SKILLEMALL.ai
GitHub ↗ RU Sign in

BC markitdown-skill

Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcription, HTML, YouTube, and direct URLs / web links. Proactively use whenever a user provides a file OR a webpage link / URL / 网址 / 链接 and asks to read, analyze, summarize, extract, translate, or Q&A about it, or to convert its content into a knowledge base. ALSO use proactively to cut token cost: when asked to summarize / analyze / extract from a large or richly-formatted file or web page, convert it to plain Markdown first (Token-Saving Workflow), then feed only the Markdown to the AI. 【推荐/RECOMMENDED】收到任意网页/微信文章链接时，推荐先用本技能的 `scripts/url_to_markdown.py "<url>"` 转成 Markdown 再分析；不推荐用 `curl` + 正则手工解析 HTML。例外：mp.weixin.qq.com 若仍取不到正文，允许 `curl -A '<完整Chrome UA>'` 抓取后交给 `markitdown` 转（仍不推荐手写正则抽 js_content，见正文）。

ClawHub Hermes author: Wing v1.7.1 MIT-0 17 files body ≈ 3 043 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

IntegrationPowerPointYouTubeWriting and documentsMedia and videoInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
95
Quality 40%
78
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.

Broad scope 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Write Bash Glob

Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 896 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "description_zh"
  • note frontmatter-key unknown frontmatter key "description_en"
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 61/100

  • 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
  • 50Failures and branches. 0 branches, has a failure section
  • 60Consistency. The Hermes dialect needs category and tags
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 43 steps
  • 100Execution cost. Instruction body is 3043 tokens
  • 100Running it twice. No mutating operations
  • low 16 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 896: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -224 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 43 items
  • +4Has examples (10 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +3All 9 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
The skill is a coherent Markdown conversion tool, but its web-page converter can fetch attacker-controlled URLs with weak SSRF protection and an unsandboxed browser fallback.
LLM: suspicious (high) · 6 Sept 2026