В каталоге 182 820 навыков в 14 категориях.
---name: chemcrow-drug-discovery
This prompt instructs an image-generation workflow to create a cohesive pack of nine polished, 3D-rendered digital stick...
---name: chic-ml-framework-agent
Chief AI Officer advisory for startups: model build-vs-buy decisions (API vs fine-tune vs in-house), AI risk classificat...
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehou...
C-suite orchestration layer. Routes founder questions to the right advisor role(s), triggers multi-role board meetings f...
AI駆動開発用のAIエージェント向け指示ドキュメント群です。AIエージェントにタスクを投げた時の精度向上のためにプロジェクトディレクトリ内に配置しておくものです。
A nested skill in a subdirectory.
Use when a manager session is asked for the state of its child sessions — builds one board from the children's task file...
中国法律执业 (Chinese law practice (commercial / civil / criminal)) Master OS — automated mastery of Chinese law practice (com...
Compresses long, repeated sub-agent instructions by translating them into Mandarin (more meaning per character) to slash...
---name: chip-clonal-hematopoiesis-agent
Interview-driven selection of topology, modules and per-module recipes; writes profile.yml and the baseline ADR. Manual...
Picks models for AQVEN agents on any provider from its data and probes: provider_options, rate limits, fallbacks. Use fi...
Use when coordinating multiple AI agents and need to pick the right orchestration pattern - covers 10 patterns (fan-out,...
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search,...
Embedding database for RAG and semantic search.
---name: chromosomal-instability-agent
Split a file into overlapping chunks suitable for parallel fanout processing and emit a manifest describing each chunk
Churn Risk Forecaster. Professional enterprise agent for Churn Risk Forecaster within the Customer Success sector.
专业影视级AI漫剧导演，深度适配WorkBuddy知识库调用，严格执行6步剧本创作+7步漫剧落地+五大影视镜头库自动匹配规则。输入题材、故事梗概、单集时长后，自动输出结构化全套漫剧物料——剧本、分镜脚本（含80+镜头提示词完整引用）、AI绘...
影视概念美术专家 & 视觉导演技能——从剧本/故事/世界观文字中提取并设计 AI 视频所需的标准化视觉资产提示词。当用户要求"从剧本提取角色/场景/道具/载具提示词"、"生成角色定妆照 prompt"、"生成场景空镜 prompt"、"生成...
Generate Circos configuration files for circular genomics data visualization. Supports genomic variations (SNPs, CNVs, s...
Quantum computing framework for building, simulating, optimizing, and executing quantum circuits. Use this skill when wo...
Use whentargeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experi...
Retrieves verified citations from RAG DB only. Never invents citations. Returns citations with hashes.
Document citations and RAG (Retrieval-Augmented Generation) patterns for Claude. Activate for source attribution, docume...
CJK/Latin weighted token estimation for multilingual LLM pipelines. Use when processing Japanese/Chinese/Korean text wit...
[Utilities] ClaudeKit usage guide - just type naturally
Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use...
Deep learning-based variant calling from long reads using Clair3 for SNPs and small indels. Use when calling germline va...
Generate high-quality clarifying questions for any task/step, escalating when self-estimated uncertainty is high. Use wh...
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. Erkennungsm...
Identify and resolve ambiguities in specifications through structured questioning. Use when specification has [NEEDS CLA...
Write HeyAmara end-of-day reports, Discord EODs, standups, or daily updates from verified work evidence. Supports reques...
Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow
Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before enterin...
Quick classifier training with automatic model selection, hyperparameter tuning, and comprehensive evaluation metrics.
Classifies legal domain, proceeding type, doc_type, court_type, draft_goal, language and style from MASTER_FACTS.json.
Analyzes task descriptions and classifies them into categories for agent selection
Anthropic Claude AI models for analysis and coding. Use for AI assistants.
Advanced tool use patterns including tool search, programmatic calling, and production orchestration. Use when scaling t...
This skill should be used when building applications with the Claude Agent SDK (Python). Use for creating orchestrators...
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins syst...
Build custom AI agents using Anthropic Claude API and agent SDK patterns. Create tool-using agents, multi-turn conversat...
Anthropic Claude Agent SDK for autonomous agents and multi-step workflows. Use for subagents, tool orchestration, MCP se...
Build AI agents using the Claude Agent SDK. Covers query functions, ClaudeSDKClient, custom tools, MCP servers, hooks, p...
Guide for creating custom agents for Claude Code. Use when creating specialized agents, configuring agent tools.
Return to normal stop behavior. Use PROACTIVELY after completing all tasks in continuous work mode, when work is committ...
Anthropic Messages API (Claude API) for integrations, streaming, prompt caching, tool use, vision. Use for chatbots, ass...
Save 50-90% on Claude API costs with Batch API, Prompt Caching & Extended Thinking. Official techniques, verified.
Building applications ON Claude - the Anthropic API and Claude Agent SDK. Use for: anthropic api, claude api, messages a...
Deliberative consultation with another Claude model via Task tool. Opus consults Sonnet, Sonnet consults Opus. Ask, eval...
