AD extract-doc
提取 .docx/.xlsx/.pdf/图片 文档内容，转换为 Markdown 格式（支持 OCR 识别）。 这是**只读提取工具**，专注于将现有文档转换为 Markdown。 TRIGGER when: 用户要求提取文档内容、读取 Word/Excel/PDF 内容、提取图片文字、 OCR 识别、文档转 Markdown、读取需求文档、提取规格书内容、把 docx 转成 md、 把 xlsx 转成 markdown、PDF 内容提取、扫描件识别、"帮我看看这个文档里有什么"、 "把这个 Word 转成 Markdown"、"读取 Excel 里的数据"、"识别图片中的文字"。 DO NOT TRIGGER when: 用户要求**创建**或**编辑**文档（用 document-skills:docx/xlsx/pdf）、 生成新的 Word/Excel/PDF 文件、修改现有文档内容、添加表格/图表到文档、 格式化文档排版、合并多个 PDF。此 skill 仅用于**读取和提取**，不用于创建或修改。
As a process D 43/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Grep Glob Write Bash mcp__zai-mcp-server__extract_text_from_screenshot
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 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
- 25Steps. 1 steps
- 40Consistency. Frontmatter name (extract-doc) differs from the folder (slugtest)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Execution cost. Instruction body is 674 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
- +4Description does not say when NOT to use the skill (false activations)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 463: enough signal without eating the budget
- +4Structure: 15 headings
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.