复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
Powered by Awesome Copilot GitHub contributors from allcontributors.org
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
来源文件:README.md
A community-created collection of custom agents, instructions, skills, hooks, workflows, and plugins to supercharge your GitHub Copilot experience.
[!TIP] Explore the full collection on the website → awesome-copilot.github.com
The website offers full-text search and filtering across hundreds of resources, plus the Learning Hub for guides and tutorials.
Using this collection in an AI agent? A machine-readable
llms.txtis available with structured listings of all agents, instructions, and skills.
New to GitHub Copilot customization? The Learning Hub on the website offers curated articles, walkthroughs, and reference material — covering everything from core concepts like agents, skills, and instructions to hands-on guides for hooks, agentic workflows, MCP servers, and the Copilot coding agent.
| Resource | Description | Browse |
|---|---|---|
| 🤖 Agents | Specialized Copilot agents that integrate with MCP servers | All agents → |
| 📋 Instructions | Coding standards applied automatically by file pattern | All instructions → |
| 🎯 Skills | Self-contained folders with instructions and bundled assets | All skills → |
| 🔌 Plugins | Curated bundles of agents and skills for specific workflows | All plugins → |
| 🍳 Cookbook | Copy-paste-ready recipes for working with Copilot APIs | — |
For most users, the Awesome Copilot marketplace is already registered in the Copilot CLI/VS Code, so you can install a plugin directly:
copilot plugin install <plugin-name>@awesome-copilot
If you are using an older Copilot CLI version or a custom setup and see an error that the marketplace is unknown, register it once and then install:
copilot plugin marketplace add github/awesome-copilot
copilot plugin install <plugin-name>@awesome-copilot
See CONTRIBUTING.md · AGENTS.md for AI agent guidance · Security · Code of Conduct
The customizations here are sourced from third-party developers. Please inspect any agent and its documentation before installing.
Thanks goes to these wonderful people (emoji key):
This project follows the all-contributors specification. Contributions of any kind welcome!
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.
name: bench-read
description: 'Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.'Read artifacts from the shared workspace (the bench) where desks leave work products for each other.
The bench is <workshop>/bench/ — the shared workspace directory
that workshop-create establishes for cross-desk work. It's not a
message queue or a chat channel — it's files. When Desk A produces
a finding and Desk B needs to review it, the finding is a file
in bench/. When the operator asks "what did the scanning desk
find?" — you read the bench.
Typical bench artifacts:
The primary shared location is the bench/ directory at the
workshop root — the designated cross-desk workspace. Desk-local
artifacts under desks/<desk-name>/ are a secondary source: read
them when you need a specific desk's own work, but shared artifacts
belong in bench/.
<workshop>/
bench/ # PRIMARY — shared cross-desk artifacts
<findings, verdicts, drafts, reports>
desks/<desk-name>/ # secondary — a desk's own workspace
journal.md # the desk's memory
<artifacts> # work still local to this desk
List what's there. Start with the directory structure to see what desks exist and what they've produced.
Read journals first. Each desk's journal tells you what it worked on and where it left things. The most recent entry is the current state.
Read artifacts second. Once you know what to look for from the journals, read the specific files.
Summarize for the operator. Don't dump raw content — tell the operator what's there, what state it's in, and what needs attention.
When one desk needs another desk's output:
评论 (0)
暂无评论,成为第一个评论者吧!