AB pptx-extract
Extract a PowerPoint deck into full-data, page-delimited Markdown — every text run, table, speaker note, and image — with unextractable data (vector metafiles, charts, OLE embeds) skipped but visibly noted on its slide, then prove losslessness with a 5-point machine audit. Use when the user asks to extract/convert a PPTX to Markdown, add a new deck to an extraction project, or regenerate a stale extraction. Related terms: PPT, PowerPoint, PPTX, slide extraction, 提取.
Extract a PowerPoint deck into full-data, page-delimited Markdown — every text run, table, speaker note, and image — with unextractable data (vector…
As a process B 79/100 · Nearly there — no weak spots found
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
- note
edit-residuethe text marks something as outdated (lines 82): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 79/100
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 27 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1402 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (7 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)
- +1No license
- +2Single-language instructions
- +3Description length 470: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.