83856 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

rubber-duck

|-

elasticdotventures
elasticdotventures
13

Python Type Hint Reviewer

Reviews code diffs (uncommited changes written by the agent) or new files(untracked files) for Python type hinting and structural principle compliance. Use this skill when user say review code diffs or new files or want to check code quality(when file is a python file). Requires explicit user confirmation before applying any modifications to ensure code quality and safety.

seedspirit
seedspirit
131

sub-package

微信小程序分包(subPackages)配置。需要将页面拆分到子包时使用

sail-sail
sail-sail
135

unocss

UnoCSS instant atomic CSS engine, superset of Tailwind CSS. Use when configuring UnoCSS, writing utility rules, shortcuts, or working with presets like Wind, Icons, Attributify.

Anthony Fu
Anthony Fu
135

ui-style

页面开发样式规范。开发 UI 界面时使用

sail-sail
sail-sail
135

pc-graphql-frontend

前端自定义 GraphQL API 接口. 当需要在前端调用后端自定义接口(非标准 CRUD)时使用

sail-sail
sail-sail
135

websocket

WebSocket 使用规范. 需要在前端订阅后端事件通知时使用

sail-sail
sail-sail
135

deno-graphql-backend

Deno GraphQL 后端接口的完整开发指南. 当需要创建、修改后端 API 接口时使用

sail-sail
sail-sail
135

tm-ui-components

tm-ui 组件 API 与源码定位。仅在需要核对某个 tm 组件的 props、events、slots、ref 方法或源码路径时使用;不要用于通用页面开发、样式规范或业务逻辑问题

sail-sail
sail-sail
135

sql-exec

仅在代码已写完、需要查库验证数据写入结果时使用。不要用于探索数据库结构或代替阅读代码

sail-sail
sail-sail
135

officecli

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

sail-sail
sail-sail
135

dict

系统字典和业务字典配置。SQL 中有 dict: 或 dictbiz: 标注的字段时使用

sail-sail
sail-sail
135

create-table

数据库建表规范。创建新表 SQL 时必须遵循;SQL 建完后必须继续阅读 table-config skill 来生成 {mod}.ts 配置

sail-sail
sail-sail
135

create-module

创建新业务模块时使用

sail-sail
sail-sail
135

table-config

表字段配置规范。生成或修改 {mod}.ts 时必须读取,尤其要检查 lbl、*_id_lbl/modelLabel、审计字段等容易漏掉的配置

sail-sail
sail-sail
135

uni-spec

移动端页面开发规范。开发 UI 界面时使用

sail-sail
sail-sail
135

uni-graphql-frontend

uni 前端自定义 GraphQL API 接口。需要在 uni 页面调用后端自定义接口时使用

sail-sail
sail-sail
135

stm32-freertos-developer

STM32 + FreeRTOS 嵌入式开发专家。支持 Cortex-M 全系列,原生 FreeRTOS v10+ 和 CMSIS-RTOS v2 API。用于创建任务/队列/信号量、集成标准库 + HAL 外设、内存优化、低功耗 Tickless 模式、STM32CubeMX 配置、调试分析(SEGGER SystemView / Percep TRACEalyzer)。

2939387245
2939387245
131

pyrevit-revit-2024

Revit 2024 API guidance for pyRevit development. Use when implementing or reviewing pyRevit commands that target Autodesk Revit 2024, including transaction patterns, API constraints, and version-specific best practices.

OriAshkenazi
OriAshkenazi
13

pyrevit-revit-2023

Revit 2023 API guidance for pyRevit development. Use when implementing or reviewing pyRevit commands that target Autodesk Revit 2023, including transaction patterns, API constraints, and version-specific best practices.

OriAshkenazi
OriAshkenazi
13

pyrevit-revit-2025

Revit 2025 API guidance for pyRevit development. Use when implementing or reviewing pyRevit commands that target Autodesk Revit 2025, including transaction patterns, API constraints, and version-specific best practices.

OriAshkenazi
OriAshkenazi
13

select-svg-icon

Choose and validate SVG icons for pyRevit extension commands. Use when creating or updating a pyRevit pushbutton and you need an SVG-only icon workflow with automated acquisition from svgrepo.com first, manual fallback on svgfind.com, and vision-based semantic ranking before finalizing icon assets.

OriAshkenazi
OriAshkenazi
13

develop-pyrevit-extensions

Build, plan, review, and document pyRevit extensions. Use when Codex needs the pyRevit development workflow, templates, prompts, checklists, or scripts for creating or updating pyRevit commands in this repo. Pair with a version-specific Revit skill (e.g., 2023/2024/2025) for API constraints.

