Loading...
Loading...
Found 98 Skills
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Write node content documents. Read download.txt, integrate local materials for each node and write detailed, accurate, and complete Markdown documents. Each sub-agent processes one node in parallel, outputting a complete node document including overview, directory/mind map, flow chart, online image URL, and reference materials. Suitable for scenarios requiring systematic and structured content creation.
Run Gemini CLI for AI-powered tasks, code understanding, file operations, and automation. Free tier with Google OAuth (included in Gemini Advanced). Use for fast generation, bulk content, debugging, and research. Preferred for load balancing sub-agent work (35% weight).
Full optimization workflow, sub-agent launch templates, agent communication contracts, default configurations, tuning strategy, and knowledge base update protocol. Use when: (1) starting an optimization cycle, (2) launching a Profiler or Designer sub-agent, (3) interpreting or formatting agent communication, (4) updating the knowledge base after a profiling or implementation iteration, (5) deciding default configurations or tuning strategy for a kernel.
Run Claude Code CLI for complex tasks, code generation, analysis, and research. Uses Anthropic OAuth (included in Claude Pro). Use for extended thinking, code review, architecture decisions. Preferred for load balancing sub-agent work (35% weight).
Spawn a Team Leader agent that manages multiple sub-agents working toward a common goal. Team Leader reads requirements, decomposes work, assigns personalities and tasks, manages communication between team members, tracks progress, and reports results following ogt-docs task workflow. Integrates fully with docs-first system via task signals and status tracking.
Test, validate, and improve agent instructions (CLAUDE.md, system prompts) using sub-agents as experiment subjects. Measures instruction compliance, context decay, and constraint strength. Use for "test prompt", "validate instructions", "prompt effectiveness", "instruction decay", or when designing robust agent behaviors.
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
Provides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents. Trigger this when specifications, rules, or best practices for the ecosystem are required.
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
Provides guidance on choosing between Agent Teams and Sub-agents and executing complex plans with parallel coordination. Use when implementing complex features requiring multiple specialized teammates working in parallel.