Loading...
Loading...
Found 479 Skills
Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.
AI agent workflow with interview-driven planning and team-based execution. Use /design to start planning, /work to execute.
Before starting any significant task, force explicit evaluation of available skills. For each potentially relevant skill, state YES/NO with reasoning. Only proceed to implementation after skills have been consciously evaluated and activated. Prevents the ~50% "coin flip" activation rate that occurs when skills are passively available but not deliberately considered.
[PREREQUISITE] Install and configure Godot MCP server for programmatic scene manipulation via Model Context Protocol. Use when user explicitly requests MCP-based scene building or automation. NOT for manual Godot workflows. Keywords MCP, Model Context Protocol, scene automation, npx, claude_desktop_config.
Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the recommended path: LiveKit Cloud + LiveKit Inference. REQUIRES writing tests for all implementations.
Create visualize finance logic diagrams (e.g., Draw.io XML) to explain complex finance transmission chains or finance logic flows.
Full RPI lifecycle orchestrator. Research → Plan → Pre-mortem → Crank → Vibe → Post-mortem. One command, sequential skill invocations with human gates and hands-free validation. Triggers: "rpi", "full lifecycle", "end to end", "research to production".
Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.
Generate structured prd.json files for autonomous agent loops (Ralph Wiggum pattern). Use when planning bulk/batch tasks, migrations, refactoring campaigns, or any work that can be decomposed into independent items with verification steps.
Sequence tasks from a feature breakdown into an optimal execution order, identify dependencies and parallelization opportunities, and create an agent-ready execution sequence. Use when you have a feature breakdown and need to determine the correct order to build tasks and which can run in parallel.
Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared state or ordering dependencies.
Convert abstract edge concepts into strategy draft variants and optional exportable ticket YAMLs for edge-candidate-agent export/validation.