Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/an8079/take-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/an8079/take-skills/takes-fro-review)<a href="https://agentmods.dev/commands/an8079/take-skills/takes-fro-review"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-fro-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/an8079/take-skills/takes-fro-review"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-fro-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.04964 |
| Opus 5 | $0.00016 | $0.02482 |
| Sonnet 5 | $0.00006 | $0.00993 |
| Haiku 4.5 | $0.00003 | $0.00496 |
Grade A, and why
takes-fro-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/takes-fro-review - GAN式前端对抗审查
灵感来源：GAN（生成对抗网络）——将"生成"和"评估"拆给两个独立 Agent，让评估者用具体打分标准将主观判断转化为可量化指标。
使用方式
/takes-fro-review
/takes-fro-review http://localhost:3000
/takes-fro-review --max-iterations 20
/takes-fro-review --target-score 85
核心概念
┌─────────────────────────────────────────────────────────┐
│ GAN 审查循环 │
├─────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────────┐ ┌──────────────────┐ │
│ │ Generator │◄────────│ Evaluator │ │
│ │ (生成器) │ 反馈 │ (评估器) │ │
│ │ 修改/生成页面 │────────►│ 量化打分+建议 │ │
│ └──────────────────┘ └──────────────────┘ │
│ ▲ │ │
│ │ 迭代 (5~15 轮) │ │
│ └──────────────────────────────┘ │
│ │
│ 退出条件: 评分达标 OR 达到最大迭代次数 │
│ │
└─────────────────────────────────────────────────────────┘
团队组成
| 角色 | 职责 | 使用的技能 |
|---|---|---|
| Generator | 负责前端页面生成与修改，接收评估反馈并改进 | skills/frontend-design/SKILL.md |
| Evaluator | 用量化标准评估页面，启动 agent-browser 实际测试 | /agent-browser + skills/webapp-testing/SKILL.md |
| Orchestrator | 协调两者迭代，统计评分，记录改进历史 | 主会话 |
四项评分标准（量化打分）
每项满分 25 分，总分 100 分。Evaluator 须逐项给出分数+证据。
| 维度 | 评估内容 | 扣分项 |
|---|---|---|
| 设计质量 (25) | 视觉连贯性、辨识度、整体协调性 | 布局混乱、配色打架、无视觉层次 |
| 原创性 (25) | 有无独立设计决策，是否千篇一律的 AI 味 | 俗套 AI 审美（见 checklist）；加分项可弥补扣分 |
| 工艺 (25) | 排版、间距、配色和谐度、CSS 细节 | 间距不一致、字体选择随意、hover 效果粗糙 |
| 功能性 (25) | 可用性、任务完成度、交互反馈 | 点击无反应、表单无法提交、响应式断裂 |
评分参考
| 分数区间 | 等级 | 说明 |
|---|---|---|
| 90-100 | 卓越 | 四项均表现优秀，有独特设计语言 |
| 75-89 | 良好 | 有明显辨识度，工艺良好，可用性达标 |
| 60-74 | 合格 | 整体可用，但设计或工艺有明显改进空间 |
| 40-59 | 不足 | 存在多个维度问题，需大幅改进 |
| 0-39 | 不合格 | 视觉粗糙、功能断裂、无设计决策 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 408 lines · 32 tokens per session scan A f6df75f34169
takes-fro-review is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 4,964 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
frontend-e2e
Perform a thorough live E2E test of a frontend web application using browser-bridge MCP tools. Tests every page, interactive element, form, navigation flow, responsive breakpoint, and accessibility rule through real browser interaction.
a11y-audit
Audit Accessibilité WCAG 2.2 AAA.
visual-test
Testing visual de componentes UI y páginas con detección de regresiones visuales. Usa cuando el usuario dice "visual test", "snapshot test", "regression test UI", "visual regression", "UI test", "component test", "screenshot test", "Chromatic", "percy", "regred visual". Detecta cambios visuales en componentes y…
test-bar
Generate a floating QA test overlay for the current branch's UI changes. Use when user says /test-bar, needs visual QA scenarios, or wants to test conditional rendering paths.
test-bar-remove
Remove test bar artifacts injected by /test-bar. Use when user says /test-bar-remove or wants to clean up QA overlay code.
build-from-canva
You are the master orchestrator for converting a Canva design into a fully working, tested React application. You receive a Canva URL and guide the entire process through 12 phases, using specialized skills and agents.