Prompts
Prompt engineering and templates
authoring-stitch-prompts
by joaquimscosta
Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Use when user says "create a Stitch prompt", "optimize this for Stitch", "convert this spec to a Stitch prompt", "write a UI prompt", or mentions Google Stitch prompt authoring. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.
prompt-engineering
by rfxlamia
Use when you need to design effective LLM prompts. Intelligently selects optimal prompting methods (Chain of Thought, Few-Shot, Zero-Shot, ReAct, Tree of Thoughts, Self-Consistency) and output formats (XML, JSON, YAML, Natural Language) based on task complexity, target LLM, accuracy requirements, and available context. Trigger on prompt design, prompt optimization, or when choosing between prompting techniques.
red-teaming
by rfxlamia
Comprehensive red teaming methodology for both cybersecurity and AI/LLM systems. Use when conducting adversary emulation, vulnerability assessment, attack simulation, or security validation. Trigger on requests for penetration testing, threat modeling, security audits, MITRE ATT&CK operations, LLM safety testing, prompt injection attacks, or compliance validation (OWASP, NIST, TIBER, DORA, EU AI Act). Apply when users ask to "test like an attacker", "red team our system", "validate security posture", "assess LLM vulnerabilities", or "simulate cyber attacks". Includes planning frameworks, execution strategies, reporting templates, and progressive references to specialized attack techniques and tools.
humanize
by rfxlamia
Transform AI-to-AI documentation into human-readable prose with personality. USE WHEN: Converting rigid AI-generated docs (checklists, templates, CAPS LOCK emphasis, perfect structures) into flowing, conversational documentation that feels like a colleague wrote it, not a robot. PRIMARY TRIGGERS: "humanize this doc" â Full transformation workflow "make this readable" â Quick readability pass "remove AI patterns" â Surgical pattern removal "add human touch" â Inject personality without losing precision INPUT: Markdown files with AI-agent patterns (checklist spam, rigid headers, template overload) OUTPUT: Flowing prose with burstiness, analogies, and occasional absurd touches CORE PRINCIPLE: Total war on AI rigidity. Destroy robotic tone while preserving technical accuracy.
ai-ml
by boisenoise
"AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features."
langchain
by 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
by masanao-ohba
Manages Git operations including commits with appropriate conventions, combining related changes logically and following project-specific policies
skill-creator
by 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
by 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
by 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
by 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
by monkey1sai
Converted from Claude plugin command "find" (Notion). Use when the user
claude-config-optimizer
by 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
by 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
by pluginagentmarketplace
Retrieval Augmented Generation systems with vector search, document processing, and hybrid retrieval.
gemini-image-generator
by stevenmays
Generate images using Google Gemini with customizable options
agent-frameworks
by pluginagentmarketplace
AI agent development with LangChain, CrewAI, AutoGen, and tool integration patterns.
claude-command-firecrawl-setup
by monkey1sai
Converted from Claude plugin command "setup" (firecrawl). Use when the
humanizer-zh
by 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
by 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
by 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
by mindmorass
Build specialized sub-agents for the workflow system
claude-agent-superpowers-code-reviewer
by monkey1sai
'Converted from Claude plugin agent "code-reviewer" (superpowers). Use
podcast-production
by mindmorass
Podcast production patterns and workflows. Use when recording podcasts, editing audio, transcribing episodes, generating show notes, RSS feed management, or podcast distribution.