Prompts
Prompt engineering and templates
cross-axis-analysis
by zcz-user
"Cross-Axis Analysis Framework. Use when you need to systematically research an unfamiliar domain, product, company, or technology concept through longitudinal timeline analysis +横向同期竞争格局对比。Also triggers on: '横纵分析', 'research framework', 'deep analysis report', '快速了解某个领域'."
alexandrescu-modern-cpp-design
by copyleftdev
Write C++ code following Andrei Alexandrescu's Modern C++ Design principles. Emphasizes policy-based design, template metaprogramming, and type-safe generic abstractions. Use when designing flexible, reusable libraries or when compile-time computation beats runtime overhead.
scaffold-skill
by maxoreric
系统初始化脚手架。用于在新项目中克隆和初始化 sop-engine 内核。
skill-creation
by totophe
"Guide for creating and structuring Agent Skills following the open standard specification (agentskills.io). Use when creating a new skill, updating an existing skill, packaging skills, writing SKILL.md files, or structuring skill directories with references, scripts, and assets."
update-claude-md
by carsten-j
You are updating this project's CLAUDE.md to reflect meta learnings (conventions, philosophy, gotchas) and significant recent changes to the codebase.
cx-config
by m19803261706
CX 工作流 — 配置管理。查看、修改 config.json 中的配置字段，如 developer_id、 github_sync 模式、代码审查开关、agent 团队模式、自动格式化等。 触发词：配置、config、设置、修改配置、改模式。 仅在用户明确调用 /cx-config 时执行。不要自动触发。
trinity
by frankyxhl
Multi-model orchestration skill. Dispatch tasks to any LLM provider via background sub-agents with auto-discovery, config overlay, session management, and health monitoring. Use when the user says /trinity or wants to delegate work to another model.
hello-world
by atovk
最简单的 Claude Code Skill 示例 - 向用户问好并展示基本结构
gemini-cli
by gswangg
Run Gemini CLI for interactive or non-interactive AI tasks, code generation, and agentic workflows
cursor-deeplinks
by janjaszczak
Generate Cursor deeplinks (prompt/command/rule and MCP install links) using the repo generator and the project output contract. Use when the user asks for a Cursor deeplink, cursor:// links, cursor.com/link links, or wants to create prompts/commands/rules via deeplinks.
sac
by SeaVerseAI
Use sac (SeaArt CLI) to generate images, video, audio, and 3D assets, chat with LLMs, inspect task results, or manage SeaArt API credentials and config.
infographic
by prabha-oss
Generate professional infographics using Nano Banana MCP (Gemini AI image generation). Follows a guided flow — analyze content, suggest visualizable concepts, propose visualization approaches, then generate on-brand images. USE THIS SKILL WHEN user says "create infographic", "make a visual", "design an infographic", "generate infographic", wants to visualize a concept, framework, or data for social media, mentions "LinkedIn post", "visual content", "infographic series", asks to explain a concept visually or create a diagram-style image, mentions "visual metaphor", "iceberg diagram", "pyramid", "funnel visualization", wants to generate images with Gemini for informational content, or says "brand visuals", "social media graphics", "thought leadership visual".
azure-devops
by yldgio
Azure DevOps pipeline security, YAML structure, variable management, and deployment patterns
agent-evaluation
by yunaamelia
"Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world ben..."
memento
by Chakibprojects
"Cognitive persistence system for session continuity. Syntax: /memento [action]. Actions: hydrate (restore context), checkpoint (save session), status (view state). Also triggers on intents like 'reprends le contexte', 'sauvegarde la session', 'où on en était'."
creating-agent-skills
by 8b-is
Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
dev:skill
by IKatsuba
Create New Skill - generates a new skill definition for this repository
setup
by Alexu0317-FATHER
"Cold-start initialization: generate Core Profile, Domain State, and Extract Buffer files, inject CLAUDE.md monitoring instructions. Run once per user, or to reset."
inspect-claude-source
by gswangg
Extract, prettify, and inspect Claude Code source from its Bun-compiled binary. Use when the user wants to understand Claude Code internals or find how a feature works.
your-skill-name
by lavderenterprise
"Clear description of when to use this skill. Include: specific triggers, use cases, and key features. This description is used by Claude to decide when to activate the skill."
SKILL.md — Web Research
by iamthetonyb
Never present speculation as fact
codex-delegation
by DUTSTECH
How to delegate implementation tasks to workers via Codex MCP or Task sub-agents. Use when executing tasks that require code implementation.
ogt-cli-claude
by OpenDNDApps
Run Claude Code CLI for complex tasks, code generation, analysis, and research. Uses Anthropic OAuth (included in Claude Pro). Use for extended thinking, code review, architecture decisions. Preferred for load balancing sub-agent work (35% weight).
migrate
by biruk741
Migrate AI documentation between formats. Converts .cursorrules to MDC, monolithic CLAUDE.md to modular rules, creates AGENTS.md from existing docs, and more. Use when adopting a new agent tool or upgrading doc format.