execute
Use when the user wants to execute tasks autonomously, run compounder on a tasks.md file, start autonomous development, compound through a task list, or implement tasks iteratively. Guides autonomous task execution using compound loops.
creating-subagents
Guide for creating custom Claude Code subagents (Task tool agents). Use when building specialized autonomous agents for specific domains or workflows. Covers agent definition, frontmatter options, tool restrictions, and spawning patterns.
worker-dispatch
Use to spawn isolated worker processes for autonomous issue work. Creates git worktrees, constructs worker prompts, and handles worker lifecycle.
autonomous-orchestration
Use when user requests autonomous operation across multiple issues. Orchestrates parallel workers, monitors progress, handles SLEEP/WAKE cycles, and works until scope is complete without user intervention.
autonomous-operation
Use when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure to work until goal is achieved
e2e-testing-agent
Build autonomous end-to-end full-stack testing agents using Claude's Computer Use API, LangGraph orchestration, and hybrid Playwright automation. Use this skill when building testing infrastructure, test automation, CI/CD test integration, or self-healing test systems.
openai-agents
|
soul_agent
The autonomous layer that gives the soul agency. Observe, judge, decide, act - exercising judgment within the confidence-risk matrix.
speclet-loop
Execute one autonomous iteration - implement the next story from spec.json
sf-ai-agentforce
>
agent-creator
>
implement
Autonomously implement tasks from specs, plans, or issues using subagents with TDD and code review
consulting-agents
Use when you need information you don't have, expertise outside your comfort zone, or fresh eyes on code - dispatches agents to research, advise, or review. NOT for implementation delegation (see subagent-driven-development).
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
ai-agent-basics
Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design
stagehand
Stagehand Python AI-powered browser automation. Use for web scraping, form filling, clicking elements, extracting structured data, and autonomous multi-step browser workflows. Covers act(), extract(), observe() methods and Computer Use Agent patterns.
create-subagent
Guide for creating specialized Claude Code subagents with proper YAML frontmatter, focused descriptions, system prompts, and tool configurations. Use when the user wants to create a new subagent, custom agent, specialized AI assistant, or mentions creating/designing/building agents or subagents.
Page 1 of 5 · 76 results