Install skills in GitHub Copilot
GitHub Copilot looks for skills in .github/skills/, .claude/skills/ and .agents/skills/ in a project, and in ~/.copilot/skills/ and ~/.agents/skills/ for all your projects.
Skill pages will open on the Copilot & VS Code install steps.
Where GitHub Copilot looks for skills
- .github/skills/
- your-skill/
- SKILL.md
- your-skill/
- .claude/skills/
- .agents/skills/
- .copilot/skills/
- your-skill/
- SKILL.md
- your-skill/
- .agents/skills/
Source: docs.github.com (opens in a new tab), checked 26 Oct 2026.
Install a skill
- Copy the skill's folder, with its SKILL.md at the top, into
.github/skills/in your project, or into~/.copilot/skills/for all your projects. - Keep the folder named exactly as the name field in its SKILL.md, as the Agent Skills spec asks.
- Or use the Copilot & VS Code tab on any skill's page here: its commands copy that skill at the commit we checked.
Watch out for
- gh skill install (GitHub CLI 2.90 or later, in preview) installs a given tag or commit with name@version, or with --pin, which also stops gh skill update from changing it.
- GitHub says the folders each surface reads differ, so do not assume a personal skill reaches Copilot cloud agent.
- In a running Copilot CLI session, run /skills reload after adding a skill.
- GitHub warns that pre-approving shell or bash in allowed-tools lets a skill run terminal commands without asking.
Recently updated
Each opens on the Copilot & VS Code install steps.
gentle-ai-skill-registry
Gentleman-Programming/gentle-shell
Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.
- Instructions only
Pattern check: Nothing flagged59/QIMIT · 1.9k repo stars · Updated 6 Nov 2026
poteto-mode
michael-denyer/pstack-claude
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
- Changes agent settings
- Runs shell commands
- +3 more
Pattern check: Nothing flagged64/QIMIT · 4.1k repo stars · Updated 6 Nov 2026
scenario-playable-ads
scenario-labs/skills
Use when a mobile game's gameplay recording, screenshots or existing art and sound should become a playable ad: an HTML5 interactive ad or interactive end card for Meta, Google Ads App campaigns, AppLovin, Unity Ads, Mintegral, Moloco, Liftoff, TikTok Pangle or any MRAID network, with a hint hand, a CTA and a mute button, packaged per network and QA-tested in headless Chromium. Keywords: playable ad, HTML5 playable, MRAID, FbPlayableAd, ExitApi, end card, CTA, hypercasual ad.
- Runs shell commands
- Reaches the network
- +2 more
Pattern check: Nothing flagged72/QIMIT · 3.4k repo stars · Updated 6 Nov 2026
Where every other agent looks for skills
Skills and repo facts come from public GitHub repos. Data as of 6 Nov 2026.
QAI did not write these skills and is not affiliated with their authors unless a page says so. Logos and icons belong to their owners and are not a mark of approval. How we check