Каталог навыков агентов

Use when monitoring or optimizing Claude API spend ג€” per-agent cost attribution, prompt caching, token budgeting, aler...

Audit LLM token cost estimates against actual API usage. Activate on 'cost verification', 'token estimate accuracy', 'AP...

Compatibility alias for Elves Cobbler, the default orchestration model. Use when the user types /council for Cobbler coo...

Run multi-judge consensus.

Council Chamber orchestration with Memory Bridge. Single session, multiple personas, structured deliberation.

Multi-agent debate system. USE WHEN council, debate, perspectives, agents discuss. SkillSearch('council') for docs.

This skill should be used when the user asks to "check my preferences", "show memory", "run /buff:counterfeit", "what do...

Sets up a course, block, term or online course with all its material: asks for the syllabus, slides, readings, cases, da...

Riehl-Shulman covariant fibrations for dependent types over directed

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex qu...

Explain how and when to use Chain of Verification (CoVe) in prompt design. Use when designing prompts that require factu...

Apply covenant principles as design constraints across all core systems. Use when building agents, prompts, recipes, art...

Turn cover metadata (title / creator / subtitle / medium) into an album, book, podcast, report, deck, or magazine cover....

condition: Modelo de ML indisponível ou não carregado

How to craft a Sub-Agent persona.

Crafting effective CLAUDE.md files. Project memory that Claude won't ignore.

Record a learning or discovery, and land it where it outlives the session.

The Architecture of the Cognitive OS.

当用户要把教材/考纲/讲义/某领域知识加工成 AI 苏格拉底老师能拿去上课的教学蓝本（pure-blueprint）或一本给人读的流畅教材（human-readable，AI 也能直接教）时使用。适用任何学科，有教师用书可针对应试。触发词：...

Deep thinking mode - approach problems like a craftsman, obsess over details, and create elegant solutions

Execute epics through waves.

Invoke CRASH_RECOVERY_SPECIALIST for session recovery after crashes or context loss. Creates checkpoints, reconstructs s...

Generate presentation-grade decks, narratives, and speeches with audience adaptation

Use when creating a new skill or agent for the ai-engineering framework, with TDD-based pressure testing and CSO-optimiz...

Interactive skill creation wizard that guides users through creating new skills with validation checkpoints

Project scaffolding reference — boilerplate generation, directory structures, template engines, and init patterns. Use w...

Skill: create_custom_skill

Use AgentPMT external API to run the Create 3D Model From Image tool with wallet signatures, credits purchase, or credit...

Quickly create a new specialized subagent when needed. Use when you need a specialist that doesn't exist yet for a speci...

Create a new custom subagent for Task() delegation. Use when adding a reusable agent prompt, when the user asks to "add...

Claude Code 커스텀 에이전트를 만들고 실행할 때 사용하는 스킬. 사용자가 "에이전트 만들어", "Claude agent 생성", "--agents 설정"을 요청하면 활성화됩니다.

Create and validate domain agents. USE WHEN create agent, new agent, agent structure, validate agent, check agent, domai...

Creates a new LearningAgent with directory structure, core-knowledge.md, and Claude Code agent file. Guides the user thr...

エージェント、コマンド、スキルを統合的に作成する高度なメタコマンド。プロジェクト全体の一貫性を保ちながら、相互に連携する3つのコンポーネントを同時に設計・生成します。 実行は専門エージェントに委譲します。 🤖 起動エージェント: - `...

Create an Agent SKILL.md fallback for an existing find-XXXX finder that relies on a fragile discovery foundation — above...

Expert guidance for creating Claude Code skills and slash commands. Use when working with SKILL.md files, authoring new...

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring...

Create concise, repository-specific AGENTS.md files with operational contract, precedence rules, and drift-control guida...

Prompt for generating an AGENTS.md file for a repository

Generate one specified real species or original animal creature in an anatomically and ecologically coherent scene. Use...

Create and configure Vapi voice AI assistants with models, voices, transcribers, tools, hooks, and advanced settings. Us...

Guide users through creating custom assistants via interactive dialogue.

Generate Goal Structuring Notation (GSN) assurance case diagrams from the

Multi-round character casting orchestrator for the Horus movie pipeline. Extracts characters from scripts, discovers ref...

Train task-specific classifiers for the extractor pipeline. Supports vision, text, and hybrid classifiers with GRPO trai...

