agentleFS
Sign inStart free
pesappesap/skills/github/SKILL.md

github

Skill1 starsChanged 3 months agoMITView on GitHub

Operate GitHub from the terminal with `gh`: inspect or update pull requests, review threads, issues, and workflow runs; debug or optimize GitHub Actions, caches, artifacts, matrices, concurrency, and runners. Use for requests such as "check this PR", "why did CI fail", or "reply to review". Do not use for GitLab or GitHub App/OAuth implementation.

166 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use taskflow-inbox-triage, BlueBubbles and 10 more.

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.
  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • jiulingyunSkill

    BlueBubbles

    为Clawdbot构建或更新BlueBubbles外部通道插件（扩展包，REST发送/探测，webhook入站）。

    Also in 20 projects that use this

  • hkyutongSkill

    node-connect

    Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

    Also in 18 projects that use this

  • molt-botSkill

    discord-e2e

    Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.

    Also in 10 projects that use this

  • molt-botSkill

    openclaw-repair-sweep

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    Also in 10 projects that use this

  • clawdbotSkill

    openclaw-performance

    Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

    Also in 7 projects that use this

  • +2 more from molt-bot

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 151 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use trigger evals only when tuning recognition and evals/evals.json only when grading output quality.

    line 32
  2. Distinctive:

    Read the matching task reference and inspect repository guidance or workflow files that govern the target.

    line 38
  3. Very specific:

    Verify the remote result with a follow-up gh query.

    line 45
  4. Distinctive:

    Before creating a PR, check for an open PR with the same head branch.

    line 52
  5. Very specific:

    Add Closes #N only when the durable source issue is resolved from explicit instruction, an issue-numbered branch, session context, or forge …

    line 55
  6. Distinctive:

    Before claiming PR success, verify its base, commits, signature state, body, close marker, and checks on the remote.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 151 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitHub

Resolve the repository and target first, then gather remote evidence with gh before proposing or making changes. When outside a repository, pass --repo owner/repo or use a URL.

Task router

Open only the reference whose trigger matches the task:

  • Pull requests — PR state, checks, review-thread replies, creation, and verification.
  • Issues — issue creation, triage, labels, and parent/child relationships.
  • Workflow runs — failed-run and job-log investigation.
  • GitHub Actions — workflow YAML, caching, matrices, artifacts, concurrency, runners, and CI performance.
  • API patterns — gh api, GraphQL, --json, and --jq when standard subcommands do not expose enough data.

Use trigger evals only when tuning recognition and evals/evals.json only when grading output quality; do not load eval files during normal GitHub work.

Core workflow

  1. Confirm repository, PR/issue/run target, and desired outcome.
  2. Read the matching task reference and inspect repository guidance or workflow files that govern the target.
  3. Gather current state with structured gh output where available.
  4. Diagnose from concrete PR state, review threads, checks, logs, artifacts, labels, issue context, or workflow YAML.
  5. Take the smallest high-impact action: reply in-thread, update metadata, rerun, patch workflow configuration, or create the requested artifact.
  6. Verify the remote result with a follow-up gh query. Do not infer success from a mutation command alone.

Critical policies

  • Reply to reviewer comments in their existing thread; use a general PR comment only when no thread exists.
  • Before creating a PR, check for an open PR with the same head branch.
  • Build PR bodies explicitly. Use a repository template when present, otherwise use pr-template.md.
  • Add Closes #N only when the durable source issue is resolved from explicit instruction, an issue-numbered branch, session context, or forge evidence.
  • Before claiming PR success, verify its base, commits, signature state, body, close marker, and checks on the remote.

Output

Report key gh evidence, findings or actions, workflow changes where relevant, verification status, and remaining risks or follow-up work.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free