agentleFS
Sign inStart free
KevinchamplinKevinchamplin/claude-skills/review/SKILL.md

review

Skill3 starsChanged 6 months agoMITView on GitHub

Quick security and quality review of current changes before deploying. Use when the user says /review or wants a pre-deploy check. Scans diffs for security issues, credential leaks, and code quality problems.

  • Reads credentials

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images and 10 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.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no local changes, diff against the base branch: git diff main...HEAD (or master)

    line 14
  2. Distinctive:

    If issues found: list each with file, line, and severity (CRITICAL / WARNING / INFO)

    line 35
  3. Distinctive:

    If clean: confirm with a one-line "all clear"

    line 36
  4. Distinctive:

    Keep the report concise — no filler

    line 37
  5. Distinctive:

    NEVER modify code during review — only report findings

    line 40

“Common” is measured: kept by at least 6 in 10 of the 157 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review — Pre-Deploy Security & Quality Check

Review all pending changes for security vulnerabilities, credential leaks, and quality issues.

Steps

  1. Gather changes:
    • git diff (unstaged) and git diff --staged (staged)
    • If no local changes, diff against the base branch: git diff main...HEAD (or master)
  2. Security scan — check the diff for:
    • Credential leaks: API keys, passwords, tokens, secrets, .env values hardcoded in source
    • SQL injection: raw user input in queries without parameterization
    • XSS: unescaped user input rendered in HTML/JSX
    • Command injection: user input passed to shell commands
    • IDOR: missing authorization checks on endpoints that access resources by ID
    • Debug code: var_dump, console.log with sensitive data, dd(), leftover die() calls
    • .env changes: flag if .env was modified — it should almost never be committed
    • API key exposure: LLM API keys (OpenAI, Anthropic), payment keys (Stripe), auth secrets hardcoded in client-side code
    • Prompt injection: user input concatenated directly into LLM prompts without sanitization
    • SSRF: user-controlled URLs passed to server-side fetch/curl without validation
  3. Quality scan — check for:
    • Incomplete implementations (TODO/FIXME/HACK comments in new code)
    • Error handling gaps (empty catch blocks, swallowed exceptions)
    • Obvious logic errors
    • Files that look accidentally included (.DS_Store, node_modules, compiled assets)
  4. Report:
    • If issues found: list each with file, line, and severity (CRITICAL / WARNING / INFO)
    • If clean: confirm with a one-line "all clear"
    • Keep the report concise — no filler

Rules

  • NEVER modify code during review — only report findings
  • Focus on the diff, not the entire codebase
  • CRITICAL issues = must fix before deploy (credentials, injection, auth bypass)
  • WARNING = should fix (debug code, missing error handling)
  • INFO = nice to fix (style, minor improvements)
  • Delegate to an Explore agent if the diff is very large (50+ files)

Download now (ZIP)

Does 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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free