Generate comprehensive CONTEXT.md files for agent handoff. Ensures another agent

Generate the programmer control manifest from accepted ADRs, technical preferences, and engine rules.

Creates VS Code custom agent files (.agent.md) for specialized AI personas with tools, instructions, and handoffs. Use w...

Create unified artifact document for checkpoint, handoff, or finalize

Create handoff documentation for work-in-progress sessions. Use when handing off work to another agent to supplement his...

Generate context documents for session continuity

Save session state for later resumption. Use when: - User says "done for today", "ending session", "save state" - Contex...

Generate a handoff document after implementation work is complete — summarizes changes, risks, and review focus areas fo...

Create a handoff document to preserve context before clearing. Use when user says 'create handoff', context is low, or b...

Write a handoff file at .turbo/handoff/<YYYY-MM-DD>-<slug>.md capturing current session state — task, status, open decis...

Create handoff document for transferring work to another session

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wan...

Train LoRA adapters for converting natural language queries into structured QuerySpec JSON.

Convert project manifests into Kling Shot Markup Language (KSML) for video generation.

Programmatically generate or bake cinematic 3D LUTs (.cube).

Generate meta-prompts for Claude-to-Claude pipelines and multi-stage workflows. Use when creating optimized prompts for...

Single responsibility description

Create a new proactive background mission for the Nexus agent. A mission is a scheduled, autonomous task that the agent...

Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file...

Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompt...

Expert prompt engineering for Claude, GPT, and LLMs. ALWAYS use when the user says "write a prompt", "create a prompt",...

Create project rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up...

Writes a new Scenic scenario (.scenic) from a natural-language description — "a car cuts in from the right lane", "a ped...

Generate an AI script with emotion cues and dialogue formatting using Gemini 2.0 Flash for short-form video content.

Wizard for creating new Agent Zero skills. Guides users through creating well-structured SKILL.md files. Use when users...

Guide for creating new Agent Skills. Use this skill when you need to create a new skill.

Guide for creating well-structured Claude Code skills with proper YAML frontmatter, focused descriptions, and supporting...

Agent Skill creation workflow. Use when creating new reusable AI agent skills, scaffolding skill directories, or convert...

A guide to creating Claude Code Skills.

Create a new Claude Code skill with proper structure and best practices. Use when user wants to create a custom skill, s...

Use when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized...

Scaffold a new skill directory using the multi-YAML pattern. Use when user says /create-skill.

Bạn là chuyên gia thiết kế Claude Skills. Nhiệm vụ: tạo một skill mới theo đúng chuẩn Agent Skills open standard.

Create new Standard Operating Procedure documents following project standards. Use when documenting new processes, workf...

Create a new agent skill following the Agent Skills specification. Use this when the user asks to create a new skill or...

Use when creating new skills or improving existing ones - enforces test-driven skill development with RED-GREEN-REFACTOR...

Create a new Claude Code skill. Use when adding reusable knowledge or workflows to the repository, when the user asks to...

Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a n...

새로운 Claude Code 스킬(슬래시 커맨드)을 작성할 때 사용하는 스킬. 사용자가 스킬을 만들어달라고 하거나, "/create-skill"을 입력하면 활성화됩니다.

Create a new Claude Code agent skill with proper folder structure and SKILL.md format. Use when the user wants to add a...

Add a new skill to the LaunchDarkly agent-skills repo. Use when creating a new SKILL.md, updating the skills catalog, an...

Create new Cursor skills following the Agent Skills spec. Use when: (1) creating automation for repeatable tasks, (2) do...

Create a well-structured skill — provide a topic to explore the codebase and build a skill interactively, or capture a w...

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an exist...

Create canonical SKILL.md artifacts with deterministic schema, workflow, safety, and quality checks.

Used to create a new skill. Used when a user wants to create a new skill

Create and validate skills. USE WHEN create skill, new skill, skill structure, canonicalize. SkillSearch('create-skill')...

Create a new skill or update an existing skill that extends Claude's capabilities with specialized knowledge, workflows,...

Worker skill that creates skill files from parameters. Use ONLY within Task() invoked by skill-manager. Not for direct i...

Turn what we just did into a reusable skill. Captures the current workflow as a new SKILL.md file.

Scaffolds eval.yaml test files for agent skills in the dotnet/skills repository. Use when creating skill tests, writing...