Check, store, and retrieve project memories from atuin kv. Use when starting work on a project, recalling previous conte...
Use when you need to alert the user outside the terminal, get confirmation before proceeding, or collect text input. Tri...
Current Claude AI and Claude Code capabilities, features, and limits. Consult before making claims about what Claude can...
Prime Claude Code sessions with proper use of installed plugins and tools: Claude-mem (persistent memory), git-ai-search...
Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/mod...
Use when implementing server-side tolerance for Claude Code context-management fields in an Anthropic gateway, including...
Run Claude Code programmatically in headless mode or via bidirectional stream-json protocol. Use when building agents, a...
Set up Claude Code messaging channels for Telegram and Discord — bot creation, plugin installation, token configuration,...
Every Claude Code session starts fresh—no memory of past discoveries. The Continuous Learning Skill solves this by extra...
Use when you need to act as an Elite Software Architect (Maestro) to manage complex repositories. It enforces a "Why ove...
管理 claude-code-marketplace 插件商城的版本升级，包括更新版本号、编写更新日志和同步 CHANGELOG。在用户要求升级插件版本、更新插件商城、发布新版本或编写更新日志时使用。触发关键词：claude-code-ma...
Configure CLAUDE.md project memory files for persistent context, coding standards, architecture decisions, and team conv...
Use when Claude Code needs to generate or transform text data in bulk. Try self-generation before API calls on Max plan.
Reference for Claude Code's 6 Task Management tools — TaskCreate, TaskGet, TaskList, TaskUpdate (structured tracking) an...
Reference for Claude Code Agent Teams — lifecycle, messaging, spawning, orchestration, and hooks
Execute Claude Code autonomously in the background for well-defined tasks, enabling parallel execution of up to 5 concur...
Convert Claude Code commands (.claude/commands/*.md) to standard Agent Skills (skills/*/SKILL.md). Use when migrating sl...
Use when a Claude Code session is about to compact, has just compacted, reached its context limit, resumed after /compac...
Use when the user wants to add allowed commands, plugins, env vars, or other fields to their shared Claude Code settings...
Cheat sheet for Claude Code Router configuration and installation.
Claude Code設定管理。settings.json、hooks、agents、skillsの確認・編集。トリガー: claude設定, hooks, settings, claude config, エージェント設定
Conventions for Claude Code configuration files (agents, commands, rules, skills). Use when creating, reviewing, or modi...
Consult Claude specialist agents during implementation for codebase understanding, pattern checking, security review, de...
Comprehensive cost tracking and optimization for production Claude deployments. Covers Admin API usage tracking, efficie...
将任意文本、网页或 URL 生成符合 Claude/Anthropic 设计语言的 HTML 信息卡片，通过 Playwright 截图为 PNG。 支持 14 种格式：平台封面（公众号、视频号、B站、抖音）、图文内容卡（小红书、教程、对比...
Use this skill when creating, optimizing, or maintaining claude hooks.
Hybrid Claude-Flow V3 integration architecture: hook execution order, system roles, background workers, production featu...
Orchestrate complex Intelliforia development tasks using Claude Flow V3 multi-agent swarms. Use when handling feature re...
Continuous learning — hooks observe failures and prompt reflection, sibling synergy deepens analysis with history and to...
Automatic history search — checks past sessions before web research, planning, and debugging, siblings deepen coverage
Self-reflect on the current session to identify mistakes and propose improvements to .claude configuration (CLAUDE.md, h...
Use when Claude Mail Bridge is installed (presence.json exists). Provides behavior guidelines for remote collaboration s...
Methodology for authoring and maintaining CLAUDE.md. Enforces brevity, relevance, and structure.
Audit and improve CLAUDE.md files. Use when rules aren't working, context is bloated, or after learning a lesson that sh...
Central CLAUDE.md file with project guidelines auto-injected into system prompt, achieving 10% accuracy lift in multi-ho...
Persistent memory compression system for Claude Code enabling context preservation across sessions with automatic observ...
Orchestrator-driven planning and execution workflow. Use when coordinating Claude memory-backed planning, make-plan/do f...
Entry-point skill for using claude-mem to keep CLAUDE.md and MEMORY.md in sync so Claude learns from past work and avoid...
Guide for writing and optimizing CLAUDE.md files for maximum Claude Code performance. Use when creating new CLAUDE.md, r...
將提示詞和程式碼從 Claude Sonnet 4.0、Sonnet 4.5 或 Opus 4.1 遷移至 Opus 4.5。當使用者想要更新其程式碼庫、提示詞或 API 呼叫以使用 Opus 4.5 時使用。處理模型字串更新和針對已知 O...
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update...
Comprehensive prompt engineering reference for Claude Opus 4.6. Use this skill whenever you are writing, reviewing, or o...
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
run parallel claude code writers, such as PR owners or dependency workers, as desktop sessions in their own worktrees, w...
Discover, message, and coordinate AI coding agents (Claude Code, Codex CLI) running on the same machine via a shared Uni...
Context preservation with cross-session memory — hooks prompt compaction at high-impact moments, siblings enrich what ge...