提示词
提示词工程与模板
xhs-cover-skill
cclank
Generates image generation prompts for Xiaohongshu covers based on user content. It polishes the content to fit Xiaohongshu style + applies a visual style template to produce a JSON output for image generation.
request-analyzer
smallnest
Proactively analyze user requests at the start of conversations to determine task type, assess prompt quality, and intelligently recommend which skills to activate. Should activate for ALL user requests to ensure optimal workflow. Evaluates clarity, specificity, and completeness to suggest prompt-optimizer when needed. Identifies UI design tasks for ui-analyzer and component requests for react-component-generator. Acts as intelligent skill coordinator.
prompt-optimizer
smallnest
Analyze and optimize user prompts for clarity, specificity, and completeness using interactive questionnaires or direct analysis. Use this skill when user requests are vague, ambiguous, incomplete, or lack necessary details. Supports two modes - Interactive Mode (uses AskUserQuestion tool for guided clarification) and Direct Analysis Mode (provides optimization suggestions). Triggers on prompts containing vague language like "something", "thing", "stuff", "it", or when requests lack context, technical specifications, success criteria, or examples. When user requests interactive/questionnaire mode, use AskUserQuestion to guide them through structured questions. Helps transform unclear requests into well-structured, actionable prompts.
markitdown
smallnest
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
template-skill
smallnest
Replace with description of the skill and when Claude should use it.
skill-porter
jduncan-rva
Converts Claude Code skills to Gemini CLI extensions and vice versa. Use when the user wants to make a skill cross-platform compatible, port a skill between platforms, or create a universal extension that works on both Claude Code and Gemini CLI.
skill-creator
smallnest
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
doc-sync-tool
littleben
自动同步项目中的 Agents.md、claude.md 和 gemini.md 文件，保持内容一致性。支持自动监听和手动触发。
claude-code-slash-commands
emdashcodes
This skill should be used when creating, configuring, or working with Claude Code slash commands. Use when users ask to create custom slash commands, set up command features like arguments or bash execution, or need guidance on slash command structure and best practices.
claude-code-hooks
emdashcodes
Claude Code hooks configuration patterns, event types, validation scripts, and decision control for automating workflows and integrating external tools. This skill should be used when creating hooks, validating tool usage, automating workflows, or integrating external tools with Claude Code.
claude-code-skills
emdashcodes
Guide for creating effective Agent Skills in Claude Code. This skill should be used when users want to create a new Skill (or update an existing Skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when working specifically with Claude Code's Skills system.
claude-code-mcp
emdashcodes
This skill should be used when configuring, installing, or managing MCP (Model Context Protocol) servers in Claude Code. Use when users need to connect Claude Code to external tools, databases, APIs, or services through MCP integration.
claude-code-subagents
emdashcodes
This skill should be used when creating, configuring, or working with Claude Code subagents. Use when users ask to create custom subagents, set up subagent configurations, manage tool permissions, or need guidance on subagent architecture and best practices.
claude-code-plugins
emdashcodes
This skill should be used when creating, configuring, or distributing Claude Code plugins and marketplaces. Use when users ask about the plugin system architecture, how to package multiple components together, create marketplaces, or set up team-wide plugin distribution.
recipe-generator
cclank
自动生成高品质菜谱的技能。当用户需要创建详细的菜谱、烹饪教程、食谱配方时使用。输入菜品名称后，检索权威来源（米其林、舌尖上的中国等）的制作工艺，生成包含完整准备工作、详细制作步骤、注意事项和专业技巧的菜谱文档，并最终生成传统中式风格的菜谱海报生图提示词。
ai-engineer-expert
personamanagmentlayer
Expert-level AI implementation, deployment, LLM integration, and production AI systems
dinachi-assistant
raymond-UI
Unified Dinachi skill for fast component integration and plan-first generative UI guidance. Use when users ask to initialize/add Dinachi components, build concrete UI features quickly, map ambiguous product requirements to Dinachi recipes, or validate generated UI plans before implementation.
skill-creator
JayZeeDesign
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
template-skill
JayZeeDesign
Replace with description of the skill and when Claude should use it.
project-development
Svenja-dev
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.
gemini-image-gen
Svenja-dev
Image generation with Google Gemini API. Models: gemini-2.5-flash-image (fast) or gemini-3-pro-image-preview (quality). For social media graphics, marketing, infographics.
clarify-spec
Svenja-dev
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. Erkennungsmerkmale (EINES genuegt!): - Auftrag <25 Woerter - Keine konkreten Dateinamen/Pfade - Vage Verben: besser, optimieren, fixen, machen, aendern, verbessern, anpassen, erweitern, refactoren, aufraumen, ueberarbeiten - Unsichere Sprache: irgendwie, vielleicht, mal eben, schnell, einfach, bisschen, koennte, sollte - Fehlende Erfolgskriterien: Kein damit, sodass, weil, um zu - Relative Begriffe ohne Kontext: schneller, besser, schoener, einfacher Output ist STRUKTURIERTES JSON fuer prompt-architect Skill. Escape: mach einfach, keine Rueckfragen, entscheide selbst ueberspringt Klaerung.
Human Writing Skill
Svenja-dev
Hastewire: AI Detection Benchmark 2025 (hastewire.com/blog/ai-detection-benchmark-2025-top-accuracy-results)
safe-git-guard
Svenja-dev
Prevents destructive Git operations by requiring backup and confirmation. Blocks git reset --hard, git push --force on main, git clean -fd. Requires backup before git checkout, git reset, git rebase. Activate on any destructive git command.