BB word-to-html
Convert Word documents (.docx, .doc) to clean HTML using the MinerU API. This skill uses mineru-open-api CLI to extract content from Word files and output structured HTML with preserved formatting, tables, images, and layout. Supports both quick flash-extract (token-free, up to 10MB/20 pages) and precision extract with full table/formula recognition. Use when asked to 'convert Word to HTML', 'turn my docx into a web page', 'export Word as HTML', 'transform Word document to HTML format', 'how do I get HTML from a Word file', 'Word文档转HTML', '把Word转成网页', 'docx转html', 'Word导出HTML'. Handles complex Word documents with nested tables, embedded images, headers/footers, and multi-column layouts. Ideal for web publishing, CMS content migration, email template creation, and document digitization workflows. Powered by MinerU document intelligence engine.
Convert Word documents (.docx, .doc) to clean HTML using the MinerU API. This skill uses mineru-open-api CLI to extract content from Word files and output…
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
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 "tools" - note
edit-residuethe text marks something as outdated (lines 26): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 68/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 349 tokens
- 100Running it twice. No mutating operations
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 854: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 9 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.