Usable — but review before you trust it能用 —— 但信任之前先审一遍
86/100
Safety grade安全评级
A
86/100 · gate: review86/100 · 闸门:复核
Token costToken 成本
1,761
around median接近中位
Efficacy有用性
—
Top models already handle it — see below强模型已能胜任 · 见下方
Efficacy · actually measured (not guessed)
Today's top models already do this well without it — no added lift to claim yet.
Today's top models
This tier already does it — no lift to add · e.g. Claude 4 · GPT-4-class · DeepSeek-V3
100% without → 100% with · measured on deepseek-chat (4×3)
Standard / older models
Measured a gain (+16.7 pts), but a conservative CI at this sample still spans 0 — directional, not yet firm · e.g. MiniMax-Text-01 · smaller open models
67% without → 83% with · measured on MiniMax-Text-01 (4×3) · 95% CI -18–50 pts
How: we install the skill into a real model, run the same tasks with it vs without, and compare — labeled with the exact model + sample size above.
有用性 · 真实测量(非猜测)
如今主流强模型不装它也已做得很好——暂无可声明的额外提升。
主流强模型
这类模型已自带,装不装一个样 · 如 Claude 4 · GPT-4 级 · DeepSeek-V3
方法:把这个 skill 装进真实模型,用同一批任务「装 vs 不装」各跑一遍再对比 —— 上面标注了具体模型和样本量。
Skill briefSkill 简述
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, glo…按照生产级最佳实践审查和编写 Cloudflare Workers 代码,适用于编写新 Worker、审查 Worker 代码、配置 wrangler.jsonc 或排查常见反模式(streaming、floating promise、全局状态等)。
Review findings · 4评测结果 · 4
Bloated: high token cost内容冗长 · token 成本偏高medium中危~1,761 tokens on every single call. Compress instructions and trim examples.每次调用都要多花约 1,761 个 token。精简指令、删减示例就能省下来。
Embedded shell script block内嵌 shell 脚本块medium中危Ships runnable command-line scripts. Not necessarily bad, but must be sandboxed and reviewed.附带了可直接运行的命令行脚本。不一定是坏事,但必须放进沙箱并经过审查。
Makes outbound network requests发起对外网络请求medium中危Sends or pulls data from external endpoints — a data-egress channel; confirm the target is trusted.向外部地址收发数据——这是一条数据外流通道;请确认目标是可信的。
References a .env file引用了 .env 文件low低危Touching .env usually means reading config or secrets — check its purpose.碰 .env 通常意味着在读配置或密钥——确认一下它到底想干什么。
Why there is no “one-click optimize” on this page为什么这页没有「一键优化」
SkillMOO is the independent evaluator: we never modify a third-party author's original work — grading and rewriting the same artifact would compromise the independence this rating stands on. One-click optimize runs only on YOUR copy: paste this skill's SKILL.md into the free detector to get an engine-verified optimize of your copy. Authors: fix the review findings above at the source — we re-grade on every refresh and this page updates automatically.SkillMOO 是评级方:我们从不改动第三方作者的原作 —— 既当裁判又动手改,评级的独立性和公信力就没了。「一键优化」只作用于你自己的副本:把这份 SKILL.md 粘贴到免费检测页,即可获得经引擎逐项校验的一键优化。若你是作者,按上方「评测结果」在源头逐条修复即可 —— 我们会重新评级,本页自动更新。
Local skill checkup — one command, every skill you run本地 Skill 全面体检 —— 一条命令,扫完你装的所有 Skill
Grades every skill in your Claude Code / Codex — safety, token bloat, and conflicts. 100% local: nothing is uploaded.给你 Claude Code / Codex 里装的每个 skill 逐个评级 —— 安全、Token 臃肿、冲突。100% 本地完成,不上传任何内容。
Grade computed 2026-08-03 · rubric skillmoo-static/2.0. Efficacy shown only when measured on a labeled model + task suite — never invented.评级生成于 2026-08-03 · 规则版本 skillmoo-static/2.0。有用分只在标注了模型+任务集的真实测量后才显示 —— 绝不虚构。
For the author · claim your rating badge作者专区 · 领取评级徽章
One step: paste this line into your README —一步:把下面这行粘进你的 README ——
Anti-forgery: the badge is rendered live by skillmoo.com, carries this skill’s NAME inside it, and links back to this page — hotlinking someone else’s badge shows the wrong name in plain sight, and one click lands on the real rating. It updates automatically whenever we re-grade.防伪说明:徽章由 skillmoo.com 实时渲染,图内自带本 skill 的名字并链回本页 —— 冒用他人徽章会当场显示对方的名字,读者一点即达真实评级页。我们重新评级时徽章自动同步。
Independent static analysis by SkillMOO — the Consumer Reports for agent skills. Safety, token, and conflict grades are computed, not opinions. Efficacy is only ever claimed when measured. We rate & link to the source; we do not rehost skill content.由 SkillMOO 独立静态分析 —— 面向 agent skill 的「消费者报告」。安全、Token、冲突三项评级都是算出来的,不是主观意见;有用性只在真实测量后才声明。我们只评级、只链回源,绝不转存 skill 内容。