Loading...
Loading...
Found 1,269 Skills
Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress test idea', 'devil advocate'.
无头模式 AI CLI 调用技能：支持 Gemini/Claude/Codex CLI 的无交互批量调用，包含 YOLO 模式和安全模式。用于批量翻译、代码审查、多模型编排等场景。
Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents on complex projects via CLI
Convert a course outline into a fully fleshed out intelligent textbook. Use when: (1) User provides a URL containing a course outline/syllabus (2) User asks to "generate a course" or "create a textbook" from an outline (3) User wants to expand a course description into full learning materials Generates: learning graph, chapter structure, MicroSim specifications, quizzes, glossary, and FAQ following the intelligent textbooks framework and evidence-based learning design principles.
Use this for complex project planning, full-stack feature implementation, or coordinating multiple skills (Design, Backend, Frontend, Ops) into a cohesive workflow.
Optimize Claude Code prompts for Opus 4.6, Sonnet 4.5, and Haiku 4.5 with model-aware reasoning settings, context control, safe tool use, and concise output shaping.
Orchestrates test planning pipeline (research → manual → auto tests). Coordinates ln-521, ln-522, ln-523. Invoked by ln-500-story-quality-gate.
Executes the implementation plan from a specification. Loops through plan phases, delegates tasks to specialists, updates phase status on completion. Supports resuming from partially-completed plans.
Эксперт ABM. Используй для account-based marketing, target account selection и personalized campaigns.
Create or update the skill registry for the current project. Scans user skills and project conventions, writes .atl/skill-registry.md, and saves to engram if available. Trigger: When user says "update skills", "skill registry", "actualizar skills", "update registry", or after installing/removing skills.
Fresh-subagent-per-task execution with two-stage review (ADR compliance + code quality). Use when an implementation plan exists with mostly independent tasks and you want quality gates between each. Use for "execute plan", "subagent", "dispatch tasks", or multi-task implementation runs. Do NOT use for single simple tasks, tightly coupled work needing shared context, or when the user wants manual review after each task.
Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation. Use when a user asks to refactor many files, split workstreams, analyze a target code area, and coordinate sub-agents with clear ownership and dependency-aware execution.