Loading...
Loading...
Found 479 Skills
Review and approve (or reject) pending playbook update proposals from the playbook-monitor agent and apply approved changes to the practice profile. Use when the playbook-monitor agent has surfaced proposals, when the user says "review playbook proposals", "what playbook updates are pending", or wants to step through deviation-driven playbook changes.
Use when tasks are complex and require full microservices collaboration: The main agent acts as a pure Orchestrator, strictly prohibited from writing code personally, and is responsible for accurately assigning responsibilities such as positioning, planning, coding, testing, and review to corresponding sub-agents (explorer, planner, worker, verifier, reviewer, fixer). This Skill enforces microservices workflow discipline, requiring full Chinese communication, minimal routing output, and minimized context transfer.
Guided, section-by-section Art Bible authoring. Creates the visual identity specification that gates all asset production. Run after /brainstorm is approved and before /map-systems or any GDD authoring begins.
Turn a vague, messy, or multi-part user ask into a clean, self-contained prompt that a fresh agent could execute without further questions. Interview the user one question at a time — walking down the decision tree, branching on each answer — until the prompt is tight, then output the final prompt as the deliverable. Trigger eagerly: any voice-dictated input, filler-heavy prose, underspecified references ("the thing", "that script"), multi-part requests, or any plan the user wants stress-tested. The skill itself can be skipped for trivial one-line requests where producing a prompt artifact would be pure ceremony — but once invoked, always produce the prompt, even if execution looks trivial.
Use when multiple subtasks have no shared files or dependencies and can be executed simultaneously.
Multi-source research synthesis — aggregate and compare 3+ sources or any source >5KB using sub-agent dispatch and SharedState
Use when the user wants Luma / 拾光 / 拾光智能体 / 拾光工具 to create a complete viral-remix short-video workflow: research, rewrite, TTS, digital human, PIP materials, subtitles, BGM, and cover.
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use when dealing with token budget management, context window limits, session handoff, state persistence across agents, or /clear strategies. Do NOT use for agent orchestration patterns (use moai-foundation-core instead).
Research codebase comprehensively using parallel sub-agents to answer user questions. Use when the user asks to "research the codebase", "understand how X works", or "investigate Y".
Orchestrates Story tasks. Prioritizes To Review -> To Rework -> Todo, delegates to ln-401/ln-402/ln-403/ln-404, hands Story quality to ln-500. Metadata-only loading up front.