OriAshkenazi
OriAshkenazi
13

doc-writing

Documentation writing patterns for Beluga AI v2. Use when creating package docs, tutorials, API guides, or teaching-oriented content.

lookatitude
lookatitude
131

go-interfaces

Go interface design with registry, middleware, and hooks for Beluga AI v2. Use when creating interfaces, extension contracts, or adding hooks/middleware.

lookatitude
lookatitude
131

streaming-patterns

Go 1.23 iter.Seq2 streaming patterns for Beluga AI v2. Use when implementing streaming, transforms, or backpressure.

lookatitude
lookatitude
131

provider-implementation

Implementing providers for Beluga AI v2 registries. Use when creating LLM, embedding, vectorstore, voice, or any other provider.

lookatitude
lookatitude
131

go-testing

Go testing patterns for Beluga AI v2. Use when writing tests, mocks, or benchmarks.

lookatitude
lookatitude
131

go-framework

Go framework design patterns for Beluga AI v2. Use when designing package structure, registries, lifecycle, or creating new packages.

lookatitude
lookatitude
131

git-state-validator

Check git repository status, detect conflicts, and validate branch state before operations. Use when verifying working directory cleanliness, checking for conflicts, or validating branch state.

edanstarfire
edanstarfire
131

custom-build-process

Project-specific build process for the Builder workflow. Builds frontend assets for claudecode_webui.

edanstarfire
edanstarfire
131

custom-cleanup-process

Project-specific cleanup process after issue completion. Stops test servers and cleans project-specific artifacts for claudecode_webui.

edanstarfire
edanstarfire
131

custom-environment-setup

Project-specific environment setup for issue workflows. Calculates test ports and provides initialization context for minions.

edanstarfire
edanstarfire
131

custom-quality-check

Project-specific code quality checks. Runs Ruff linting on modified Python files for claudecode_webui.

edanstarfire
edanstarfire
131

custom-test-process

Project-specific test process. Starts backend/vite servers, runs pytest, and verifies health endpoints for claudecode_webui.

edanstarfire
edanstarfire
131

ui-navigate

Navigate to the Claude Code WebUI application, verify it loads, and optionally select a project and/or session by name. Use when starting any UI test, opening the app, verifying the app is loaded, switching projects, or selecting sessions.

edanstarfire
edanstarfire
131

ui-permission-respond

Detect and respond to a permission prompt in the Claude Code WebUI. Use when approving or denying tool permissions, handling permission modals, responding to Claude asking for approval, or unblocking a paused session.

edanstarfire
edanstarfire
131

ui-project-create

Create a new project in the Claude Code WebUI via the UI. Use when creating a project, adding a project, opening the new project modal, or testing project creation flow.

edanstarfire
edanstarfire
131

ui-project-delete

Delete a project via the Claude Code WebUI. Use when deleting a project, removing a project, testing project deletion, or cleaning up test projects.

edanstarfire
edanstarfire
131

ui-send-message

Send a message in the active session of the Claude Code WebUI. Use when typing and sending a message to Claude, submitting a prompt, interacting with an active session, or waiting for the assistant to finish responding.

edanstarfire
edanstarfire
131

ui-session-create

Create a new session within the currently selected project in the Claude Code WebUI. Use when adding a new session, creating an agent, testing session creation, or setting up a new conversation.

edanstarfire
edanstarfire
131

ui-session-reset

Reset a session via the manage modal in the Claude Code WebUI. Use when resetting a session, clearing session history, restarting a Claude Code conversation, or waiting for session reconnect after reset.

edanstarfire
edanstarfire
131

ui-verify-snapshot

Take a snapshot of the Claude Code WebUI and verify expected content is present. Use when asserting UI state, checking that text or elements are visible, verifying a test condition, taking a screenshot for review, or reporting pass/fail on UI expectations.

edanstarfire
edanstarfire
131

codebase-explorer

Identify relevant files, understand architecture patterns, and find code by functionality. Use when you need to understand where specific functionality lives or find files related to a feature area.

edanstarfire
edanstarfire
131

git-branch-manager

Create, switch, and manage git branches with proper handling of uncommitted changes. Use when creating feature branches, switching contexts, or cleaning up after merges.

edanstarfire
edanstarfire
131

git-commit-composer

Create well-formatted semantic commit messages following project conventions. Use when committing changes to ensure consistent, descriptive commit history.

edanstarfire
edanstarfire
131

git-sync

Synchronize local default branch with remote, ensuring up-to-date base for worktrees.

edanstarfire
edanstarfire
131

github-authenticator

Verify and troubleshoot GitHub CLI authentication. Use when gh commands fail with auth errors or when setting up GitHub integration for the first time.

edanstarfire
edanstarfire
131

github-issue-creator

Create well-structured GitHub issues focused on user problems and outcomes, not implementation. Use when user reports bugs or requests features to ensure clear, testable requirements without premature implementation details.

edanstarfire
edanstarfire
131

github-issue-reader

Fetch and analyze GitHub issue details including comments, metadata, and discussion context. Use when user mentions issue numbers, URLs, or you need to understand implementation requirements from a GitHub issue.

edanstarfire
edanstarfire
131

Page 1051 of 1678 · 83856 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.