381,784 Collected SKILL.md files

Explore AI Agent Skills & Claude Prompts

Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.

search
expand_more
Active:
lazygophers
Showing 12 of 19 skills
lazygophers

flutter-ios

by lazygophers
star 4

Flutter iOS 平台规范 — Cupertino 设计、Impeller (iOS 默认)、ATT/隐私清单、Info.plist 权限描述、ProMotion 120Hz、App Store 审核合规。当用户开发 iOS/iPadOS 端、提到 "iOS"、"Cupertino"、"App Store"、"ATT"、"权限"、"Info.plist"、"TestFlight" 时加载。

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

csharp-data

by lazygophers
star 4

C# 数据访问与 ORM 规范。覆盖 EF Core 10 compiled queries、JSON columns、 complex types、bulk operations (ExecuteUpdate / ExecuteDelete)、SaveChanges interceptors、迁移策略、连接池、TestContainers 集成测试、Dapper micro-ORM 选型、 EF Core 10 Vector / Native AOT。当访问数据库、设计数据模型、调优查询性能、 写迁移脚本、配置 DbContext, 或说 "EF Core"、"Entity Framework"、"DbContext"、 "migration"、"Dapper"、"Npgsql"、"SqlServer"、"compiled query" 时加载。

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

cortex-video-understand

by lazygophers
star 4

视频理解 — 多 provider VLM 视频分析。两种模式 video_url (zhipu glm-4v-plus / qwen-vl-max-video 原生视频) 与 frames (ffmpeg 抽帧走 image VLM, 兼容 openai gpt-4o)。从 vault/.cortex/config/video-understand.yaml 选 provider。Triggers on "看视频", "视频理解", "video understanding", "总结视频", "视频问答", "video QA", "/cortex:video-understand".

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

cortex-image-understand

by lazygophers
star 4

图理解 — 调多 provider VLM (zhipu glm-4v / openai gpt-4o / qwen-vl) 完成图片描述、视觉问答、OCR、结构化抽取。从 vault/.cortex/config/image-understand.yaml 选 provider。Triggers on "看图", "识图", "图理解", "VQA", "vision", "describe image", "看看这张图", "图里写了什么", "提取图中文字", "OCR", "/cortex:understand".

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

rust-core

by lazygophers
star 4

Rust 核心开发规范 — Edition 2024 / Rust 1.85+、所有权三原则、Result/Option/? 错误处理、thiserror + anyhow、let-else、if-let-chains、async fn in traits、cargo / clippy / rustfmt / nextest 工具链。所有 Rust 编码、调试、测试、性能优化任务的前置基线规范,其他 rust 系列 skill 的共同前提。触发短语:写 Rust、Rust 项目结构、Cargo.toml、错误处理、clippy 报错、cargo lint、Rust 规范、Rust best practices、Rust 2024。

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

c-concurrency

by lazygophers
star 4

C concurrency conventions: C11 atomics with explicit memory orders, C11 threads.h and POSIX pthread (mutex, condvar, rwlock, barrier), cache-line alignment to kill false sharing, ThreadSanitizer for race detection, and async-signal-safe rules for signal handlers. Use when designing multi-threaded data structures, debugging races/deadlocks, picking a memory order, or reasoning about lock-free patterns. Triggers on "原子操作", "memory_order", "TSan", "data race", "死锁", "条件变量", "false sharing", "pthread_mutex", "atomic_compare_exchange".

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

c-core

by lazygophers
star 4

C language core conventions covering C11/C17/C23 standard features, coding style, build systems (CMake 3.30+, Meson), and static analysis (clang-tidy, cppcheck, scan-build). Use when writing, reviewing, refactoring, or debugging any C source. Also triggers on "C 标准", "C11", "C17", "C23 特性", "CMake C", "constexpr C", "nullptr C", "_BitInt", "#embed", "[[nodiscard]]", "clang-tidy 配置", "C 编译警告".

