Skip to content
cccskills
FreePublished on GitHubEnglish overview

gh-skill

Manage Agent Skills through `gh skill`: search for skills, preview their contents, install them for a chosen agent, update installed copies, and publish a repository as a discoverable skill source.

OriginalShow the original description

Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.

cli/cli46,747 stars(GitHub 46,747 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Finding skills by topic
  • Checking a skill before installing it
  • Installing a pinned skill for an agent
  • Updating installed skills
  • Publishing a repository of skills

Overview

What it does

Use gh skill to search for Agent Skills on GitHub, inspect their contents, install them, and update installed copies. Choose the target agent and whether the skill is saved in the current project or for your user account. You can pin an installation to a tag, branch, or commit, or install from a local repository. For publication, the skill checks the repository layout and SKILL.md metadata, then guides you through making the repository discoverable as a skill source on GitHub.

When it helps

Use it when you want to find a skill on GitHub and review it before installing. It also helps when you use different skills in multiple agent environments, need to update installed skills together, or want to organize and prepare your own skills for publication.

Example requests

  • “Find skills for proofreading and show me what the candidates contain.”
  • “Install this skill for Codex, pinned to a specific version.”
  • “Check whether the skills in this repository are ready to publish.”

Notes

Choose the target agent when installing. Publishing involves actions on a GitHub repository, and the publish procedure uses a specified tag.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Document check

AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).

SafetyAre sending data, deleting files, and running commands disclosed?
BPartly lackingPublishing pushes commits and creates a release; confirmation safeguards are limited.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lacking`gh skill` and a target agent are assumed; their setup steps are absent.

Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 26, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Managing skills with gh skill

gh skill installs, previews, searches, updates, and publishes Agent Skills. An agent can use it to keep its own skill set in sync with one or more GitHub repositories.

The command is also aliased as gh skills. Prefer the canonical singular gh skill in scripts and docs.

Search

gh skill search <query>                                  # free-text search
gh skill search <query> --owner <org>                    # restrict to one owner
gh skill search <query> --limit 20 --page 2
gh skill search <query> --json skillName,repo,description

Preview before installing

gh skill preview <owner>/<repo> <skill-name>
gh skill preview <owner>/<repo> <skill-name>@v1.2.0   # pin a version

Install

gh skill install <owner>/<repo> <skill-name>
gh skill install <owner>/<repo> <skill-name>@v1.2.0
gh skill install <owner>/<repo> skills/<scope>/<skill-name>   # exact path, fastest
gh skill install ./local-skills-repo --from-local

<owner>/<repo> and <skill-name> are both required.

Useful flags:

  • --agent <id> - target host (e.g. github-copilot, claude-code, cursor, codex, gemini-cli). Repeat for multiple. Default is github-copilot when non-interactive. You should know what agent you are, so set this appropriately to install for yourself.
  • --scope project|user - project (default) writes inside the current git repo; user writes to the home directory and applies everywhere.
  • --pin <ref> - pin to a tag, branch, or commit SHA. Mutually exclusive with --from-local and with inline @version syntax.
  • --allow-hidden-dirs - also discover skills under dot-directories such as .claude/skills/. Don't use this unless you need to, it comes with risks.
  • --force - overwrite an existing install.

Update

gh skill update --all          # update every installed skill
gh skill update <skill>        # update one
gh skill update <skill> --force
gh skill update --unpin        # drop the pin and move to latest

Publish

Publishing turns a repo into a discoverable skill source. Skills are discovered with these conventions:

  • skills/<name>/SKILL.md
  • skills/<scope>/<name>/SKILL.md
  • <name>/SKILL.md (root-level)
  • plugins/<scope>/skills/<name>/SKILL.md

Each SKILL.md needs YAML frontmatter:

---
name: my-skill                # must equal the directory name
description: One sentence...  # required, recommended <= 1024 chars
license: MIT                  # optional but recommended
---

Validate, then publish

gh skill publish --dry-run                 # validate only, no release
gh skill publish --dry-run ./path/to/repo  # validate a specific dir
gh skill publish --fix                     # auto-strip install metadata
gh skill publish --tag v1.0.0              # non-interactive publish
gh skill publish                           # interactive publish flow

--fix and --dry-run are mutually exclusive. --fix only rewrites install-injected metadata.github-* keys and does not publish; commit the result and re-run publish.

The publish flow will:

  1. Add the agent-skills topic to the repo (so search can find it).
  2. Use --tag (or prompt for one in a TTY).
  3. Auto-push any unpushed commits.
  4. Create a GitHub release with auto-generated notes.

Always pass --tag so it doesn't fall through to the interactive flow.

Self-management pattern for agents

A reasonable loop:

  1. gh skill search <topic> --json skillName,repo,namespace
  2. gh skill preview <repo> <skill> to inspect the SKILL.md.
  3. gh skill install <repo> <skill> --agent <host> --pin <ref> for a reproducible install.
  4. Periodically gh skill update --all to refresh.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

agentic-workflows

FreeSummary

This dispatcher helps with GitHub Agentic Workflows by identifying whether a request is about design, creation, configuration, updates, debugging, or upgrades. It selects the matching workflow prompt or skill file so the agent can follow task-specific guidance.

  • Design a GitHub Agentic Workflow from scratch
  • Create or configure a workflow engine
  • Update or debug an existing workflow
cli/cli46.7KUpdated Oct 25, 2026

cli-exercise

FreeSummary

Exercise a real command-line program with specified cases or a stated goal, then capture and verify the observed behavior. It produces local media evidence such as a session video, helping reviewers see what the command did without treating the recording as proof of general correctness.

  • Record specified CLI test cases
  • Demonstrate a command’s behavior
  • Validate an interactive terminal workflow
cli/cli46.7KUpdated Oct 25, 2026

cli-exercise-evidence

FreeSummary

Verify CLI exercise expectations against recorded evidence, render requested media, inspect the results, and return local artifacts with case outcomes. The workflow keeps failures visible and does not publish evidence by default.

  • Verifying a recorded CLI exercise
  • Rendering and inspecting session evidence
  • Returning local artifacts without publishing
cli/cli46.7KUpdated Oct 25, 2026

cli-exercise-exact

FreeSummary

Use this skill to execute supplied CLI test cases without changing their commands, inputs, ordering, or assertions. It guides preparation, exercise, and validation case by case, then classifies results as passed, failed, blocked, or observed based on actual evidence.

  • Run caller-supplied CLI cases in their specified order
  • Preserve literal inputs and expected assertions
  • Validate each case against observed output or state
cli/cli46.7KUpdated Oct 25, 2026

cli-exercise-explore

FreeSummary

Use this skill to explore a CLI goal by choosing observable checks within an approved scope. It guides the agent through preparation, one exercise, and immediate validation for each case, then helps report what the evidence established and what remained unreachable.

  • Explore a CLI task with a clear goal and approved boundaries
  • Choose checks for an outcome such as uploading a file
  • Run and validate CLI cases one at a time
cli/cli46.7KUpdated Oct 25, 2026

cli-exercise-preflight

FreeSummary

This internal module checks whether cli-exercise can use its required build, terminal, and media tools. When a dependency is missing, it identifies a suitable setup path and requires approval before installation, then rechecks readiness. It does not authorize recordings or other actions.

  • Check cli-exercise tool readiness
  • Find missing recording or rendering dependencies
  • Prepare an approved dependency installation
cli/cli46.7KUpdated Oct 25, 2026

See all skills by cli

Report a problem with this skill