GitHub (gh-first) Skill

Trust Score 92/100

Guides agents to perform GitHub workflows using the GitHub CLI (`gh`)—auth, repo creation, remotes, and safe credential handling—minimizing user prompts.

triggers:githubgh authrepo createpushremote setupgit workflowcredential handling

GitHub SKILL.md

What it does

This skill teaches an agent a gh-first workflow for interacting with GitHub: detect and reuse existing authentication, create repositories, configure remotes, push branches, and fall back safely to git or API calls when necessary. It prescribes minimal-interruption prompts, strict secret-handling rules, and step-by-step execution flows for different environment states.

When to use it

Use when the agent needs to perform GitHub-related tasks on behalf of the user: creating or pushing to repos, setting remotes, performing authenticated gh actions, or finishing onboarding flows that require minimal user input. Helpful for CI setup, repo initialization, and automated pushes.

What's included

Scripts: none in the skill directory (has_scripts=false)
References: none (has_references=false)
Instructions: detailed rules for credential handling, interactive gh auth driving, fallback strategies if gh is missing, and exact preferred command flows for success conditions.

Compatible agents

Agents capable of running shell commands and using gh (CLI-aware agents like Copilot/Codex, CLI automation agents, or containerized runners).

Audit Summary

Well-crafted skill guiding agents through GitHub CLI (gh) workflows with strong emphasis on minimizing user prompts and safe credential handling. No bundled scripts — purely instructional SKILL.md. Exceptional security posture: explicitly forbids exposing or persisting secrets. Clear, unambiguous instructions with good/bad prompt examples. Solid architecture with proper frontmatter and progressive disclosure, though it's a single-file skill without scripts/ or references/ directories.

Watch Out

Requires gh CLI installed for full functionality
Falls back to plain git if gh unavailable

Notes

Pure instructional skill with no scripts to execute. Security rules are exemplary — actively prevents secret exposure. Could benefit from adding scripts/ for common operations like repo creation or auth checking.

Information

Repository: openagent
Stars: 5,231

Trust Score

Overall92

Security100

Code Quality88

Architecture78

Usefulness82

More from openagent

PowerPoint (PptxGenJS)

Create, update, and QA editable PowerPoint (.pptx) presentations by providing a PptxGenJS build script; includes read/write tooling for validation and visual QA

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Back to Skills