В каталоге 182 820 навыков в 14 категориях.
需适配
Use when coordinating complex research tasks requiring literature synthesis, quantitative validation, or multi-source in...
Use when coordinating software development projects requiring multiple specialists (architect, developers, mathematician...
Analyze construction site photos to track progress, detect safety issues, and compare against BIM models using computer...
Implements hub-and-spoke lazy loading to minimize token usage in large skills. Use when building multi-module skills tha...
Pattern for creating skills with YAML frontmatter that enables progressive disclosure and token optimization. Use when b...
Manage route-agent project: check status, find next tasks, spawn parallel work. Use when starting work, checking progres...
Map, suggest and request the folder access a project needs: `map` (read-only report), `suggest` (draft `.pi/access.json`...
Generates a structured Project Brief — a comprehensive markdown document that extracts goals, architecture, knowledge fi...
Foundational rule — context, coexistence, Plan Mode, language, credentials.
Run this skill at the very start of any new conversation or agent session before writing a single line of code. It loads...
Maintains project context and progress tracking across Claude sessions. Use at session start to load context, on session...
NodeJS-Starter-V1 specific knowledge
Continue a project after PR merge or new session with full context loading
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fi...
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing b...
Create, verify, transfer, and resume compact project handoff packets for long-running Codex work. Use after a second obs...
Captures project-specific patterns and anti-patterns into the project's CLAUDE.md. Loaded by other skills (bug-killer, f...
Generate thin project-local .codex/skills from a scaffolded repo's actual harness artifacts. Use after scaffold or harne...
提供项目管理、任务跟踪、团队协调和项目交付能力。当需要管理项目、跟踪进度或协调团队时使用。
Analyze the current repository and create or refresh .claude/PROJECT.md to match the project. Use when PROJECT.md is mis...
Persist and recall project-specific context across sessions. Store architectural decisions, patterns, solutions, and lea...
Generate CLAUDE.md project memory files that transfer institutional knowledge, not obvious information. Use when setting...
Persist context across sessions using external memory files
Set up and maintain a structured project memory system in docs/project_notes/ that tracks bugs with solutions, architect...
계획된 변경사항과 관련된 프로젝트 메모리(경계, 규약, 규칙)를 확인하고 위반 여부를 검사
Coordinate multiple agents by routing tasks to appropriate specialists. EXCLUSIVE to project-manager agent.
Orchestrate multi-phase project implementation using background Claude agents for isolated development, review, and inte...
Project management and multi-agent orchestration for autonomous software development. Use when coordinating development...
AI project OS for autonomous loop, automated orchestration, and rule-driven execution.
CRITICAL: This orchestrator skill REQUIRES extended context settings:
Audit a project and recommend the highest-value skills to add or update.
Creates project-managed skills in .chalk/skills with safe naming, ownership metadata, and versioned frontmatter.
Teach promise vocabulary, fundamentals, and coordination diagnosis for promise-based systems. Do not use this skill for...
产品宣传片制作总控 skill pack。用于从产品说明、官网、应用截图或 GitHub 仓库制作 60-90 秒宣传视频，按阶段完成 brief、storyboard、素材、HyperFrames 剪辑、BGM 设计和交付。当用户要做宣传...
产品宣传片制作总控流程。串联 6 个 Skills，按阶段执行并暂停确认。从产品 URL 到带 BGM 成片 MP4 的全自动流水线。当用户提到"做个宣传片""promo""产品视频""项目介绍视频"时触发。
Find the requests you keep making to your AI assistant by scanning Claude Code transcripts and claude.ai exports, cluste...
Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiv...
Load and execute a prompt from the project's .claude/prompts/ directory
Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (us...
Orchestrator skill for the `prompt` skillset. Dispatches to member skills in a safe, predictable order. Separates intent...
Crafts optimized, copy-ready prompts for any AI tool — LLMs, coding agents, image generators, workflow tools. Extracts i...
Capture each prompt into Graphiti memory (episodes) for this repo/user.
Ingeniería de prompts para los Agentes de Ventas, Soporte y Business Forge.
Design and optimize prompts for large language models (LLMs) to achieve reliable, high-quality outputs across diverse ta...
> Prompt verimliliğini artırma ve token maliyeti düşürme metodolojisi.
Internal metacognitive skill for episodic memory retrieval cues — surfaces relevant workflows when needed
Annotates agent prompts with structural XML tags for comprehension, gap detection, and skill extraction. Use when analyz...
Analyzes and improves prompts using 31 frameworks across 7 intent categories. Use when a user wants to improve, rewrite,...
