AC pdf-extract-md-figs
Split a PDF (especially a scientific paper / 论文) into clean body-text Markdown PLUS a folder of extracted figure images that are saved but NOT read into context, so tokens are never wasted on irrelevant figures. Text goes through markitdown; figures are extracted with PyMuPDF, auto-separated into real numbered figures vs junk (logos/ads/TOC), indexed in a manifest mapping page→Figure number, and only opened one-at-a-time on explicit request. Use this skill WHENEVER the user uploads a PDF and wants to read/analyze/process/对比/梳理 it, OR says things like 'turn this paper into markdown', '把这篇PDF拆一下', '用这个skill', '提取图片但先别读图', 'process this PDF', or hands over a paper expecting figure-aware analysis. Trigger even if they only say '测试一下' / 'analyze this PDF' after uploading — default to this split-first, read-figures-on-demand workflow rather than dumping the whole PDF (with all its images) into context.
Split a PDF (especially a scientific paper / 论文) into clean body-text Markdown PLUS a folder of extracted figure images that are saved but NOT read into…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 4. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 9 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1029 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (6 tags): a typed call is more reliable
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 909: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.