Total 56,326 skills, AI & Machine Learning has 9376 skills
Showing 12 of 9376 skills
STUB — installed at ~/openclaw/skills/coding-agent/SKILL.md
Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills in the right order at the right depth. Auto-activates on any coding task. Centralizes the decision logic for which skills to use, how deep each goes, and how artifacts pass between them. Handles three pipeline variants: standard (plan-interview, intent-framed-agent, context-surfing, simplify-and-harden, self-improvement), team-based (agent-teams-simplify-and-harden), and CI (simplify-and-harden-ci, self-improvement-ci). Use this skill whenever starting any coding work — it determines the appropriate pipeline depth and variant automatically. Does not replace individual skills; dispatches to them.
Guide to video generation in MassGen. Use when creating videos from text prompts or images across Grok, Google Veo, and OpenAI Sora backends.
Guide to audio generation and understanding in MassGen. Covers text-to-speech, music, sound effects, and audio understanding across ElevenLabs and OpenAI backends.
Use when running autonomous loops, repeated operations, or when detecting stagnation patterns - enforces rate limits, protects configuration files, manages recovery with cooldown periods, and prevents infinite loops during autonomous development
Use when creating new skills, commands, or agent definitions for Claude Code, including writing SKILL.md files, defining triggers, and testing skill behavior
Unified task execution protocol for Codex-only work. Supports Single Task, Epic Task, and Batch Task while preserving CSV truth-source, validation gates, context recovery, and Debug-First failure exposure. WHEN TO USE: user asks to "track tasks", "create todo list", "make a plan", "track progress", "long task", "big project", "build from scratch", "autonomous session", "跟踪任务", "自主执行", "长时任务", "从零开始", "任务管理", "做个计划", "大工程", or when a task clearly requires 3+ ordered steps that produce file changes. DO NOT USE: single-step fixes, pure Q&A, code review, explaining code, search/research tasks, tasks with fewer than 3 steps, or tasks that do not produce file changes.
Guide pour la création de serveurs MCP (Model Context Protocol) de qualité permettant aux LLM d'interagir avec des services externes via des outils bien conçus. À utiliser pour construire des serveurs MCP intégrant des API ou services externes, en Python (FastMCP) ou Node/TypeScript (MCP SDK).
Post-session retrospective: audits efficiency, proposes skill/memory/CLAUDE.md updates, and generates coaching feedback
Integrated AI agent orchestration skill that combines plannotator, ralphmode, team or bmad execution, agent-browser verification, and agentation feedback loops, while maintaining a project-local `.jeo` ledger for planning, development, and QA. Use when the user wants an end-to-end multi-agent workflow with plan approval, implementation, UI review, cleanup, and durable task history. Triggers on: jeo, annotate, ui-review, multi-agent orchestration.
Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.
When the user wants to cut 2D sheets optimally, minimize waste in rectangular sheet cutting, or solve two-dimensional cutting stock problems. Also use when the user mentions "2D cutting," "sheet cutting optimization," "panel cutting," "glass cutting," "steel plate cutting," "guillotine cutting patterns," "two-stage cutting," or "2D trim loss." For 1D problems, see 1d-cutting-stock. For bin packing, see 2d-bin-packing. For irregular shapes, see nesting-optimization.