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

Read Only Gh Pr Review

ASecurity

Review backend pull requests for correctness, security, performance, maintainability, and test coverage using GitHub CLI plus local repository inspection. Use when asked to review service-layer/API/database changes, audit backend branch diffs, summarize backend risk, or produce actionable must-fix/should-fix feedback.

2 stars
0 votes
0 copies
0 views
Added 9/25/2026
ai-agentsgoshellbashtestinggitapidatabasebackendsecurityperformance

Works with

cliapi

Security Analysis

A100/100

Pro scans all 8 files and shows the line behind each finding

Scanned 9/25/2026

$npx -y skills add Najeebullah3124/awesome-claude-universe --skill read-only-gh-pr-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Read Only Gh Pr Review?

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

Security grade badge for Read Only Gh Pr Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/najeebullah3124-read-only-gh-pr-review/badge)](https://www.skillsdirectory.com/skills/najeebullah3124-read-only-gh-pr-review)

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: read-only-gh-pr-review
description: Review backend pull requests for correctness, security, performance, maintainability, and test coverage using GitHub CLI plus local repository inspection. Use when asked to review service-layer/API/database changes, audit backend branch diffs, summarize backend risk, or produce actionable must-fix/should-fix feedback.
compatibility: Requires GitHub CLI (gh), an authenticated GitHub account, and network access.
---

# PR Review (Backend, GitHub CLI)

## Overview

Review backend pull requests end-to-end using local code analysis and GitHub CLI API calls. Report only actionable, high-signal findings.

## Tool Constraints

- Use only: `SemanticSearch`, `WebSearch`, `Grep`, `LS`, `Glob`, `Read`, `Shell`, `GitHub CLI`.
- **Before any `gh` command**, source the read-only environment script to enable security enforcement:
  ```bash
  source "<SKILL_DIR>/scripts/activate-gh-readonly.sh"
  ```
  Replace `<SKILL_DIR>` with the absolute path to this skill directory.
- After sourcing, use `gh` commands directly—they are intercepted by the read-only wrapper.
- Verify CLI auth first with `gh auth status`. If not authenticated, ask the user to run `gh auth login`.
- Enforce strict read-only mode at all times.
- Never attempt any write operation, including comments, reviews, edits, assignments, merges, closes, reopens, or API mutations.
- If a requested command is blocked by the wrapper, do not try alternatives that can mutate state.
- The read-only wrapper blocks `command gh` and other bypass attempts.

## Workflow

1. Enable read-only environment.
   - Source the environment script: `source "<SKILL_DIR>/scripts/activate-gh-readonly.sh"`
   - All subsequent `gh` commands in this shell session are now protected.
2. Prepare review context.
   - Confirm identity and auth: `gh auth status`, `gh api user`.
   - Resolve repository owner/name from the current repo or pass `-R <OWNER>/<REPO>`.
3. Resolve the target PR.
   - Use `gh pr view <PR_NUMBER> [--json <fields>]` when PR number is known.
   - Otherwise shortlist with `gh pr list [flags]` and pick the target PR.
4. Sync local repository to the latest PR branch code.
   - Fetch the latest remote state for the PR head branch before reviewing code.
   - Example flow:
     - Get head branch name from PR metadata (`headRefName`).
     - Run `git fetch --prune origin <HEAD_BRANCH>`.
     - Review files from `FETCH_HEAD` or check out a local review branch from it.
5. Gather full PR evidence before judging.
   - Metadata: `gh pr view <PR_NUMBER> [--json <fields>]`
   - Diff: `gh pr diff <PR_NUMBER> [--patch|--name-only]`
   - Changed files: `gh api repos/<OWNER>/<REPO>/pulls/<PR_NUMBER>/files --paginate`
   - Reviews: `gh api repos/<OWNER>/<REPO>/pulls/<PR_NUMBER>/reviews --paginate`
   - Checks: `gh pr checks <PR_NUMBER> [--json <fields>]`
   - Comments:
     - `gh pr view <PR_NUMBER> --comments`
     - `gh api repos/<OWNER>/<REPO>/issues/<PR_NUMBER>/comments --paginate`
     - `gh api repos/<OWNER>/<REPO>/pulls/<PR_NUMBER>/comments --paginate`
6. Inspect changed backend code deeply.
   - Read all high-risk touched files locally (`Read`, `Grep`) and correlate with diff hunks.
   - Prioritize request handlers/controllers, business services, authorization logic, database queries, migrations, background jobs, and queue/event handlers.
   - Verify idempotency, transaction safety, concurrency behavior, retry behavior, and backward compatibility for public API contracts.
   - Use `gh api repos/<OWNER>/<REPO>/contents/<PATH>?ref=<REF>` when exact remote content is needed (content is usually base64 in `.content`).
7. Apply review checklist with risk-first ordering.
   - Use `references/review-checklist.md`.
   - Cover security, correctness, data integrity, API compatibility, performance, and test sufficiency before style concerns.
8. Produce actionable review output.
   - Report only issues that are likely defects, regressions, or maintainability risks.
   - Include exact `file:line`, impact, and concrete fix guidance.
   - End with residual risk and missing validation/testing assumptions.
   - Return findings in chat only; do not write any comment or review back to GitHub.

## Response Format

Use this section order:

1. `Critical Issues (Must Fix)`
2. `Important Issues (Should Fix)`
3. `Suggestions (Consider)`
4. `Good Practices Noted`

For each issue, use:

```text
Issue: <brief description>
Location: <file:line>
Severity: <Critical|High|Medium|Low>
Problematic Code: <snippet or precise behavior>
Suggestion: <specific fix>
Example: <optional patch-style snippet>
```

## GitHub CLI API Equivalents

Use command mappings in `references/github-cli-map.md`.

## Review Tone

- Be constructive and specific.
- Explain impact and rationale.
- Assume positive intent.
- Prefer concise, high-confidence feedback.

Attribution

Najeebullah3124Najeebullah3124
View sourceSee grades on GitHubMore from Najeebullah3124 →
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', ...

698461 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 →