Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Review

ASecurity

Read-only review of recent git changes (diff since the last review/tag) for correctness, security, and quality — flags edge cases and missing boundary error handling, hardcoded secrets, injection risks (SQL/XSS/command), sensitive data in logs, over-engineering, and dead code, then returns a prioritized checklist. Reports only; does not edit — to actually apply simplifications use simplify. Use when the user asks to "review my changes", "check this before I ship", "look over the diff", "is th...

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgosqlgitsecurity

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add jckeen/dotfiles --skill review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Review?

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

Security grade badge for Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jckeen-review-dotfiles/badge)](https://www.skillsdirectory.com/skills/jckeen-review-dotfiles)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: review
description: Read-only review of recent git changes (diff since the last review/tag) for correctness, security, and quality — flags edge cases and missing boundary error handling, hardcoded secrets, injection risks (SQL/XSS/command), sensitive data in logs, over-engineering, and dead code, then returns a prioritized checklist. Reports only; does not edit — to actually apply simplifications use simplify. Use when the user asks to "review my changes", "check this before I ship", "look over the diff", "is this safe/correct", or wants a quality/security pass on recent work.
---

When the user runs /review, do the following:

1. Run `git diff HEAD~3..HEAD` (or since last review/tag) to see recent changes.
   If the argument is a PR number, review that GitHub PR instead: `gh pr diff <n>`
   selects the PR by number and needs no local branch state — never require the
   current checkout to match the PR. For surrounding files at the PR's revision,
   resolve its head with `gh pr view <n> --json headRefOid`, fetch that commit,
   and inspect it with `git show <verified-head>:<path>`. If running checks needs
   a checkout, use a separate temporary worktree at that verified head. Never
   switch branches or replace files in the user's checkout for a review.
2. Review the diff for the checklist below. Run this pass at low effort — a
   fast, literal read of what the code does, not a rewrite of the design.

**Correctness**
- Does the code do what it's supposed to?
- Are there edge cases or missing error handling at system boundaries?

**Security**
- Any hardcoded secrets, keys, or tokens?
- SQL injection, XSS, or command injection risks?
- Sensitive data in logs or responses?

**Quality**
- Unnecessary complexity or over-engineering?
- Dead code or unused imports?
- Naming clarity?

3. Present findings as a short checklist:
   - ✅ Looks good: [thing]
   - ⚠️ Worth considering: [suggestion]
   - 🚨 Fix before shipping: [issue]

4. Keep it focused — only flag things that matter. Don't nitpick style unless it hurts readability.

## Coach pass (judgment, not bugs)

After the correctness checklist above, do one fresh-eyes pass whose only question
is quality. Read the diff and the files it touches as a skeptical senior reviewer,
and answer two things:

- Would this genuinely impress a sharp reviewer, or land as
  competent-but-forgettable?
- What single change would most raise its quality — a missed edge case, a test
  that proves the hard part, a clearer abstraction, better naming, a real
  simplification, or a doc/comment that earns its place?

Cite file:line. If it's already strong, say so — don't invent nitpicks. This is
distinct from the correctness pass: it reports no bugs, only the one
highest-leverage improvement.

Attribution

jckeenjckeen
View sourceMore from jckeen →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →