提示词
提示词工程与模板
deep-research
Soul-Brews-Studio
Deep Research via Gemini. Use when user says "deep research", "research this topic", or needs comprehensive analysis with sources.
gemini
Soul-Brews-Studio
Control Gemini via MQTT WebSocket. Use when user says "gemini", needs to send messages to Gemini, or control the Gemini browser tab.
Qt GUI Testing
talmolab
A deep learning framework for multi-animal pose tracking.
quality-gates
yonatangross
Use when assessing task complexity, before starting complex tasks, when stuck after multiple attempts, or reviewing code against best practices. Provides quality-gates scoring (1-5), escalation workflows, and pattern library management.
anthropic-claude-development
Mindrally
Expert guidance for Anthropic Claude API development including Messages API, tool use, prompt engineering, and building production applications with Claude models.
claude-in-mobile
AlexGladkov
"This skill should be used when the user asks to interact with device screens (screenshot, annotate, tap, swipe, type text), manage apps (install, launch, stop, uninstall), transfer files (push, pull), query device info (logs, system info, clipboard, screen size), run shell commands, manage desktop windows, or automate Android, iOS, Aurora OS, or Desktop apps."
elevenlabs-agents
jezweb
Build conversational AI voice agents with ElevenLabs Platform. Workflow: configure agent, add tools and knowledge base, integrate SDK, test, deploy. Supports React, React Native, and Swift SDKs. Use when building voice agents, AI phone systems, or troubleshooting @11labs deprecated packages, webhook errors, CSP violations, localhost allowlist, or tool parsing errors.
context-manager
jezweb
"Audit and manage the full project context landscape: CLAUDE.md memory hierarchy, project documentation, markdown footprint, and content overlap. Detects project type, scores quality, flags stale docs, and reports total context cost. Trigger with 'audit context', 'audit memory', 'update CLAUDE.md', 'restructure memory', 'session capture', 'check project docs', 'markdown footprint', or 'what docs does this project need'."
skill-creator
jezweb
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.
claude-capabilities
jezweb
Current Claude AI and Claude Code capabilities, features, and limits. Consult before making claims about what Claude can or cannot do, what features exist, model availability, pricing, or environment differences. Use when answering "can Claude do X?", comparing Claude AI vs Code, checking current model specs, or advising on which environment suits a task.
claude-capabilities
jezweb
Current Claude AI and Claude Code capabilities, features, and limits. Consult before making claims about what Claude can or cannot do, what features exist, model availability, pricing, or environment differences. Use when answering "can Claude do X?", comparing Claude AI vs Code, checking current model specs, or advising on which environment suits a task.
humanizer-zh
op7418
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
plan-maestro
ReinaMacCredy
"Universal interview-driven planning for Claude Code, Codex, and Amp Code. Uses subagents only -- no Agent Teams required."
design
ReinaMacCredy
"Start interview-driven planning with Prometheus. Asks clarifying questions before generating implementation plan."
project-conventions
ReinaMacCredy
Discovers host project conventions from CLAUDE.md, package.json, linter configs, and other configuration files. Use when agents need to understand the target project's coding standards.
temp-files
llama-farm
Guidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository.
generate-subsystem-skills
llama-farm
Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.
reflect
llama-farm
Analyze the current session and propose improvements to skills. Proactively invoke this skill when you notice user corrections after skill usage, or at the end of skill-heavy sessions. Also use when user says "reflect", "improve skill", or "learn from this".
Lobster
EthanAlgoX
One-off tasks that won't be repeated
jimeng_mcp_skill
wwwzhouhui
使用jimeng-mcp-server进行AI图像和视频生成。当用户请求从文本生成图像、合成多张图片、从文本描述创建视频或为静态图像添加动画时使用此技能。支持四大核心能力：文生图、图像合成、文生视频、图生视频。需要jimeng-mcp-server在本地运行或通过SSE/HTTP访问。
writing-assistant
yunshu0909
写作助手 - 当用户说"我想写XX"、"帮我梳理选题"、"怎么形成框架"、"给我组织思路"时触发。根据观点清晰度自动选择最优路线：清晰观点走"框架→内容"，模糊观点走"挖掘→选题→框架→内容"。
dev
atopile
"LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags."
memory-management
aaron-he-zhu
'Use when the user asks to "remember project context", "save SEO data", "track campaign progress", "store keyword data", "manage project memory", "remember this for next time", "save my keyword data", or "keep track of this campaign". Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with intelligent promotion/demotion.'
heygen
heygen-com
HeyGen AI video creation API. Use when: (1) Using Video Agent for one-shot prompt-to-video generation, (2) Generating AI avatar videos with /v2/video/generate, (3) Working with HeyGen avatars, voices, backgrounds, or captions, (4) Creating transparent WebM videos for compositing, (5) Polling video status or handling webhooks, (6) Integrating HeyGen with Remotion for programmatic video, (7) Translating or dubbing existing videos, (8) Generating standalone TTS audio with the Starfish model via /v1/audio.