BF web-publisher
输入文章 URL **或本地文档（PDF/DOCX/PPTX/XLSX/EPUB/图片/音频/...）**，自动提取正文、可选 AI 改写、并发布到微信公众号；也可只把任意文档转成 Markdown 文本（不发布）。抓取 / 转换 / 改写 / 发布都在服务端 (tools.siping.me) 完成，CLI 不装任何 npm 依赖；登录、公众号配置全部通过对话 + 一次性浏览器跳转完成。⚠️ 服务端走云端固定 IP，**对小红书、部分知乎专栏、登录墙文章、海外站点经常被反爬挡掉**——此时由 AI Agent（Hermes / Cursor / OpenClaw 等）改调用**用户本地安装的 `news-to-markdown-skill`** 把 URL 抓成 Markdown，然后人工复核 / 归档。也可配合 `browser-web-search` 先搜索拿到 URL 再批量发布。
As a process F 36/100 · Will not run — References files that are not bundled: url
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/lib/credentials.js:138Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7642 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: url
Process rating: all ten parameters 36/100
- 0Tools and files. 1 referenced file(s) missing: url
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 41 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 7642 tokens
- 100Steps. 68 steps
- 100Consistency. Name and required fields are in place
- low The response is described with custom markup (19 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 400: enough signal without eating the budget
- +4Structure: 44 headings
- +3Step-by-step instructions: 68 items
- +4Has examples (36 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.