SKILLEMALL.ai
GitHub ↗ RU Sign in

BF xhs-crafter

将MD文章排版为3:4比例的精美图片+压缩文字稿，用于公众号/小红书贴图发布。核心能力是本地HTML模板填充+Puppeteer截图渲染（启动本地127.0.0.1 HTTP server加载预存HTML模板，非MD→HTML编译管道）。可选外部能力（每项需用户独立明确同意）：(1)Pexels/Pixabay/Unsplash图库API搜索（发送搜索关键词到外部API）；(2)AI生图API（发送prompt到trae-api-cn，仅限TRAE内部环境）；(3)飞书云盘上传（上传生成的PNG+txt到飞书服务器）。Invoke when用户明确说'xhs-crafter排版'、'用xhs-crafter转图片'、'公众号贴图排版'、'小红书图文卡片'。Do NOT use for原创写作、纯文字排版、视频制作、用户只提到MD文件路径但未明确要求图片排版。

ClawHub Agent Skills author: AI花生 v7.8.0 MIT-0 21 files body ≈ 2 851 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

将MD文章排版为3:4比例的精美图片+压缩文字稿，用于公众号/小红书贴图发布。核心能力是本地HTML模板填充+Puppeteer截图渲染（启动本地127.0.0.1 HTTP…

As a process F 36/100 · Will not run — References files that are not bundled: 路径

IntegrationPlaywrightMarketingtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
94
Quality 40%
82
Run on models
none yet
Process rating
F
36/100
Will not run
References files that are not bundled: 路径
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-credential-use references/image-sources.md:36
    Credential used in a network call (verify the destination is the intended service)
    curl.exe -s -H "Authorization: $env:PEXELS_API_KEY" \
  • low Dangerous commands cmd-privilege assets/screenshot.js:121
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    '--disable-setuid-sandbox',
    code literal

Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: 路径
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "summary"

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: 路径
  • 0Tools and files. 1 referenced file(s) missing: 路径
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 94 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2851 tokens
  • low The response is described with custom markup (6 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
  • +3Output format is not stated: the model decides each time
  • -213 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 384: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 94 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (11 of 13)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

External checks

ClawHub: clean
This skill is a disclosed local Markdown-to-image workflow with optional external image search and cloud upload only after user consent.
LLM: benign (high) · VirusTotal: · 15 Jul 2026