skill-registry 163
-
learning-accommodation-planner
accommodation-planner for inclusive and accessible learning experiences.
majiayu000/claude-skill-registry 163
-
rebase-parent
Rebase the current branch onto an updated parent PR branch. Use when you have stacked PRs and the parent branch has been updated (force-pushed after its own rebase or new commits added).
majiayu000/claude-skill-registry 163
-
Pytest Testing Patterns
Apply pytest best practices and project testing conventions. Use when writing or modifying tests.
majiayu000/claude-skill-registry 163
-
Swift Concurrency
Use when swift's modern concurrency model including async/await, actors, task groups, structured concurrency, and async sequences for building safe, performant concurrent code without data races or callback pyramids.
majiayu000/claude-skill-registry 163
-
autonomous-agents
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
majiayu000/claude-skill-registry 163
-
meta-creativeentelechy-trading-agent
majiayu000/claude-skill-registry 163
-
optimizing-io-operations-lite
Provides essential high-performance I/O patterns. Use when quickly referencing core I/O optimization techniques without detailed explanations.
majiayu000/claude-skill-registry 163
-
rls-policy-generator
Generate production-ready Row Level Security (RLS) policies for Supabase tables with is_super_admin() bypass, proper USING/WITH CHECK, and common relationship patterns; use when creating RLS policies, securing tables, implementing data access controls, or securing storage buckets
majiayu000/claude-skill-registry 163
-
optimization-phase
Validates production readiness through performance benchmarking, accessibility audits, security reviews, and code quality checks. Use after implementation phase completes, before deployment, or when conducting quality gates for features. (project)
majiayu000/claude-skill-registry 163
-
multi-cloud-architecture
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.
majiayu000/claude-skill-registry 163
-
team-topologies
Four fundamental team types and interaction modes from Team Topologies
majiayu000/claude-skill-registry 163
-
convert
Convert tasks.md to prd.json with smart routing classification. Use after creating tasks. Triggers on: convert to prd, generate prd.json, convert tasks.
majiayu000/claude-skill-registry 163
-
codebase-orientation
Guide quick orientation of an unfamiliar codebase with module mapping, entry points, and local run steps. Use when a junior developer needs to get situated fast.
majiayu000/claude-skill-registry 163
-
review-pr-sasamuku-dotfiles
majiayu000/claude-skill-registry 163
-
registry-forensics
Analyze Windows Registry hives for forensic investigation. Use when investigating
malware persistence, user activity, system configuration changes, or evidence of
program execution. Supports offline registry analysis from disk images or extracted hives.
majiayu000/claude-skill-registry 163
-
moonshot-evaluate-complexity
Evaluates complexity (simple, medium, complex) based on estimated files/lines/time. Use after task classification.
majiayu000/claude-skill-registry 163
-
aesthetic-critic-historian
[Aesthetics] Positions aesthetics within art/design history, identifies what traditions it echoes, and spots clichés, generic trends, and AI-slop patterns to avoid. Outputs Critical Notes as Memo nodes in Brain canvas.
majiayu000/claude-skill-registry 163
-
riverpod-lapc506-flutter-agentic-boil-2
majiayu000/claude-skill-registry 163
-
assessment-architect
Generate certification exams for chapters or parts. Extracts concepts first, then generates scenario-based questions. Use "ch X" for chapter, "part X" for part.
majiayu000/claude-skill-registry 163
-
cleaning-wsl-docker
Reclaims SSD disk space consumed by WSL2/Docker. Use when user reports disk space issues, Docker build failures due to space, or slow WSL performance. Handles Docker prune, cache cleanup, VHDX compaction, and prevention setup. MUST BE USED when "disk full", "out of space", or "VHDX" mentioned.
majiayu000/claude-skill-registry 163
-
native-integration-lapc506-flutter-agentic-boil-2
majiayu000/claude-skill-registry 163
-
frontend-ui-integration
Implement or extend a user-facing workflow in a web application, integrating with existing backend APIs. Use when the feature is primarily a UI/UX change backed by existing APIs, affects only the web frontend, and requires following design system, routing, and testing conventions.
majiayu000/claude-skill-registry 163