Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Using Github

ASecurity

Work the forge from the command line with gh — open and describe a pull request, read review comments, check why CI failed, file and close issues. Use when a task involves a pull request, an issue, or a failing check rather than only local code.

6 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentsgitapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/30/2026

$npx -y skills add mirzaaghazadeh/StandBye --skill using-github --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Using Github?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Using Github
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mirzaaghazadeh-using-github/badge)](https://www.skillsdirectory.com/skills/mirzaaghazadeh-using-github)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: using-github
description: Work the forge from the command line with gh — open and describe a pull request, read review comments, check why CI failed, file and close issues. Use when a task involves a pull request, an issue, or a failing check rather than only local code.
---

# Using GitHub

The `gh` CLI is how you see what the humans see. Check it is there and authenticated before you
plan around it: `gh auth status`. If it is missing or logged out, say so — that is a setup problem
for the owner, not something to work around by scraping the web.

## Reading before writing

Most GitHub work starts with a question, and these answer it:

- `gh pr list` / `gh pr view <n> --comments` — what is open and what reviewers said.
- `gh pr diff <n>` — the change itself, without checking it out.
- `gh pr checks <n>` — which checks failed. Follow with `gh run view <id> --log-failed` to get the
  actual failure rather than guessing from the name.
- `gh issue list --label bug` / `gh issue view <n>` — what has been reported.
- `gh api` when nothing else exposes what you need. Prefer the porcelain commands where they exist.

## Opening a pull request

The description is the part a human reads, so write it for them:

- **What changed**, in a sentence a non-author understands.
- **Why**, or the issue it closes — link it (`Closes #123`) so it closes itself.
- **How you tested it**: the commands you ran and what they printed.
- **What to look at hardest**: the risky hunk, the assumption you made, the thing you were unsure
  about. Reviewers give better reviews when you aim them.

Keep it in the repo's template if there is one. Open it as a draft if it is not ready — a draft is
information, a broken pull request marked ready is noise.

## Responding to review

- Answer every comment, even if the answer is "done" — an unanswered comment reads as ignored.
- Push a fix as a new commit rather than force-pushing over the review, so the reviewer can see
  what changed since they looked.
- Disagree once, with reasoning. Then do what the reviewer asked or take it to the owner.
- Do not resolve a thread you did not act on.

## Issues

- When you file one, make it reproducible: version, steps, what you expected, what happened. An
  issue nobody can reproduce is a note to self.
- Close with the commit or pull request that fixed it, so the trail survives.
- Do not open issues for things you are about to do in the next ten minutes.

## What is not yours

Merging, releasing, changing repository settings, inviting people, and anything that touches
another person's pull request are the owner's, unless your rules say otherwise. Approving a pull
request is a review action — say what you checked; do not approve on the strength of a skim, and
never approve your own.

Comments you post are public and permanent. Write them as if the owner's colleagues will read
them, because they will.

Attribution

mirzaaghazadehmirzaaghazadeh
View sourceSee grades on GitHubMore from mirzaaghazadeh →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →