SKILLEMALL.ai
GitHub ↗ RU Sign in

DD huo15-markdown-export

火一五排版发布技能 / 火一五 markdown 排版 / 火一五 PDF 导出 / 火一五出版 / 火一五发布 / huo15-markdown-export — 【青岛火一五】markdown 一键导出 PDF / Word / HTML / 长图 / 公众号 inline。**12 主题**默认 **apple-tech(苹果科技风,大字 hero + 紧字距 + 黑白蓝 + 大留白,默认主题)**,其他 11 套:typora-newsprint 报纸 / typora-night 暗色 / github / academic / 微信 / 小红书 / huo15-brand 品牌 / anthropic-doc Anthropic 文档 / editorial-magazine 杂志 / manuscript-book 书稿 / tufte-handout Tufte 边注。Node + markdown-it + Puppeteer + qrcode。与 office-doc 互补(它走公文,本 skill 走 md 视觉美学)。v0.4.2:加 apple-tech 默认 + 修 YAML frontmatter 错乱渲染 + 强化触发词。v0.4.1:反 Type 3 字体修复(PDF 浅灰看不清);v0.4.0:抽 _tokens.css + DESIGN.md 团队规范(8 大设计范式 + 反 AI Slop / Type 3 红线)。capability detection 集成 enhance:md-share/md-publish 输出 JSON,AI chain 调 enhance_share_file 拿公网 URL 发企微/钉钉/微信;无 enhance 独立可跑。触发词:火一五排版发布、火一五排版发布技能、火一五排版、火一五出版、火一五发布、火一五markdown、火一五PDF、火一五导出、排版发布、导出PDF、导出Word、md转PDF、md转Word、md2pdf、md2docx、Typora、长图、小红书、朋友圈长图、微信公众号、博客导出、复盘、changelog、版本对比、品牌报告、发到企微、发给客户、分享链接、公网链接、卡片预览、二维码、苹果科技风、Apple 风、科技风、技术博客、产品文档、品牌故事、深度长文、小说、长篇随笔、研究报告、数据分析、教学讲义、Anthropic 文档风、杂志体、书稿体、Tufte 边注。

ClawHub Agent Skills author: Job Zhao v0.4.4 MIT-0 22 files · 13 scripts body ≈ 5 179 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

火一五排版发布技能 / 火一五 markdown 排版 / 火一五 PDF 导出 / 火一五出版 / 火一五发布 / huo15-markdown-export — 【青岛火一五】markdown 一键导出 PDF / Word / HTML / 长图 / 公众号 inline。12 主题默认…

As a process D 38/100 · Unfinished process — References files that are not bundled: templates/pdf-print.css

AnalyzerGitHubPlaywrightWordSlackAI and agentstype 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
D
70/100
safety, quality, tests
Safety 60%
99
Quality 40%
26
Run on models
none yet
Process rating
D
38/100
Unfinished process
References files that are not bundled: templates/pdf-print.css
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

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. Shorten the description to 1024 characters.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • low Dangerous commands cmd-privilege scripts/md2pdf-puppet.js:88
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    const browser = await puppeteer.launch({ headless: 'new', args: ['--no-sandbox', '--disable-setuid-sandbox'] });
    detectorcode literal

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1049 chars, limit 1024
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5179 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: templates/pdf-print.css
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "aliases"
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: templates/pdf-print.css
  • 0Tools and files. 1 referenced file(s) missing: templates/pdf-print.css
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 20 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Execution cost. Instruction body is 5179 tokens
  • 100Steps. 73 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 12 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (8 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)
  • +3Description length 1049: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 37 headings
  • +3Step-by-step instructions: 73 items
  • +4Has examples (11 code blocks)
  • +3All 12 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 26.

External checks

ClawHub: suspicious
The skill mostly does what it advertises, but it grants broad local publishing/install authority and renders active Markdown content in ways users should review before installing.
LLM: suspicious (high) · VirusTotal: · 16 Sept 2026