agentleFS
himkthimkt/config/skills/github-cli/SKILL.md

github-cli

Skill40 starsChanged 4 days agoMITView on GitHub

Use this skill when the user shares a GitHub URL (issue or pull request). Automatically fetch details using GitHub CLI (gh command). Triggered by URLs like github.com/himkt/.claude/issues/123 or github.com/himkt/.claude/pull/123. Do NOT run gh commands directly — always invoke this skill first.

  • Commits and pushes

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use terraform, codex-cli and 3 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.
  • ihiteshguptaSkill

    terraform

    Expert in Infrastructure as Code with Terraform. Use for creating, managing, and versioning infrastructure across cloud providers.

    Also in 3 projects that use this

  • garri333Skill

    codex-cli

    OpenAI Codex CLI mastery skill for installation, authentication, terminal commands, code generation from natural language, file editing, project scaffolding, and IDE integrations. Covers GPT-5.2 Instant/Thinking tiers and shell/container execution modes.

    Also in 3 projects that use this

  • PostHogSkill

    karpathy-guidelines

    Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Based on https://github.com/multica-ai/andrej-karpathy-skills.

    Also in 3 projects that use this

  • MicrosoftSkill

    caveman

    Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules

    Also in 3 projects that use this

  • BlockSkill

    frontend-design

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Always pass --jq to project fields and, when relevant, drop out-of-scope rows.

    line 13
  2. Very specific:

    Use gh --jq directly — do not pipe to external jq.

    line 15
  3. Distinctive:

    Write a concise title and description based on the final diff.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 19 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 CLI Skill

Fetch GitHub issues and pull requests with gh + --json + --jq.

Workflow

  1. Parse {owner}, {repo}, {number} from the URL. If only a number was given, run gh repo view --json nameWithOwner -q .nameWithOwner.
  2. Always pass --jq to project fields and, when relevant, drop out-of-scope rows. Unfiltered comment/review/file payloads run to thousands of lines; a focused filter shrinks input 10–100×.

Use gh --jq directly — do not pipe to external jq. The local Bash validator rejects multi-command pipes.

Common select(...) predicates:

  • Time window: select((.created_at | fromdateiso8601) > (now - 10800))
  • Author: select(.user.login == "...")
  • State: select(.state == "OPEN")
  • Unresolved threads: select(.in_reply_to_id == null)

Fetch commands

# Issue
gh issue view {url} --json title,author,body,state,labels,comments --jq '...'

# PR overview
gh pr view {url} --json title,author,body,state,reviewDecision,baseRefName,headRefName,comments --jq '...'

# Diff (do NOT use gh api for diffs)
gh pr diff {url}              # full
gh pr diff {url} --name-only  # files only

# Inline review comments
gh api repos/{owner}/{repo}/pulls/{number}/comments --paginate --jq '[.[] | {user: .user.login, path, line, body, html_url, created_at}]'

# Review summaries
gh api repos/{owner}/{repo}/pulls/{number}/reviews --paginate --jq '[.[] | {user: .user.login, state, body, submitted_at}]'

# CI checks
gh pr checks {url}

Creating a PR

Write a concise title and description based on the final diff. Explain what changed and why, and include relevant validation. Follow applicable CLAUDE.md / AGENTS.md instructions for language, structure, and style.

gh pr create --title "..." --body-file /path/to/pr-description.md

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.