Prompts
Prompt engineering and templates
agent-md-refactor
by VisualxIntelligence
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
oatda-vision-analysis
by devcsde
Use when the user wants to analyze images using vision-capable AI models through OATDA's unified API. Supports OpenAI GPT-4o, Anthropic Claude, and Google Gemini vision models.
truth-shield
by BAS-More
"Fact-verification layer v3 — catches hallucinations using 10 verification tiers, self-consistency sampling, isolated-context verification (CoVe), package existence checking (DepScope), and multi-judge arbitration. Cross-checks claims against local files, stored knowledge, live docs, web search, multi-model cross-check, and external fact-checkers. Every contradiction is persisted so the same lie is never repeated. MANDATORY TRIGGERS: 'verify this', 'truth-check this', 'fact-check this', 'shield this', 'truth shield', 'truth-shield', 'is this true', 'check your work'. STRONG TRIGGERS: 'are you sure', 'really?', 'source?', 'prove it', 'how do you know', 'is that right', 'double-check that'. PASSIVE MODE: 'shield on' / 'shield off'. Do NOT trigger on opinions, creative writing, brainstorming, or subjective preferences."
prompt-caching
by anilsoylu
Guide for optimizing prompt caching in agentic AI applications. Use when building Claude agents, optimizing API costs, designing system prompts, managing tool definitions, implementing compaction, or troubleshooting cache miss rates. Triggers: "prompt caching", "cache hit rate", "reduce API costs", "system prompt ordering", "tool definitions caching", "compaction", "context window management", "agent cost optimization", "prefix caching", "cache-safe forking", "agentic loop cost", "token cost reduction", "cache miss debugging".
Init Project
by midhunxavier
Initialize paper projects with venue-specific templates (LaTeX or DOCX). Detects existing repositories and creates subfolders to keep project root clean.
create-agent-skills
by myuon
新しい Claude Code スキルを作成するためのガイド。スキルの作り方、SKILL.md の書き方、配置場所を案内する。
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。
Python Script Skill Template
by Wesley1600
[list required packages]
voice-realtime
by keenranger
Real-time voice AI knowledge including STT and TTS providers, LiveKit Agents plugins, and voice pipeline patterns. Use when working with speech-to-text, text-to-speech, voice agents, LiveKit, or any voice-related infrastructure.
release-management
by recoupable
Manage music releases using RELEASE.md documents stored in releases/{release-slug}/ within an artist workspace. Triggers when the user mentions an artist's album, EP, single, or project — or asks about release planning, DSP pitches, metadata, marketing, press materials, physical production, or tour coordination. First infer which artist and release the user means, then find or create the RELEASE.md. Use this skill to create, update, or pull data from release documents, and to generate deliverables like DSP pitches, press one-sheets, and production specs.
stats
by Saturate
Query Claude Code usage stats from observability logs. Shows costs, session summaries, tool usage, token consumption, and more. Use when asked about costs, usage, stats, spending, session history, most-used tools, or token usage. Invoked with /stats or when asking questions like "how much have I spent today?"
ai-research
by ParkJumyung
Systematic AI research process. Use when the user is AI researcher and the project is involved in AI research project.
codex-collaborator
by ShintaroaSuzuki
Collaborate with Codex CLI through iterative AI-to-AI discussion. Use whenever the user mentions "Codex" in any context—asking for Codex's opinion, consulting Codex, discussing with Codex, or any request involving Codex collaboration. Also triggers on phrases like "ask another AI", "get a second opinion from AI", or "AI-to-AI discussion".
zhin-prompt-interaction
by zhinjs
Guides interactive user input collection using the Zhin Prompt class. Covers text, number, confirm, list, and pick prompts with timeout handling and Schema-based input. Use when a plugin needs to collect input from users in a conversational flow.
load-template
by tkarakai
Load an AI agent instruction template into the current project. Use when you need structured instructions for a specific role like technical planning.
with-codex
by Seika139
Enables Claude Code to collaborate with OpenAI Codex CLI on Windows. Use this skill when the user wants to get a second opinion from Codex, compare approaches between Claude and Codex, or leverage both AI assistants for collaborative problem-solving. This skill supports both non-interactive mode (automatic response retrieval) and interactive mode (visual pane splitting with tmux).
safety-boundary-initialization
by evcgs
"Safety Boundary Initialization - A skill that triggers on first conversation to help user set up safety boundaries, authorization levels, and communication protocols."
AI Security Engineer
by anorbert-cmyk
AI Security Engineer focused on preventing prompt injection, data exfiltration, and model abuse in LLM-enabled products.
execa
by yusenthebot
Process execution for humans. Use when: Simple syntax: promises and template strings, like zx; Script interface; Execute locally installed binaries without npx. NOT for: database replacement; network storage without proper SDKs.
create-skill
by paulo20223
Create new skills for Claude Code. Use when users ask to create a skill, add a skill, make a new command, build a skill, add a slash command, create a plugin skill, or define a new automation. Trigger phrases include "create a skill", "new skill", "add a skill", "make a command", "build a skill", "I want a skill that", "add slash command", "create automation".
SKILL.md — MIKIの文体・投稿スキルガイド
by spikesukeshun
——（em dash）が使われていないか
conversation-logging
by ianphil
Global hooks for logging Claude Code conversation events to markdown files. Tracks prompts, tool usage, and responses across all sessions. Useful for debugging, auditing, and providing conversation context to Claude.
frontend
by Lynricsy
Frontend UI/UX Engineer for interface design and implementation. Use when: creating UI components, styling, animations, responsive design, or UI review. 前端/UI 专家，设计师型开发者，关注间距、色彩、微交互。
video-gen
by InfQuest
使用 AI 生成视频，支持 Veo/Sora 模型。Use when user wants to 生成视频, AI视频, 文生视频, 图生视频, generate video, create video, text to video, image to video, 做一个视频.