Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
backend-error-handling
Backend typed error handling and boundary mapping
majiayu000/claude-skill-registry 163
-
pufferlib
This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.
majiayu000/claude-skill-registry 163
-
sonoscli
Control Sonos speakers (discover/status/play/volume/group).
majiayu000/claude-skill-registry 163
-
hooks
Claude Code の Hook 作成・管理ガイド。PreToolUse、PostToolUse、Stop等のフック実装。 使用タイミング: (1) 危険操作をブロックしたい時 (2) ツール実行後に提案を出したい時 (3) セッション終了時にクリーンアップしたい時 (4) Claude Codeをカスタマイズしたい時。 トリガー例: 「フックを作って」「PreToolUseフック」「危険操作をブロック」 「コミット後に提案」「Claude Codeのhooks」
majiayu000/claude-skill-registry 163
-
manual_tests
Runs all manual hook/rule tests using sub-agents. Use when validating that DeepWork rules fire correctly.
majiayu000/claude-skill-registry 163
-
complex-object-comparison
majiayu000/claude-skill-registry 163
-
token-efficient
Use when processing 50+ items, analyzing CSV/log files, executing code in sandbox, or searching for tools. Load for data processing tasks. Achieves 98%+ token savings via in-sandbox execution, progressive disclosure, and pagination. Supports heredocs for multi-line bash.
majiayu000/claude-skill-registry 163
-
k8s-gitops
GitOps workflows and CI/CD pipeline integration for Kubernetes and OpenShift. Use this skill when:
(1) Setting up ArgoCD or Flux for GitOps deployment
(2) Creating CI/CD pipelines for K8s workloads (GitHub Actions, GitLab CI, Tekton)
(3) Implementing progressive delivery (Canary, Blue-Green, A/B testing)
(4) Configuring Kustomize overlays for multi-environment deployments
(5) Creating Helm charts or managing Helm releases
(6) Setting up image automation and promotion workflows
(7) Implementing policy-as-code (Kyverno, OPA Gatekeeper)
(8) Secret management in GitOps (Sealed Secrets, External Secrets, SOPS)
(9) Multi-cluster GitOps configurations
(10) OpenShift Pipelines (Tekton) and GitOps Operator setup
majiayu000/claude-skill-registry 163
-
exa-search
Semantic search, similar content discovery, and structured research using Exa API
majiayu000/claude-skill-registry 163
-
safe-schedule-generation
Safe schedule generation with mandatory backup. REQUIRES database backup before any write operations to schedule tables. Use when generating schedules, bulk assigning, or executing swaps.
majiayu000/claude-skill-registry 163
-
discopy-operads
DiscoPy Operads Skill
majiayu000/claude-skill-registry 163
-
deep-analysis
Execute high-density analysis on complex ideas/tasks. Move from 'Vague' to 'Verified' by producing: constraints -> core modules -> facts vs assumptions -> ASCII flow maps (boundary + critical path) -> latticework lens sweep -> micro->macro causal chains -> pre-mortem failure modes. Use when analyzing system architecture, validating technical ideas, or decomposing a thorny problem before designing solutions.
majiayu000/claude-skill-registry 163
-
screpcombiningexpression
Combine scTCR/BCR repertoire data with scRNA-seq expression data using `scRepertoire::combineExpression()`. This process integrates immune receptor information (CDR3 sequences, V(D)J genes, clonotypes) into a Seurat object's metadata, enabling clonotype-aware gene expression analysis.
majiayu000/claude-skill-registry 163
-
proxychains
Auto-detect network issues and force proxy usage with proxychains4. Use this skill when encountering connection timeouts, DNS failures, or blocked network access. Default proxy is http://127.0.0.1:9910
majiayu000/claude-skill-registry 163
-
introspection
Analyze and explain Claude's reasoning, decision patterns, and problem-solving approaches. Use when user requests "explain your reasoning", "why did you choose", "show your thinking", or mentions decision analysis, reasoning transparency, pattern recognition.
majiayu000/claude-skill-registry 163
-
workflow-start
Activate a workflow from the injected catalog. Use when the workflow-router hook injects a catalog and a matching workflow is identified, or when the user explicitly requests a workflow activation (e.g., "start feature workflow", "activate bugfix workflow").
majiayu000/claude-skill-registry 163
-
Swift iOS Design Best Practices
Comprehensive guide to UI/UX design principles, architectural patterns, and animation techniques for building high-quality iOS apps with Swift.
majiayu000/claude-skill-registry 163
-
in2-premortem-analysis
Apply IN2 Premortem Analysis to assume failure has occurred and work backward to identify causes.
majiayu000/claude-skill-registry 163
-
starknet-react-rules
Specific rules for Starknet React projects, focusing on blockchain integration.
majiayu000/claude-skill-registry 163
-
tailwindcss-framework-integration
Tailwind CSS integration guide for React, Vue, Next.js, and other frameworks
majiayu000/claude-skill-registry 163
-
cui-css
Modern CSS standards covering essentials, responsive design, quality practices, and tooling for CUI projects
majiayu000/claude-skill-registry 163
-
vibe-coding-tutor
AI skill that teaches while coding through MCQs, TDD enforcement, and systematic debugging. Activate on any code request. NEVER skip the Vibe Check. ALWAYS use TDD. ALWAYS verify before claiming completion.
majiayu000/claude-skill-registry 163
-
enrich-ioc
Enrich an IOC (IP, domain, hash, URL) with threat intelligence. Use when you need to look up reputation and context for an indicator using GTI and SIEM. Returns threat intel findings, SIEM entity summary, and IOC match status.
majiayu000/claude-skill-registry 163
-
analyze-ci
Analyze failed GitHub Action jobs for a pull request.
majiayu000/claude-skill-registry 163