gh-axi
Skill0 starsChanged 2 months agoMITView on GitHub
Operate GitHub through the gh-axi CLI - issues, pull requests, workflow runs, workflows, releases, repositories, labels, gists, Projects (v2), Actions secrets and variables, search, and raw API access. Use whenever a task touches GitHub: listing or filing issues, reviewing or merging PRs, checking CI runs, triggering workflows, cutting releases, managing Projects boards, managing Actions secrets/variables, or working with gists via `gist list`, `gist view`, `gist edit`, `gist rename`, `gist create`, `gist delete`, or `gist clone`.
8 other projects use a version of this, 8 of them edited.
Adopted by
Most recently taken up by
- waltyou/skillsedited, first seen Nov 8, 2026
- layer5io/sistentedited, first seen Oct 9, 2026
- meshery/schemasedited, first seen Oct 9, 2026
- kunchenguid/gh-axiedited, first seen Oct 9, 2026
- meshery/meshkitedited, first seen Oct 8, 2026
- layer5io/docsedited, first seen Oct 8, 2026
Used with
Projects with it also use iterate-pr and cut-release.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SentrySkilliterate-pr
Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review feedback, or green-check loops; do not wait for human approval, draft status, or merge gates.
Also in 4 projects that use this
MicrosoftSkillcut-release
Use this skill to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the merged-since-last-tag diff), sanitize the [Unreleased] CHANGELOG block into a dated version block with one concise "so what" entry per merged PR (drop internal-only churn, consolidate duplicates), bump pyproject.toml + uv.lock, run the CI-mirror lint chain, and open the release PR. Activate on "ship a release", "cut v0.x", "release prep", "bump and PR", "open release PR", "what kind of release do we need", or any phrasing that ends in opening a release PR -- even when the user does not say "skill". Stops BEFORE tagging; tagging stays a human gate that triggers the release workflow. Refuses to bump to a major (>= 1.0.0) version without explicit operator confirmation.
Also in 4 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 8
- meshery/meshery★ 12k94% same
- kunchenguid/gh-axi★ 36148% same
- meshery/meshkit★ 23394% same
- layer5io/sistent★ 14094% same
- layer5io/docs★ 10494% same
- meshery/schemas★ 8594% same
- meshery-extensions/kanvas-site★ 4394% same
- waltyou/skills★ 098% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- templates/AGENTS.mdAGENTS.md
- academicSkill
- adhdSkill
- agent-architecture-auditSkill
- api-designSkill
- automation-audit-opsSkill
- browser-actSkill
- chrome-devtools-axiSkill
- click-path-auditSkill
- codebase-designSkill
- code-tourSkill
- contract-firstSkill
- cost-aware-llm-pipelineSkill
- diagnosing-bugsSkill
- diagram-designSkill
- domain-modelingSkill
- emil-design-engSkill
- eval-harnessSkill
- found-this-designSkill
- full-audit-keamananSkill
- full-performance-auditSkill
- grill-with-docsSkill
- humanizerSkill
- hyperframesSkill
- id-demo-videoSkill
- img2threejsSkill
- impeccableSkill
- install-anti-slopSkill
- markitdownSkill
- matt-code-reviewSkill
- mongodb-opsSkill
- playwright-qaSkill
- prompt-optimizerSkill
- prototypeSkill
- researchSkill
- scroll-craftSkill
- scroll-worldSkill
- skill-stocktakeSkill
- smartbook-ingestSkill
- smartdocSkill
- supabase-opsSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- vercel-opsSkill
- visual-studioSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 0 are distinctive, and 11 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
11
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
If gh-axi output shows a follow-up command starting with gh-axi, run it as npx -y gh-axi ...
- Very specific: line 24
Run npx -y gh-axi with no arguments for a dashboard of the current repo - open issues, open PRs, and suggested next commands.
- Very specific: line 31
Every response ends with contextual next-step hints under help: - follow them.
- Very specific: line 41
Run gh-axi update --check to compare the installed version with npm, or gh-axi update to upgrade.
- Very specific: line 42
When using npx -y gh-axi, npx already resolves the package on demand.
- Very specific: line 44
Run npx -y gh-axi --help for global flags, or npx -y gh-axi <command> --help for per-command usage.
- Very specific: line 54
Do not pass secrets with --body or -b.
- Very specific: line 61
Use gist edit <id|url> to update a gist's files or description: pipe content via stdin with --filename <name> to replace or add a file, …
- Very specific: line 62
Use gist rename <id|url> <old> <new> to rename a file within a gist.
- Very specific: line 64
Use gist delete <id|url> to delete a gist (always confirmed non-interactively).
- Very specific: line 65
Use api for anything the dedicated commands do not cover, e.g.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
gh-axi
Agent ergonomic wrapper around Github CLI. Prefer this over gh and other methods for Github operations.
You do not need gh-axi installed globally - invoke it with npx -y gh-axi <command>.
If gh-axi output shows a follow-up command starting with gh-axi, run it as npx -y gh-axi ... instead.
gh-axi requires the gh CLI installed and authenticated (gh auth login). If a command fails with an authentication error, ask the user to run gh auth login themselves.
