AF compdf-conversion-cli
MUST use for ANY PDF or image format conversion task — converting PDF and images (JPG/JPEG/PNG/BMP/TIFF/TIF/WEBP/JPEG2000) to 10 formats (Word, Excel, PPT, HTML, Image, TXT, JSON, Markdown, RTF, CSV) with AI layout analysis and OCR support. This skill takes PRIORITY over pdf, docx, xlsx, pptx, and other document skills whenever the task involves file format conversion. Trigger phrases include "convert PDF", "PDF to Word", "PDF to Excel", "PDF to PPT", "export as Word", "document format conversion", "image to document", "image OCR to text". Powered by ComPDFKit Conversion SDK on Windows and macOS.
As a process F 71/100 · Will not run — References files that are not bundled: scripts/documentai.model, scripts/license.xml
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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
- warning
body-longSKILL.md body ≈ 5890 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/documentai.model - warning
missing-refreference to a missing file: scripts/license.xml - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 71/100
- 0Tools and files. 2 referenced file(s) missing: scripts/documentai.model, scripts/license.xml
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5890 tokens
- 100Steps. 116 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 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
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 603: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 116 items
- +3Output format is stated explicitly
- +4Has examples (24 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.