AC html-extract
Extract content from HTML pages and files using MinerU. Converts HTML to clean, structured Markdown preserving headings, lists, tables, and text hierarchy. Features: HTML content extraction to Markdown. Preserves document structure and formatting. Handles complex HTML layouts. Token-based extraction for full feature set. Use when you need to: extract content from HTML, convert HTML to Markdown, get text from a web page, parse HTML file content. Use when asked: 'how do I extract content from HTML', 'convert HTML to Markdown', 'I want to read this HTML file', 'can my agent extract text from HTML', 'is there a skill for HTML extraction', 'parse this web page'. Built on MinerU by OpenDataLab (Shanghai AI Lab), an open-source document intelligence engine. Works with local HTML files and URLs. Great for content scrapers, documentation tools, and workflows that need to convert HTML content into clean Markdown for further processing.
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. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 402 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 939: 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: 8 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.