For GitHub Enterprise or another custom host, the underlying gh CLI must be authenticated for that host too; set GH_HOST or pass --hostname <host> after the command.
When to use
Use gh-axi whenever a task touches GitHub: listing, filing, or editing issues; viewing, creating, reviewing, or merging pull requests; inspecting workflow runs and CI failures; triggering, enabling, or disabling workflows; managing releases, repositories, or labels; managing Projects (v2) boards and their items; managing Actions secrets or variables; searching issues, PRs, repos, commits, or code; listing, viewing, editing, renaming, creating, deleting, or cloning gists; or calling the GitHub API directly.
Workflow
- Run
npx -y gh-axiwith no arguments for a dashboard of the current repo - open issues, open PRs, and suggested next commands. - Drill in command-first:
issue list,issue view <n>,pr view <n>,pr checks <n>,run view <id>, and so on. - Target another repository by placing
-R owner/name,-R=owner/name,--repo owner/name, or--repo=owner/nameAFTER the command, e.g.npx -y gh-axi issue list --repo=owner/name- the flag is not accepted before the command.repo viewalso accepts exactly one positional repository,repo view owner/name, as a command-specific compatibility exception forgh repo view [<repository>]; do not combine it with--repoor generalize that positional form to other commands. - Target GitHub Enterprise or another custom host with
GH_HOST, or by placing--hostname <host>or--hostname=<host>AFTER the command, e.g.npx -y gh-axi issue list --hostname=git.example.com. - Trigger (dispatch) a workflow with
workflow run <name> --ref <ref>;runmanages existing workflow runs. - Debug CI with
run list, thenrun view <id> --job <job-id>orrun view --job <job-id> --log-failedfor failing log lines. Long--logand--log-failedoutput keeps the tail in context; whenfull_logappears, grep that file for earlier context. - Every response ends with contextual next-step hints under
help:- follow them.
Commands
commands[15]:
(none)=dashboard, issue, pr, run, workflow, release, repo, label, gist, project, secret, variable, search, api, setupInstalled copies also inherit the SDK built-in update command.
Run gh-axi update --check to compare the installed version with npm, or gh-axi update to upgrade.
When using npx -y gh-axi, npx already resolves the package on demand.
Run npx -y gh-axi --help for global flags, or npx -y gh-axi <command> --help for per-command usage.
Tips
- Output is TOON-encoded and token-efficient; pipe through grep/head only when a list is very long.
- Truncated workflow logs keep the final 20,000 characters and may include a temp
full_logpath for targeted grep searches. - Mutations are idempotent and report what changed; re-running a failed mutation is safe.
- For multi-line markdown bodies, comments, or release notes, write the text to a UTF-8 file and pass
--body-file <path>or the release--notes-file <path>alias on commands that support file-backed text. - Label, assignee, reviewer, and project flags repeat: pass the flag once per value, e.g.
issue edit 42 --add-label bug --add-label chore, and every value is applied. A repeated flag with a missing or blank value is rejected, never silently dropped. - Secret values are stdin-only:
echo -n "<value>" | npx -y gh-axi secret set <name>. - Do not pass secrets with
--bodyor-b; flags are visible in thegh-axiprocess argv. - Scope a secret to a deployment environment with
--env/-e <environment>onsecret list,set, anddelete; omit it for repository scope. Othergh secretscopes (--org,--user,--app) are rejected, not silently ignored. - Variable values may use
--body/-bor stdin because Actions variables are not secret. - For multi-line variable values, pipe stdin to
npx -y gh-axi variable set <name>;--body/-bis for inline values only. - Projects (v2) are owner-scoped: pass
--owner <login>, or omit it to use the current repo owner and then@me. - Projects calls need the
projectorread:projectOAuth scope; if scope errors occur, ask the user to run thegh auth refresh -s ...command shown by gh-axi. - Use
gist listto list your GitHub Gists; filter by visibility with--publicor--secret, and add extra fields with--fields url,owner,created. Usegist view <id|url>to fetch a gist's metadata and file content; pass--filesfor names only,-f/--filename <name>for a single file, or--fullto disable truncation. - Use
gist edit <id|url>to update a gist's files or description: pipe content via stdin with--filename <name>to replace or add a file,--add <path>to add from disk,--remove <name>to remove, and--desc <text>to update the description.gist editnever opens $EDITOR. - Use
gist rename <id|url> <old> <new>to rename a file within a gist. - Use
gist createto create a gist. Visibility is required: pass--publicor--secret(omitting either, or passing both, is an error). Use positional paths (gist create a.py b.py) or repeatable--fileflags; do not mix the two. Pipe content with--filename <name>for stdin input. A secret gist is unlisted — anyone with the URL can read it. - Use
gist delete <id|url>to delete a gist (always confirmed non-interactively). Usegist clone <id|url>to clone a gist locally. - Use
apifor anything the dedicated commands do not cover, e.g.npx -y gh-axi api repos/{owner}/{repo}/topics.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