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

cortex-session

by lazygophers
star 4

导入 claude code / cli transcript → 记忆/L4-流水账/sessions/, 同步关键事件 append 到 ledger。Triggers on "import session", "导入会话", "归档会话", Stop hook 自动触发.

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

cortex-install

by lazygophers
star 4

初始化 vault — 双 namespace (知识库 + 记忆 L0-L4) + 仪表盘 + 归档 + 9 cron 注册。lang 询问 (zh-CN/en/ja)。触发: "init vault" / "安装 cortex" / "初始化 vault" / "cortex 装机"。

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

powershell-core

by lazygophers
star 4

PowerShell core conventions covering PowerShell 7.4 LTS (cross-platform pwsh) vs Windows PowerShell 5.1 (built-in legacy), Verb-Noun cmdlet naming with approved verbs, advanced functions ([CmdletBinding()] / param blocks / SupportsShouldProcess), pipeline semantics (ValueFromPipeline, process/begin/end blocks), strict mode (Set-StrictMode -Version 3.0), $ErrorActionPreference, $PSStyle ANSI formatting, ForEach-Object -Parallel, ConvertFrom-Json -AsHashtable. Use proactively when the user asks to "写 PowerShell 脚本 / pwsh 脚本 / Windows 自动化 / cmdlet 开发". Also triggers on "powershell", "pwsh", "ps1", "cmdlet", "advanced function", "Verb-Noun", "$PSStyle", "Set-StrictMode", "powershell 规范".

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

powershell-error

by lazygophers
star 4

PowerShell error handling: terminating vs non-terminating errors, $ErrorActionPreference levels (Continue/Stop/SilentlyContinue/Ignore/Inquire), -ErrorAction parameter scope, try/catch/finally with typed catches, ErrorRecord anatomy ($_.Exception/$_.CategoryInfo/$_.TargetObject), throw vs Write-Error, trap statement, $LASTEXITCODE for native commands, $PSNativeCommandUseErrorActionPreference (7.3+), $? boolean, exit codes, custom exception classes. Use proactively when the user asks "PowerShell 错误处理 / try-catch / ErrorAction / 退出码 / LASTEXITCODE / terminating error". Also triggers on "throw", "trap", "$Error", "ErrorRecord", "$ErrorActionPreference", "终止错误", "非终止错误".

navigation main article SKILL.md
schedule Updated 1 month ago
lazygophers

powershell-modules

by lazygophers
star 4

PowerShell module authoring and distribution: .psd1 manifest, .psm1 root module, function/cmdlet/variable/alias export rules, scope (Script/Private/Global), PSResourceGet (Install-PSResource) replacing the legacy PowerShellGet v2, PSGallery publish workflow, semantic versioning, module layout (Public/Private folders + dot-source loader), binary modules basics, RequiredModules and CompatiblePSEditions. Use proactively when the user asks to "写 PowerShell 模块 / ps 模块发布 / Publish-PSResource / psgallery / module manifest". Also triggers on "psd1", "psm1", "Export-ModuleMember", "PSResourceGet", "Install-PSResource", "PowerShellGet", "PSGallery".

navigation main article SKILL.md
schedule Updated 1 month ago
Page 1 of 2

Browse Agent Skills by Occupation

23 major groups · 867 SOC occupations

Browse by Category

Explore agent skills organized by their primary use case

SKILLMD / CREATORS AND OCCUPATION CATEGORIES

Explore the agent skills ecosystem by occupation and creator

SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.

Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.

Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.

01 Map a field

Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.

02 Follow creators

Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.

03 Search with sources

Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.

Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.

SEO KNOWLEDGE HUB & TECHNICAL OVERVIEW

Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)

In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.

Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.

The Structure of a Professional SKILL.md File

A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:

  • Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
  • Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
  • System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
  • Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
  • Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.

Optimizing Agent Workflows for Modern LLMs

Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.

Exploring by SOC Occupations and Creator Profiles

What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.

SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.

8 QUESTIONS

Frequently Asked Questions

A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.