Comprehensive framework for analyzing, creating, and refining prompts for AI systems. Use when creating prompts for Clau...
Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patte...
Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Basiert auf: - Nate B....
Аудит промтов и инструкций: чёткость, полнота, безопасность, структура и соответствие схеме
Применяй при разработке, написании или ревью промптов для LLM — универсальный стандарт промпта
AI绘画与AI视频制作的提示词生成助手。支持文生图、图生图、文生视频、图生视频、首尾帧视频等多种生成模式的提示词构建。当用户需要生成AI绘画或视频提示词时使用，包括：人物设定、环境场景、发型设计、姿势摆拍、地理位置、镜头运镜、构图视角等参数...
当需求还只是"帮我写个东西""让 AI 做这个任务"这种一句话时使用。用至多 3–5 个高杠杆追问把它补成一份可交付的任务简报——目标、产物、受众、已有素材、约束、验收标准、不做什么、待确认假设，外加一段可直接粘贴的执行 prompt。简报...
Build effective prompts for Claude Code skills. Creates clear, specific, actionable prompts using engineering principles...
Guide users through creating high-quality GitHub Copilot prompts with proper structure, tools, and best practices.
Restructures LLM calls so stable prefixes cache: frozen system prompts, deterministic tool lists. Use when the task invo...
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Genera...
Compile the YAML artifact into PROMPT.md with deterministic structure. A final agent pass polishes for fluidity, concise...
Automated prompt generation from pattern library. Input asset specifications → output production-ready Gemini prompt wit...
Compress verbose prompts & context before LLM processing. This skill should be used when input exceeds 1500 tokens, cont...
Master the Arcanean Prompt Language - advanced prompt engineering using mythological frameworks, constraint architecture...
Techniques and templates for creating optimal prompts following Anthropic conventions
Create standardized context prompts for AI assistants in prompts/ directory. Two types: technology-stack (project config...
Baseline prompt-injection and data-protection guardrails for any agent. Treats fetched/third-party/document content as u...
Design, version, and improve prompts as testable behavior contracts with explicit instructions, trustworthy context boun...
Track prompt changes across git history and flag drift that affects output quality or safety. Trigger: /prompt-drift
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models....
设计、优化和测试AI模型提示词，使用系统化的提示工程技术，包括少样本学习、思维链和结构化输出。
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output...
专注大语言模型提示词设计与优化的专家，精通系统提示词架构、思维链设计、少样本学习策略、以及提示词效果评测和迭代方法论。
Design, iterate, test, and version prompts for LLMs — system prompts, few-shot examples, chain-of-thought, structured ou...
Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performan...
Skill para desenhar prompts reutilizaveis de texto, imagem e video com foco em clareza, controle, custo e reprodutibilid...
Expert prompt engineering for building AI agents via Claude, GPT, and Gemini APIs. Triggers when: writing or editing sys...
Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters ch...
World-class expert in prompt engineering, LLM fine-tuning, RAG systems, and AI/ML workflows. Use when crafting prompts,...
Expert in designing, optimizing, and evaluating prompts for Large Language Models. Specializes in Chain-of-Thought, ReAc...
Analyzes and rewrites prompts for better AI output, creates reusable prompt templates for marketing use cases (ad copy,...
Use this skill when crafting LLM prompts, implementing chain-of-thought reasoning, designing few-shot examples, building...
Comprehensive guide for LLM prompt engineering techniques and best practices. Prompt engineering is the art and science...
Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when b...
Prompt engineering knowledge base — technique taxonomy with decision tree, prompt template patterns and formatting conve...
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve...
Prompt engineering for Claude API, system prompts, context management, instruction design, depth levels, HTML generation...
Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interacti...
Prompt Engineering — Institutional capability and runbook for prompt-engineering.
Craft effective prompts that get the best results from language models.
通用提示词工程与提示词改写技能，用于设计、优化、评审、模板化与迭代 LLM 提示词；当任务涉及明确目标/约束/输出格式、角色与指令层级、few-shot 示例、结构化标签、链式分解、长上下文管理、评估与回归测试、跨模型迁移或提示词标准化时使...
Provides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-though...
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructi...
Use when writing or improving prompts for a language model. Covers instruction structure, examples, reasoning elicitatio...
Prompt design patterns — few-shot, chain-of-thought, structured output, injection defense. Use when crafting or refining...
Prompt engineering patterns for Claude including system prompts, few-shot examples, chain-of-thought, structured output,...
Prompt templates, few-shot examples, chain-of-thought, structured output, evals