Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Add new skills to an existing workflow and update all related documentation. Use when user wants to add skills from GitHub URLs to a workflow (e.g., "add this skill to the workflow", "δΈΊε·₯δ½ζ΅ζ·»ε ζθ½")....
This skill should be used when the user asks to "install a skill", "add a skill to the project", "unpack a skill", or "integrate a new skill". Automates the full workflow of unpacking .skill...
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool...
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool...
Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project
This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent...
This skill should be used when the user asks to "create a skill", "write a new skill", "build a custom skill", "make a Claude Code skill", "update a skill", "modify a skill", "edit existing...
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
Manage local skills - list, add, remove, search, edit
Conducts a deep, multi-round interview to clarify ambiguous requirements and produces a structured specification document. Automatically discovers requirement files and asks probing, non-obvious...
Transform project descriptions and feature requests into comprehensive specifications and actionable task lists. Use when the user wants to: (1) Create a specification from a project/feature...
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations,...
Local-first backlog workflow. Use when planning work, creating/updating backlog items, writing ADRs, enforcing Ready gate, generating views, or maintaining derived indexes (SQLite/FTS/embeddings).
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation...
Guide for removing skills from an existing workflow and updating all related documentation. Use when user wants to remove skills from a workflow (e.g., "remove skill", "delete skill", "移ι€ζθ½", "ε ι€ζθ½").
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation...
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation...
Generate a complete, standards-compliant SKILL.md for a new Anthropic Skill based on a given capability description.
The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.