Prompts
Prompt engineering and templates
flipswitch-status
by flipswitch-io
Shows an overview of all feature flags with on/off status per environment, targeting rules, and rollout indicators. Use when checking the current state of feature flags or when the user asks about flag status across environments.
omcc-workflow
by Lynricsy
OMCC (Coder-Reviewer-Advisor) collaboration for code and document tasks. Use when: writing/modifying code, editing documents, implementing features, fixing bugs, refactoring, or code review. 协调 Coder 执行代码/文档改动，Reviewer 审核代码质量。
product-self-knowledge
by unicorn-plugins
Anthropic 제품 지식 — Claude Code, Claude API, Claude.ai 관련 정확한 정보 제공
skill-design
by teslasoft-de
Design new agent skills using the 10-step Skill Design Loop (SDL). Use when creating reusable, portable agent capabilities with progressive disclosure, VOI-driven uncertainty management, and security hardening.
init-project
by kdkyum
Initialize a new research project with standard directory structure, CLAUDE.md, pyproject.toml, and skills. Use at the start of any new notebook-based research project. Run from within the project folder — the folder name becomes the project name.
non-stop
by WebSmartTeam
Work autonomously until task is complete with self-correction loop. No questions asked - makes decisions based on evidence (console errors, screenshots, test results). Use when you want continuous uninterrupted work. Can be combined with ultraplan phases - "Create Phase 2 in non-stop mode". Triggers: non-stop, don't stop, work until done, autonomous mode, keep going, work autonomously, no questions.
agent-md-refactor
by cachemoney
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
note-writer
by khw1031
Obsidian 호환 학습 노트를 Skill 형식으로 작성합니다. 레퍼런스, 키워드, 개념 정리, 노트 작성, 지식 정리 요청 시 사용. 텍스트, URL, 이미지, 영상 등 다양한 입력 지원.
google-stitch-ai
by dmonteroh
"Create DESIGN.md summaries from Google Stitch projects or offline assets for UI design workflows, and refine Stitch-ready UI prompts using extracted design tokens."
coder-workspace-management
by jovermier
Coder CLI commands for workspace management, templates, and platform operations
improving-prompts
by cachemoney
Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files for Claude 4.5 models - applies documented Anthropic best practices systematically instead of inventing improvements
backend-ai-agent
by Workshop-Ventures
Create AI agents using Vercel AI SDK with tool use, tracing, and failover. Use when asked to "create an AI agent", "add AI", "create LLM integration", or "build an assistant".
product-marketing-context
by fefogarcia
"When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Creates .claude/product-marketing-context.md that other marketing skills reference."
codex
by cachemoney
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.
stream-clipper
by ET06731
直播切片智能剪辑工具。核心原则：切片前必须提取字幕！支持两种工作模式： 1)直播录播：实时录制直播间，每30分钟自动分段防止硬盘溢出，同时录制弹幕； 2)录播切片：下载直播回放（支持B站/YouTube等），必须提取字幕+弹幕，基于 字幕内容和弹幕密度进行智能切片，支持主播风格模板，自动生成基于实际对话 的切片标题（制造悬念、引用金句）和简介，一键上传到视频平台。 使用场景：直播录制、直播切片制作、VTuber剪辑、精彩片段提取、批量切片上传。 关键词：直播切片、字幕提取、弹幕分析、VTuber、智能剪辑、自动上传
gemini-computer-use
by sarfraznawaz2005
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
cc-dev-agents
by choru-k
This skill should be used when the user asks to "create a subagent", "add a subagent", "write a subagent", "subagent frontmatter", "permissionMode", "subagent memory", "subagent hooks", "/agents command", "agent frontmatter", "when to use description", "agent examples", "agent tools", "autonomous agent", or needs guidance on subagent structure, system prompts, triggering conditions, storage scopes, or subagent development best practices for Claude Code.
tool-selection-framework
by NaveedTechLab
Design systematic decision frameworks for selecting appropriate AI tools (Claude Code vs Gemini CLI) based on context requirements, codebase size, reasoning depth needs, and task complexity. Use this skill when starting projects with unclear tool requirements, optimizing context-constrained workflows, or designing multi-phase strategies that leverage multiple tools' strengths. This skill helps match tool capabilities to task characteristics, preventing wasted context and ensuring optimal resource allocation.
ai-agent-basics
by pluginagentmarketplace
Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design
integrating-mcp
by Git-Fg
"Provides comprehensive MCP integration guidance for Claude Code plugins. MUST Use when integrating databases via MCP, setting up MCP servers, or configuring connections. Do not use for API integration, web services, or general database access."
claude-code-mcp-manual-install
by shimo4228
"Use when adding MCP servers from within a Claude Code session where CLI is unavailable. jq-based ~/.claude.json editing workaround."
skill-creator
by brettatoms
Create or update Claude skills. Use when user wants to create a new skill, update an existing skill, or asks about skill structure. Handles both user-level skills (portable across projects) and project-level skills (repository-specific).
pageindex-rag
by mmtmr
Build reasoning-based RAG systems using PageIndex architecture. Replaces vector databases with hierarchical table-of-contents indices and LLM-driven navigation. Use when (1) implementing RAG for long structured documents (financial reports, legal contracts, technical manuals), (2) improving existing vector-based RAG systems with poor accuracy on structured content, (3) designing document indexing strategies with semantic coherence, (4) explaining PageIndex concepts including reasoning-based retrieval, hierarchical navigation, and cross-reference following, or (5) handling documents with internal references and multi-turn conversations. Focuses on technical architecture, core research insights, and practical implementation patterns rather than using the PageIndex package directly.
ai-sdk-6-skill
by francostan
Expert guide for Vercel AI SDK 6 - ToolLoopAgent, safety patterns, MCP, RAG, DevTools.