Loading...
Loading...
Found 39 Skills
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
Fix build and TypeScript errors with minimal changes
Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, following Cursor's patterns and directories (.cursor/agents/). Triggers on "cursor subagent", "cursor agent".
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.
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).
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).
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.
Coordinates multi-session, delegated, or long-running work with persistent state, recovery checks, and explicit status transitions. Use when a task spans multiple turns, multiple agents, background jobs, or scheduled loops, or when interrupted work must be resumed reliably.
Use when finding and claiming tasks. Matches tasks to your declared capabilities for optimal assignment.
Discover patterns, rules, and interfaces through iterative analysis cycles. Use when analyzing business rules, technical patterns, security, performance, integration points, or domain-specific areas. Includes cycle pattern for discovery to documentation to review workflow.
Create phased implementation plans from research findings. Invoke when a task needs an implementation plan.
Analyzes Claude Code session transcripts (JSONL files) to reveal context window content, token usage patterns, and decision-making processes using view_session_context.py tool. Use when debugging Claude behavior, investigating token patterns, tracking agent delegation, or analyzing context exhaustion. Triggers on "why did Claude do X", "analyze session", "check session logs", "context window exhaustion", or "track agent delegation".