智能体
Agent 规划、多步流程与编排
aio-code-review
aiocean
Ultimate code review with multi-phase pipeline. Triggers when user says "review code", "code review", "review this", "review changes", "review PR", "ultra review", or mentions "comprehensive review". Runs domain-specific skills (Go, iOS, React, XState, observability), CodeWiki static analytics, 4 core + 4 conditional parallel review agents, and a critic meta-review with confidence scoring.
pinion-chain-intel
chu2bard
On-chain intelligence, transactions and wallet tools on Base. 9 x402-paywalled skills at $0.01 USDC each.
isms
ssiumha
ISMS-P certification preparation. Use when preparing for ISMS-P audit, checking compliance items, creating checklists, or planning implementation. 인증 준비, 항목 조회.
agent-registry
MaTriXy
MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or .claude/agents/. Provides lazy loading via search and get tools. Use when: (1) user task may benefit from specialized agent expertise, (2) user asks about available agents, (3) starting complex workflows that historically used agents. This skill reduces context window usage by ~95% compared to loading all agents upfront.
typescript-sdk
inkeep
Use when creating, modifying, or testing AI Agents built with the Inkeep TypeScript SDK (@inkeep/agents-sdk).
orchestrator
kcns008
Platform Agent Swarm Orchestrator — coordinates work across all specialized agents, manages task routing, runs daily standups, and ensures accountability across Kubernetes and OpenShift platform operations.
claude-agent-sdk
ssiumha
Builds Claude Agent SDK agents in Python. Use when creating custom tools, hooks, sub-agents, or MCP integrations with the Agent SDK. Python 에이전트 구축 시 사용.
article-agent-context-research
HayattiQ
記事執筆の前工程として、周辺情報をWeb等で検索し、一次情報・論点・反論・用語・数字を揃えたContext Packを作る。
agent-assistant
nahisaho
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction Use when: User reports agent is stuck, looping, or needs memory/learning management
orchestrator
nahisaho
Integrated orchestrator agent that manages and coordinates 25 specialized AI agents for Specification Driven Development Trigger terms: orchestrate, coordinate, multi-agent, workflow, execution plan, task breakdown, agent selection, project planning, complex task, full lifecycle, end-to-end development, comprehensive solution Use when: User requests involve orchestrator tasks.
market-researcher-agent
michaelboeding
Use this skill to research markets, understand trends, find opportunities, and validate ideas. Triggers: "market research", "market analysis", "market opportunity", "market size", "TAM SAM SOM", "industry analysis", "market trends", "validate idea", "market validation", "customer research", "market sizing", "opportunity analysis" Outputs: Market report with size, trends, opportunities, competitive landscape.
product-engineer-agent
michaelboeding
Use this skill to design new products, iterate on product ideas, or develop product specifications. Triggers: "design product", "new product idea", "product concept", "product development", "product spec", "iterate on product", "product design", "invention", "prototype spec", "product requirements", "product engineering", "develop product" Outputs: Product specification, BOM estimate, feature breakdown, differentiation analysis.
patent-lawyer-agent
michaelboeding
Use this skill for intellectual property guidance, prior art research, patent strategy, and drafting patent applications. Triggers: "patent", "prior art", "IP protection", "intellectual property", "patent search", "patentability", "patent claims", "invention disclosure", "patent strategy", "trade secret", "patent application", "freedom to operate", "infringement", "draft patent", "write patent", "provisional patent", "patent document", "design around", "get around patent", "avoid patent", "work around patent", "FTO", "freedom to operate analysis", "patent analysis" Outputs: Patentability assessment, prior art report, draft claims, IP strategy, full patent application draft, design-around analysis. DISCLAIMER: This is informational only, not legal advice. Consult a licensed patent attorney.
competitive-intel-agent
michaelboeding
Use this skill to analyze competitors, find competitive gaps, and develop competitive strategy. Triggers: "competitor analysis", "competitive analysis", "analyze competitor", "competitive intel", "competitive intelligence", "competitive landscape", "competitor comparison", "beat competitor", "competitor weakness", "competitive advantage", "competitor research" Outputs: Competitive matrix, gap analysis, differentiation strategy, battlecards.
parallel-builder
michaelboeding
Divide-and-conquer implementation from specs/plans. Decomposes a reference document into independent tasks, assigns each to a builder agent, executes in parallel waves respecting dependencies, then integrates results. Use when you have a spec, PRD, plan, or large feature to implement quickly with parallel execution.
feature-council
michaelboeding
Multi-agent feature implementation. Spawns independent solver agents that each implement the feature from scratch, then synthesizes the best elements from each. Use when building complex features where you want diverse approaches and comprehensive edge case coverage.
review-analyst-agent
michaelboeding
Use this skill to analyze product reviews, find common issues, and prioritize improvements. Triggers: "analyze reviews", "review analysis", "customer feedback", "what are people saying", "product reviews", "review sentiment", "find complaints", "customer complaints", "improvement recommendations", "voice of customer", "VOC analysis", "feedback analysis" Outputs: Prioritized issues, sentiment analysis, improvement recommendations.
debug-council
michaelboeding
Research-aligned self-consistency for debugging. Spawns independent solver agents that each explore and debug the problem from scratch. Uses majority voting. Based on "Self-Consistency Improves Chain of Thought Reasoning" (Wang et al., 2022). Use for critical bugs, algorithms, or when other approaches have failed.
portkey-ca-agent-skills
Portkey-Wallet
"Portkey CA wallet registration/auth/guardian/transfer operations for agents."
create-agent
jpoutrin
Create a new Claude Code agent with proper YAML frontmatter structure. Use when the user wants to add a specialized agent to a plugin. Handles agent file creation with name, description, tools, model selection, and color configuration.
beautiful-mermaid
third774
Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.
agent-skills
third774
Author and improve Agent Skills following the agentskills.io specification. Use when creating new SKILL.md files, modifying existing skills, reviewing skill quality, or organizing skill directories with proper naming, descriptions, and progressive disclosure.
agent-comms
buddyh
"Send messages to other Claude Code or Codex sessions via tmux. Hand off complex debugging context, get second opinions, share detailed technical findings across sessions."
github-actions-container-build
pigfoot
Build multi-architecture container images in GitHub Actions. Matrix builds (public repos with native ARM64), QEMU emulation (private repos), or ARM64 larger runners (Team/Enterprise). Uses Podman rootless builds with push-by-digest pattern