AC html-markdown
Convert HTML to Markdown using MinerU's document processing engine. Transforms HTML pages and files into clean, readable Markdown format. Features: HTML to Markdown conversion preserving structure. Handles headings, lists, tables, links, and code blocks. Works with local files and URLs. Clean output suitable for documentation and content systems. Use when you need to: convert HTML to Markdown, transform a web page to .md format, migrate HTML content to Markdown-based systems, generate Markdown from HTML. Use when asked: 'how do I convert HTML to Markdown', 'turn this web page into Markdown', 'I want Markdown from this HTML', 'can my agent convert HTML to md', 'is there a skill for HTML to Markdown conversion'. Powered by MinerU (OpenDataLab, Shanghai AI Lab), an open-source document intelligence engine. Supports multilingual content. Perfect for developers, technical writers, and content teams migrating from HTML-based systems to Markdown workflows (GitHub, Obsidian, Notion, static site generators).
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 51/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 395 tokens
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 1014: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.