AC doc-to-text
Extract plain readable text from Word documents (.doc, .docx) using MinerU. Outputs Markdown (the closest plain-text format supported) for easy reading and processing. Features: quick text extraction from .docx without token (flash-extract). Full extraction for .doc and .docx with token. JSON output mode with dedicated text fields for true plain text. Language support for English, Chinese, and more. Use when you need to: get plain text from a Word file, extract readable content from .docx, convert Word to text, read a Word document as plain text. Use when asked: 'how do I get text from a Word file', 'extract plain text from docx', 'I want to read this Word document as text', 'can my agent convert Word to text', 'is there a skill for Word to text'. Built on MinerU by OpenDataLab (Shanghai AI Lab), an open-source document intelligence engine. Works with local files and URLs. Perfect for data pipelines, search indexing, NLP preprocessing, and any workflow that needs raw text content from Word documents.
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 446 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 1015: 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.