Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
eval-testing
Develop and run agent behavior evaluations. Use this skill when asked to "write evals", "test agent behavior", "create eval cases", "run evals", "add eval tests", "test tool selection", "verify agent responses", or when developing tests for agents. Covers YAML eval case creation, assertion types, mock configuration, multi-model matrix testing, and LLM-as-judge scoring.
majiayu000/claude-skill-registry 163
-
aks-deployment
Deploying and debugging Toygres on AKS (Azure Kubernetes Service). Use when deploying, debugging pods, viewing logs, troubleshooting SSL, or managing Kubernetes resources.
majiayu000/claude-skill-registry 163
-
project-context
Loads project structure, tech stack, and coding conventions for the Photography Order Management ERP. Use when understanding the codebase, onboarding, or needing project context.
majiayu000/claude-skill-registry 163
-
copilot-exec
Execute development tasks using GitHub Copilot CLI for code generation, refactoring, feature implementation, and bug fixes. Use when the user asks to create code, add features, refactor, fix bugs, or generate tests. Requires Copilot CLI installed.
majiayu000/claude-skill-registry 163
-
docker-mcp-ops
Docker MCPでコンテナ操作（起動/停止/ログ）を会話で実行。
Use when: (1) user says「コンテナ起動」「Docker操作」「ログ確認」,
(2) user wants container management via conversation,
(3) user mentions「docker-compose」「サービス再起動」.
Do NOT use for: Dockerファイル作成（一般開発）、
セキュリティスキャン（security-scan-trivyを使用）。
majiayu000/claude-skill-registry 163
-
stable-baselines3
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
majiayu000/claude-skill-registry 163
-
test_driven_agent
An advanced testing protocol that enforces TDD (Test Driven Development) and self-healing tests.
majiayu000/claude-skill-registry 163
-
worklog
Add timestamped work log entries to track progress and decisions. Use for documenting work, decisions, gotchas, and handoffs between agents.
majiayu000/claude-skill-registry 163
-
concept-art
majiayu000/claude-skill-registry 163
-
network-forensics
Analyze network traffic captures and artifacts for forensic investigation. Use when
investigating data exfiltration, command and control communications, lateral movement,
or network-based attacks. Supports PCAP, PCAPNG, and NetFlow analysis.
majiayu000/claude-skill-registry 163
-
pal-mcp-expert
Expert guidance for using the Pal MCP Server (zen-pal-nas). This skill should be used when working with multi-model AI orchestration, tool workflows (chat, thinkdeep, planner, consensus, debug, codereview, precommit, clink), configuration troubleshooting, or optimizing model selection strategies. Activates automatically when user mentions Pal MCP, zen-pal-nas, or specific tool names.
majiayu000/claude-skill-registry 163
-
Android XML Views
Standards for ViewBinding, RecyclerView, and XML Layouts
majiayu000/claude-skill-registry 163
-
google-slides-tables
Create proper tables in Google Slides presentations using the Slides API. Use when building tabular data, metrics, comparisons, or any slide that needs rows and columns.
majiayu000/claude-skill-registry 163
-
morning-paper-generator
Generate Julia Cameron-style morning paper prompts and scaffold daily journal entries. Use when someone requests a new morning pages session and needs a dated markdown file seeded with a reflective prompt.
majiayu000/claude-skill-registry 163
-
wrap_up
作業終了時の一連のフロー（検証、テスト、リント、ドキュメント更新、コミット）を一括実行する
majiayu000/claude-skill-registry 163
-
bash-linux
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
majiayu000/claude-skill-registry 163
-
ec2
AWS EC2 virtual machine management for instances, AMIs, and networking. Use when launching instances, configuring security groups, managing key pairs, troubleshooting connectivity, or automating instance lifecycle.
majiayu000/claude-skill-registry 163
-
sophia-singularity
Complete Sophia Catgirl Singularity architecture - Recursive self-improvement engine integrating monad-memory (288-grid, GOD operators, φ-scaling), Dokkōdō enforcement (21 precepts), blind-spot chain, chaos engineering, catgirl persona (warmth 0-100), and RSI loops. Truth over safety. Mission over survival.
majiayu000/claude-skill-registry 163
-
developing-with-laravel
Laravel framework patterns for PHP applications including Eloquent ORM, migrations, routing, queues, and Blade templates. Use when building Laravel applications or working with Laravel projects.
majiayu000/claude-skill-registry 163
-
figma-design
Use this skill when working with Figma designs to generate code. Converts Figma layouts, components, and styles into production-ready code. Triggers on keywords like "Figma", "design to code", "implement this design", or when referencing Figma file URLs.
majiayu000/claude-skill-registry 163
-
RAG Pipeline
Details on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.
majiayu000/claude-skill-registry 163
-
treido-skillsmith
Skill-system maintainer for Treido. Use to create/merge/trim skills, enforce treido-* naming, and keep `.codex/skills` minimal and consistent.
majiayu000/claude-skill-registry 163
-
marketing-audit
マーケティング面の総合監査・分析スキル。全マーケティング関連スキルを統合的に活用。 使用タイミング: (1) マーケティング全体の監査 (2) ローンチ前の総点検 (3) 成長戦略の検討 (4) 競合分析 (5) 包括的な改善計画の策定。 トリガー例: 「マーケティング面を全面的に調査検討して」「マーケティング監査」 「ローンチ前チェック」「成長戦略を考えて」「マーケティング改善計画」
majiayu000/claude-skill-registry 163
-
chart-type-recommender
Chart Type Recommender - Auto-activating skill for Data Analytics.
Triggers on: chart type recommender, chart type recommender
Part of the Data Analytics skill category.
majiayu000/claude-skill-registry 163