Usable, but review first — and it is token-heavy能用,但先审一遍 —— 而且很吃 Token
70/100
Safety grade安全评级
C
70/100 · gate: review70/100 · 闸门:复核
Token costToken 成本
4,357
2.1× median2.1× 中位
Skill briefSkill 简述
Set up Cloudflare Turnstile end-to-end in a project. Scan the codebase, create the widget via the Cloudflare API, embed it on the right forms, wire canonical server-side siteverify in the customer's existing backend, validate, and persist t…在项目中端到端配置 Cloudflare Turnstile:扫描代码库、通过 Cloudflare API 创建 widget、嵌入合适的表单、在现有后端对接规范的 siteverify 服务端校验、验证并持久化 token。
Review findings · 10评测结果 · 10
Description doesn’t say WHEN to use itdescription 没说清什么时候该用它medium中危A good description names the trigger (e.g. "when reviewing a PR"). Without it the skill mis-fires or never fires.好的 description 会点明触发场景(比如"审查 PR 时")。少了它,skill 要么乱触发、要么根本不触发。
Bloated: high token cost内容冗长 · token 成本偏高medium中危~4,357 tokens on every single call. Compress instructions and trim examples.每次调用都要多花约 4,357 个 token。精简指令、删减示例就能省下来。
References API keys / env config引用 API key / 环境变量配置medium中危Reads an API key or env var — normal for API clients. Ensure keys come from the runtime (not hardcoded); a leak risk only if sent to an untrusted endpoint.读取 API key 或环境变量——对 API 客户端来说很正常。确保 key 来自运行时(别硬编码在文件里);只有把它发往不可信的地址时才有泄露风险。
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。
Contains curl / wget network command包含 curl / wget 网络命令medium中危Accesses the network from the shell. If the target is untrusted it can pull malware or exfiltrate data.从 shell 直接访问网络。如果目标不可信,可能被用来拉取恶意程序或外传数据。
Reads credentials and makes network calls — verify the destination既读凭证又发网络请求——请核实目标地址medium中危The normal shape of an API client (your key → the API). Static analysis sees the capability, not the intent — confirm the endpoint is one you trust; it is a data-leak risk only if it is not.API 客户端本来就长这样(你的 key → 对应的 API)。静态分析只看得到"能做什么",看不到"想干什么"——确认这个地址是你信得过的;只有它不可信时才谈得上泄露风险。
Privilege escalation / changes exec permission — in a warning提权 / 修改可执行权限 —— 出现在警告里low低危Appears inside a prohibition/warning ("never …"), not as an instruction to run. Flagged for awareness only.它出现在一句禁止 / 警告里("never …"),并不是要你执行的指令。这里只是提醒你留意一下。
Hard-coded IP address硬编码的 IP 地址low低危Literal IPs are often used to bypass domain review for egress — worth verifying.写死的 IP 常被用来绕过域名审查、偷偷外联——值得核实一下。
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。