Prompts
Prompt engineering and templates
skill-writer
by metalagman
Use this skill to design, document, and structure AI agent skills for Gemini, Claude, and Codex. It provides architectural rules, directory standards, and writing best practices.
handoff
by petekp
Generate a smart bootstrap prompt to continue the current conversation in a fresh session. Use when (1) approaching context limits, (2) user says "handoff", "bootstrap", "continue later", "save session", or similar, (3) before closing a session with unfinished work, (4) user wants to resume in a different environment. Outputs a clipboard-ready prompt capturing essential context while minimizing tokens.
pangu-skill
by longjingcha
盘古造 Skill：输入人名/主题/模糊需求，自动深度调研→协议提炼→生成可运行的协议产物。 两种入口：(1)明确对象→直接处理 (2)模糊需求→诊断推荐→再处理。 触发词：「造skill」「盘古」「造人」「XX的思维方式」「做个XX协议」「更新XX的skill」。 模糊需求也触发：「我想提升决策质量」「有没有一种思维方式能帮我...」「我需要一个思维顾问」。
design-patterns
by Tyler-R-Kendrick
Gang of Four (GoF) design patterns — 23 proven object-oriented solutions organized into Creational, Structural, and Behavioral categories, drawn from Gamma, Helm, Johnson, and Vlissides. USE FOR: GoF design patterns, pattern selection, object-oriented design, creational/structural/behavioral patterns, composition over inheritance DO NOT USE FOR: enterprise messaging patterns (use dev/integration-patterns), architecture styles (use dev/architecture), algorithm selection (use dev/algorithms)
agent-skills
by Tyler-R-Kendrick
Use when creating, packaging, or distributing Agent Skills. Covers the SKILL.md specification, frontmatter schema, naming conventions, marketplace publishing, and the skills-ref validator. USE FOR: creating SKILL.md files, packaging reusable agent capabilities, marketplace publishing, frontmatter schema validation DO NOT USE FOR: project-level agent guidance (use agents-md), agent runtime configuration (use adl or cagent)
pydantic-ai-agents
by Fuenfgeld
"Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection."
pydantic-evals
by Fuenfgeld
"Test and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing. Use when the user wants to: (1) Create evaluation datasets with test cases for AI agents, (2) Define evaluators (deterministic, LLM-as-Judge, custom, or span-based), (3) Run evaluations and generate reports, (4) Compare model performance across experiments, (5) Integrate evaluations with Pydantic AI agents, (6) Set up observability with Logfire, (7) Generate test datasets using LLMs, (8) Implement regression testing for AI systems."
claude-code-config
by dongzhuoyao
Use when setting up Claude Code on a new machine, configuring permissions, statusline, or plugins. Contains the standard settings.json and statusline script.
helm
by Tyler-R-Kendrick
Use when creating or managing Helm charts for Kubernetes applications. Covers chart structure, values files, templates, Go template functions, dependencies, and release management. USE FOR: Helm charts, Kubernetes package management, Go templates, values files, chart dependencies, release management DO NOT USE FOR: raw Kubernetes manifests without templating (use kubernetes), cloud provisioning (use terraform or pulumi), container builds (use docker)
cloud-formation
by Tyler-R-Kendrick
Use when writing or managing AWS CloudFormation templates. Covers stack resources, parameters, outputs, intrinsic functions, nested stacks, and change sets. USE FOR: AWS stack provisioning, CloudFormation YAML/JSON templates, intrinsic functions, nested stacks, change sets DO NOT USE FOR: Azure infrastructure (use bicep or arm), multi-cloud infrastructure (use terraform or pulumi), Kubernetes resources (use kubernetes)
claude-dev-pack
by Peiiii
"Developer toolkit: build, test, deploy, and debug with curated skills."
claude-design-pack
by Peiiii
"Design toolkit: UI/UX, themes, brand guidelines, and generative art."
project-os
by Peiiii
AI project OS for autonomous loop, automated orchestration, and rule-driven execution.
claude-office-pack
by Peiiii
"Office toolkit: PDF/Word/PPT/Excel + internal comms."
claude-content-pack
by Peiiii
"Content toolkit: research, writing, summarization, and insights."
skill-builder
by metaskills
Use this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.
MCP Connector
by Sounder25
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Adversarial Reviewer
by Sounder25
Generates a 'Red Team' critique of recent code or plans to identify weak assumptions and edge cases.
ideaverse-enrichment
by mrfelton
Systematically add new knowledge to Ideaverse vaults while maintaining consistency. Use when assimilating new information, extracting concepts from sources, processing research, integrating learned knowledge, detecting duplicates, or classifying knowledge types. Triggers on requests like "add this to my vault", "process this article", "integrate this knowledge", "what type of knowledge is this", or "check for duplicates".
slidekit-templ
by nogataka
"Convert PDF presentations to HTML slide templates using a visual reproduction approach. Pipeline: PDF → slide screenshots → Claude writes HTML matching each screenshot. Use when the user wants to convert a PDF to HTML slide templates, reproduce a presentation as HTML, or create reusable templates from existing decks. Triggers: 'pdf to html', 'convert pdf to template', 'reproduce this deck as html', 'create template from pdf'."
meta-dialogue-v2
by gongebb
Advanced metacognitive dialogue skill with cross-session accumulation. Builds a meta-profile of hypotheses about your thinking patterns, detects when patterns break (more valuable than confirmation), and includes frame-health safeguards against self-negation and direction errors. Hypothesis-first approach — challenges before confirms. 세션 간 축적형 메타인지 대화 스킬. 가설 기반 메타 프로필을 누적하고, 패턴 깨짐을 감지하며, 자기부정/방향오류 안전장치를 포함합니다. 확인보다 도전을 먼저 하는 대화 방식.
meta-dialogue
by gongebb
A metacognitive dialogue skill for deep self-exploration. Helps structure scattered thoughts, discover personal patterns, and extract insights for writing. Uses hypothesis-driven questions (not just "why?") to uncover hidden values, growth directions, and blind spots. Ideal for self-reflection, journaling prompts, and article ideation. 메타인지 사고를 돕는 대화 스킬. 흩어진 생각을 구조화하고, 자기 이해를 심화하며, 글감이 될 인사이트를 발굴합니다. "내 생각 정리해줘", "나에 대해 알고 싶어", "아티클 쓰려고 해" 등의 요청 시 사용합니다.
zimage-skill
by yizhiyanhua-ai
Generate images using ModelScope Z-Image-Turbo API. Use when user asks to generate, create, or make images, pictures, or illustrations.
pj-init
by ssiumha
Initializes multi-repo workspace CLAUDE.md. Use when managing multiple repositories as a single project.