Agents
AI agents and automation
improving-skills
by taisukeoe
Improve existing agent skills based on user feedback and best practices. Use when the user wants to fix, enhance, or refactor an existing skill. Gathers user feedback first, then applies technical analysis and implements improvements.
unified-taskflow
by ooooooooooooooooooop
【强制】复杂任务管理系统。 AI 必须在遇到以下情况时先读取此 SKILL.md，再执行任何操作： - 多文件变更、规划设计、新功能开发 - 用户说"帮我想想/重构/升级/实现" 禁止使用内置 agentic_mode 的 artifact 目录处理复杂任务，必须使用项目根目录下的 .taskflow/ 目录。
Agentic Orchestration for Oracle Cloud
by oci-ai-architects
Claude Code skills for OCI AI Architects. Community-led reference implementations and patterns.
session-verify
by 101mare
End-of-session verification skill that validates all changes made during a coding session. Checks for bugs, security vulnerabilities, dead code, efficiency issues, and documentation gaps. Does NOT handle: plan review (use plan-review), PR review (use pr-review), debugging (use systematic-debugging), implementation (use tdd). Use when: finishing a task, before committing, user says "verify", "check my changes", "review session", "are we done?", "everything correct?", or at end of coding sessions. Orchestrates specialized review agents and ensures documentation is updated.
analyze-crypto
by jssfy
一键综合分析加密货币。通过并行子代理采集价格、新闻情绪、赛道对比、市场环境、项目基本面五个维度，交叉分析后输出 HTML 报告（含24小时行情和7日趋势）。触发词：分析BTC、analyze ETH、比特币怎么样、SOL值得买吗。
Oracle Agent Spec Expert Skill
by oci-ai-architects
Claude Code skills for OCI AI Architects. Community-led reference implementations and patterns.
rag-patterns
by Agentient
Vertex AI RAG Engine integration patterns for grounding agent responses in private data sources including corpus management, retrieval tool creation, and citation extraction. PROACTIVELY activate for: (1) RAG pipeline integration and Vertex AI RAG Engine setup, (2) corpus creation and document ingestion, (3) retrieval tool configuration and grounding metadata parsing. Triggers: "add rag", "rag pipeline", "vertex ai search"
coverage-gated-refactor
by Mr0bean
"Drive full-project modular refactors with a strict pipeline: prioritize splitting oversized files, enumerate candidates for user scope selection, raise per-module test coverage to at least 90 percent with verified runnable tests, refactor frontend and backend in slices with immediate regression checks, update related documentation, and finish only when all selected modules plus historical tests pass."
router-builder
by mindmorass
Build intent routers for agent task distribution
Claude Code Starter Kit
by emersonmccuin-pixel
Go from zero to creating your first project with Claude Code in under an hour. Includes a guided discovery interviewer skill (/interviewer) that helps you figure out what to build, plus three structured workflows (app, document, plan) that walk you through actually creating it. No coding experience required.
pedagogy-review
by clearsmog
Run holistic pedagogical review on academic slides and educational documents. Checks narrative arc, student prerequisites, worked examples, notation clarity, and deck pacing. Supports .tex, .qmd, and .typ slide decks.
adk-fundamentals
by Agentient
Foundational knowledge for creating ADK (Agent Development Kit) agents including environment setup, project structure, and basic agent scaffolding. PROACTIVELY activate for: (1) new ADK agent creation, (2) ADK project setup and environment configuration, (3) AdkApp initialization and understanding core ADK architecture. Triggers: "create adk agent", "new agent", "setup adk"
claude-agent-coderabbit-code-reviewer
by monkey1sai
Converted from Claude plugin agent "code-reviewer" (coderabbit). Use
pattern-recognition-specialist
by carmandale
Analyzes code for design patterns, anti-patterns, naming conventions, and duplication. Use when checking codebase consistency or verifying new code follows established patterns.
orchestrating-workflows
by tenzir
Orchestrate Tenzir workflows. Use when executing Tenzir workflows.
deepen-plan
by carmandale
Enhance a plan with parallel research agents for each section to add depth, best practices, and implementation details
techdebt
by MitchellX
"Scan codebase for technical debt: duplicated code, code smells, architectural issues, and maintenance risks. Uses parallel subagents for fast analysis. Run at end of session to keep codebase clean."
your-skill-name
by ooooooooooooooooooop
One-line description of what this skill does
sentry-setup-ai-monitoring
by getsentry
Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.
agent-native-reviewer
by carmandale
Reviews code to ensure agent-native parity — any action a user can take, an agent can also take. Use after adding UI features, agent tools, or system prompts.
feature-video
by carmandale
Record a video walkthrough of a feature and add it to the PR description
github-project-analyzer
by OliverOuyang
GitHub 开源项目自动化分析器 - 自动克隆项目、测试功能、探索使用场景、评估有效性并生成完整的 MD 分析报告。触发方式：命令 /github-analyze、/项目分析，或包含关键词（分析项目、评估项目、GitHub 项目）时自动触发。适用场景：(1) 技术选型评估，(2) 开源项目调研，(3) 竞品分析，(4) 学习研究。
ai-engineer
by sidetoolco
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use when working with LLM features, chatbots, AI-powered applications, or agentic systems.
managing-skills
by mikekelly
"Install, find, update, and manage agent skills. Use when the user wants to add a new skill, search for skills that do something, check if skills are up to date, or update existing skills. Triggers on: install skill, add skill, get skill, find skill, search skill, update skill, check skills, list skills."