GITHUB AGENT SKILLS / 技能收录

给你的 AI 助手
装上专业技能

我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

github
github/gh-aw

error-recovery-patterns

Design gh-aw error handling, retry, recovery, and debugging flows.

开发工程师
★ 5.6k
github
github/gh-aw

error-pattern-safety

Apply safe error-pattern matching rules for agentic engines.

★ 5.6k
github
github/gh-aw

error-messages

Write consistent, actionable validation error messages in gh-aw.

★ 5.6k
github
github/gh-aw

documentation

Write concise Diataxis docs for gh-aw with Starlight markdown conventions.

★ 5.6k
github
github/gh-aw

docs-design

Design rules for the docs site and landing page (docs/). Use before any visual change there — layout, widths, spacing, colour, typography, header navigation, or new page chrome.

设计师视觉设计
★ 5.6k
github
github/gh-aw

developer-security

Security best practices for gh-aw workflows and Go code: template injection prevention, shell script security, supply chain hardening, and static analysis integration.

开发工程师
★ 5.6k
github
github/gh-aw

developer-release

Release management, changeset workflow, firewall log parsing, breaking CLI change rules, and Go module summaries for gh-aw.

开发工程师
★ 5.6k
github
github/gh-aw

developer-internals

Internal gh-aw architecture: validation, pure session graders, safe output messages, schema validation, YAML compatibility, and MCP logs guardrail.

开发工程师Skill与智能体开发
★ 5.6k
github
github/gh-aw

developer-code-organization

Code organization patterns, file structure guidelines, WASM build variants, and string processing conventions for gh-aw Go code.

开发工程师
★ 5.6k
github
github/gh-aw

debugging-workflows

Diagnose gh-aw failures using the canonical debugging strategy and evidence reference.

★ 5.6k
github
github/gh-aw

custom-engine-implementation

Add and test declarative behavior-defined agentic engines in gh-aw, extending Go infrastructure only when necessary.

★ 5.6k
github
github/gh-aw

custom-agents

Define and validate GitHub custom agent files, prompts, and examples.

Skill与智能体开发
★ 5.6k
github
github/gh-aw

create-canvas

Author, validate, and debug canvas extensions that the agent can open in the GitHub Copilot app's side panel. Use when creating, reviewing, or troubleshooting a canvas extension — including its actions, inputs, rendered content, and the surrounding extension wiring (tools, hooks, lifecycle).

开发工程师视觉设计Skill与智能体开发
★ 5.6k
github
github/gh-aw

copilot-review

Teach Copilot how to plan, address, and respond to pull request review feedback.

★ 5.6k
github
github/gh-aw

console-rendering

Use Go struct tags to render styled terminal output in gh-aw.

★ 5.6k
github
github/gh-aw

checkout-credential-review

Review code that performs git or gh operations against repository checkouts in gh-aw, checking that the right credentials are available at the right time and that sparseness, shallowness and credential-free factors are properly considered.

★ 5.6k
github
github/gh-aw

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

测试与质量
★ 5.6k
NVIDIA
NVIDIA/Model-Optimizer

modelopt-speculative-decoding

Train, debug, and validate a speculative decoding draft model (EAGLE3, DFlash, DSpark, Domino) through the ModelOpt launcher pipeline. Use when the user wants to add a new model to a draft-training pipeline, asks why a pipeline run failed, wants experiment logs reviewed, or wants to check whether a run's acceptance rate meets threshold. Triggers on "EAGLE3", "DFlash", "DSpark", "Domino", "draft model", "acceptance rate", "speculative decoding pipeline". Do NOT use for quantizing a model (use modelopt-ptq) or serving a checkpoint (use modelopt-deployment).

★ 5.6k