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
- rogue-dev-studio/ai-agents-roguetheir own version, first seen Nov 1, 2026
- kuailexiaozixin/githubtheir own version, first seen Oct 24, 2026
- Anish29801/cursor-plugin-github-clitheir own version, first seen Oct 20, 2026
- danilolucasmd/skillstheir own version, first seen Oct 19, 2026
- garri333/Skillstheir own version, first seen Oct 11, 2026
- momo0338/skillstheir own version, first seen Oct 11, 2026
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.
ihiteshguptaSkillterraform
Expert in Infrastructure as Code with Terraform. Use for creating, managing, and versioning infrastructure across cloud providers.
Also in 3 projects that use this
garri333Skillcodex-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
PostHogSkillkarpathy-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
MicrosoftSkillcaveman
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
BlockSkillfrontend-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
Other versions25 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 25
- kaeawc/auto-mobile★ 56same name
- georgekhananaev/claude-skills-vault★ 28same name
- doug-skinner/github-cli-claude-skill★ 10same name
- abdullahkhawer/devops-skills★ 8same name
- jonhill90/skills★ 8same name
- trotsky1997/My-Claude-Agent-Skills★ 7same name
- magnusrodseth/dotfiles★ 3same name
- shalomb/agent-skills★ 3same name
- aaronflorey/agent-skills★ 2same name
- chief-builder/cli-vs-mcp★ 2same name
15 more not listed
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 repositoryOne other file it gives its agents.
- claude/CLAUDE.mdCLAUDE.md
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
- Very specific: line 13
Always pass --jq to project fields and, when relevant, drop out-of-scope rows.
- Very specific: line 15
Use gh --jq directly — do not pipe to external jq.
- Distinctive: line 49
Write a concise title and description based on the final diff.
“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.
Files
GitHub CLI Skill
Fetch GitHub issues and pull requests with gh + --json + --jq.
Workflow
- Parse
{owner},{repo},{number}from the URL. If only a number was given, rungh repo view --json nameWithOwner -q .nameWithOwner. - Always pass
--jqto 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.mdDoes 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.

