提示词
提示词工程与模板
ai-ml
boisenoise
"AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features."
langchain
svngoku
Build AI agents with LangChain framework. Use when building agents, tools, memory, MCP integrations, RAG pipelines, multi-agent systems, or any LLM-powered applications using LangChain or LangGraph in Python or TypeScript.
git-operator
masanao-ohba
Manages Git operations including commits with appropriate conventions, combining related changes logically and following project-specific policies
skill-creator
ThomasRohde
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
ios-dev
AlphaSquadTech
iOS development workflow for building, running, testing, debugging, and fixing iOS apps using Xcode, Simulator, screenshots, and Maestro UI automation. Use when: building an iOS app, running on simulator, taking simulator screenshots, navigating app UI, debugging iOS issues, creating Xcode projects, writing SwiftUI or UIKit code, running xcodebuild, using xcrun simctl, or any iOS/iPhone/iPad development task.
code-review-uncommitted
nangongwentian-fe
对 git 中未提交的代码变更进行多维度 code review，包括项目规范合规性、Bug 扫描、代码注释合规性、组件封装/架构设计合理性审查，并通过置信度评分过滤误报。当用户要求 review 未提交的代码、review 当前改动、或使用 /code-review-uncommitted 时触发。
claude-workspace-trust-fix
i9wa4
Fix for Claude Code PreToolUse hooks being silently skipped in interactive mode. Sets hasTrustDialogAccepted: true for all project entries in ~/.claude/.claude.json. Use when: - PreToolUse hooks are not firing in interactive mode - Hooks work in -p mode but not interactive - User says "fix workspace trust" or "hooks not working" - Setting up Claude Code on a new machine - After adding new projects to Claude Code
claude-command-notion-find
monkey1sai
Converted from Claude plugin command "find" (Notion). Use when the user
claude-config-optimizer
i9wa4
Claude Code config optimization skill. Use when: - Editing CLAUDE.md, rules/, skills/, agents/, commands/ - User asks about config best practices - Checking optimization status - User says "claude code changelog" or "claude code updates" - User asks about new features or breaking changes in Claude Code
ai
telagod
AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。
rag-systems
pluginagentmarketplace
Retrieval Augmented Generation systems with vector search, document processing, and hybrid retrieval.
gemini-image-generator
stevenmays
Generate images using Google Gemini with customizable options
agent-frameworks
pluginagentmarketplace
AI agent development with LangChain, CrewAI, AutoGen, and tool integration patterns.
claude-command-firecrawl-setup
monkey1sai
Converted from Claude plugin command "setup" (firecrawl). Use when the
humanizer-zh
maximumtresh228
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。
copywriting
cyrwheelninja
Use when writing headlines, hooks, email copy, landing pages, ads, sales copy, social posts, or website copy. Also use when copy sounds generic, robotic, AI-like, doesn't convert, or needs to sound more human.
a2a-role-auditor
i9wa4
Role template auditor for tmux-a2a-postman multi-agent systems. Audits nodes/*.toml role definitions to fix node-to-node interaction breakdowns. Use when: - A node behaves unexpectedly (routes wrongly, ignores messages, approves nothing) - Nodes can't see each other in talks_to_line (after confirming PONG/session issue is ruled out) - Adding a new node and need to verify its template is complete and consistent - User wants to review or improve role definitions for any node Do NOT use for daemon-level failures (dead-letter from routing/edge misconfiguration); run triage first to determine if the issue is template-level.
agent-builder
mindmorass
Build specialized sub-agents for the workflow system
claude-agent-superpowers-code-reviewer
monkey1sai
'Converted from Claude plugin agent "code-reviewer" (superpowers). Use
podcast-production
mindmorass
Podcast production patterns and workflows. Use when recording podcasts, editing audio, transcribing episodes, generating show notes, RSS feed management, or podcast distribution.
ralph-loop
belumume
Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.
iot-homeassistant-best-practices
jasonraimondi
Home Assistant automation, helper, script, and device control best practices. Enforces native HA constructs over Jinja2 templates and safe refactoring workflows. TRIGGER WHEN: - Creating or editing HA automations, scripts, or scenes - Choosing between template sensors and built-in helpers - Writing triggers, conditions, waits, or selecting automation modes - Setting up Zigbee button/remote automations (ZHA or Zigbee2MQTT) - Renaming entities or migrating device_id to entity_id - Agent uses Jinja2 templates where native constructs exist - Agent uses device_id instead of entity_id - Agent picks wrong automation mode (e.g., single for motion lights)
continuous-learning
mhylle
Pattern extraction framework for learning from sessions. This skill captures valuable patterns discovered during work sessions including error resolutions, user corrections, workarounds, debugging techniques, and project-specific patterns. Triggers on Stop hook, end of session, "save learnings", "extract patterns", or when explicitly asked to capture knowledge from the current session. Outputs learned skills to ~/.claude/skills/learned/.
media-generation
vargHQ
Generate AI videos using varg SDK. Use for videos, animations, talking characters, slideshows, social content. JSX-based - describe scenes, render videos.