
Copilot Spaces Access
Load curated project context from GitHub Copilot Spaces and manage Spaces via the API
- Repository
- github/awesome-copilot
- Stars
- 40,703
- Licence
- MIT
- Files
- 1 file
What it does
This skill teaches an agent to find and load GitHub Copilot Spaces, which are shared collections of repositories, files, documentation and instructions maintained by a team. Once a Space is loaded, the agent answers questions and writes code using that team's own standards instead of generic knowledge. It can also create, update or delete Spaces and their collaborators through the GitHub REST API using the gh command line tool.
Great for
- Developers and teams that already keep project docs and standards in GitHub Copilot Spaces
- Engineers who want answers grounded in their organisation's architecture or policies
- Team leads who maintain Spaces and want to script updates to instructions or attached resources
Skip it if
- People without a GitHub account or access to Copilot Spaces, since the tools return nothing useful
- Anyone wanting to change Space data casually: write operations can overwrite instructions and replace the entire attached resource list, and deletion is permanent
- Use where the Spaces REST API is unavailable, because the skill notes it is not in the public API docs and may need a feature flag
Try asking
- “Load the Accessibility copilot space and summarise our compliance process”
- “What copilot spaces are available for our team?”
- “Using the security space, what is our policy on secret scanning?”
- “Write my weekly update using the PM Weekly Updates space”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
copilot-spaces.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip copilot-spaces.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip copilot-spaces.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Start by asking for the list of spaces so the agent uses exact owner and space names, which are case-sensitive.
- Grant the token only the scopes you need; add the user write scope only when you intend to change a Space, and review any update or delete command before the agent runs it.
- Ask the agent to show progress after each step when a Space contains a multi-step workflow so you can steer it.
What's inside
- SKILL.md
Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.