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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Review

ASecurity

Use for review lifecycle work: human-gate checks or UI screenshot evidence. Not for archiving (retired), product code review, or Lighthouse analysis.

45 stars
0 votes
0 copies
0 views
Added 9/22/2026
developmentnodecode-reviewperformance

Works with

claude code

Security Analysis

A100/100

Scanned 9/24/2026

Install to Claude Code

$npx -y skills add Charles5277/nuxt-supabase-starter --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/charles5277-review/badge)](https://www.skillsdirectory.com/skills/charles5277-review)

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

Download with Pro
Files
SKILL.md
---
name: review
description: "Use for review lifecycle work: human-gate checks or UI screenshot evidence. Not for archiving (retired), product code review, or Lighthouse analysis."
---

<!-- clade-skill-scope: both -->

# Review lifecycle(統一入口)

`review` is the single public entry for the review support lifecycle. Choose one
mode from the user's request, then read the corresponding legacy guide before
acting; those guides retain the detailed contracts and are references, not
independently discoverable skills.

| Mode | Use when | Detailed guide |
| --- | --- | --- |
| `scan` | Check whether anything in this repo is waiting on a human | No guide: run `flow gates --repo-only --json` and follow [[review-gui-surface]] § Hard rule |
| `screenshot` | Collect UI screenshots or execute a visual checklist | [screenshot guide](references/.legacy/review-screenshot/SKILL.md) and its evidence contract |
| `archive` | Retired: do not append `docs/manual-review-archive.md`; completed items stay in the work package | [review archive guide](references/.legacy/review-archive/SKILL.md) |
| `screenshots` | Retired: do not move topics into `_archive/` | [screenshot archive guide](references/.legacy/screenshots-archive/SKILL.md) |

Screenshot evidence is collected by the named **Pi Gemini 3.8 Flash** worker
(`screenshot-review-verify`, effort `high`; dispatch with
`--model gemini --effort high --table-row screenshot-review-verify`); 截圖與 item 的符合性 gate 另交 **Claude Opus 5.5 · medium** (`screenshot-match-analysis`). The worker must not
sign its own compliance result.

需要使用者拍板時,向使用者提問並等待回答;不要自行補完未決事項。

## Routing

- `/review scan` runs `node ~/offline/clade/vendor/scripts/flow/flow.ts gates --repo-only --json`
  from the consumer root (never with `CLADE_HOME`) and reports every card by
  gate family; exit 2 from `--require-empty` means it could not tell, never "none".
- `/review screenshot` collects evidence through the existing screenshot
  worker and preserves every evidence limitation in the receipt.
- `/review archive` does **not** write `docs/manual-review-archive.md`. Completed items stay in the work package; see the retired guide.
- `/review screenshots` does **not** sweep topics into `_archive/`; it reports current top-level topics only.

If the request is a product code review, use the configured code-review agent.
If it is a Lighthouse audit or performance trace breakdown, use the dedicated
browser-devtools capability. This skill owns lifecycle evidence. Archive production writers are retired.


## Runtime 執行 — Claude Code

本 runtime 的合格視覺執行載體是 Claude Code `Agent` tool,`subagent_type: screenshot-review`。in-process dispatch 將 brief 放在 `prompt`;完成後由主線收取 JSON manifest,再依共同 evidence gate 判讀。

**NEVER** 派 Pi 任一 model,也 **NEVER** 讓執行體再轉派或因 quota 不足降低獨立視覺判讀要求。工具不可用時回報阻擋,保留 gate 未完成。

## Archive interaction

When `/review archive` or `/review screenshots` requires a user choice, use
Claude Code `AskUserQuestion` with every valid option and an explicit skip
option, then wait for the answer before moving files. The question mechanism
is only the runtime carrier of the shared interaction contract.

Attribution

YuDefineYuDefine
View sourceMore from Charles5277 →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

284722 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2192 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →