AC docs-pdf
Use this skill whenever the user wants to do anything with PDF files. Triggers include: reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs from scratch, filling PDF forms, encrypting or password-protecting PDFs, extracting images from PDFs, OCR on scanned PDFs, compressing/optimizing PDFs, viewing PDF info/metadata, converting images to PDF, converting PDF to images, comparing two PDFs, reordering pages, repairing corrupted PDFs, and listing fonts. Also trigger when the user uploads a .pdf file and asks you to do something with it, or when they mention "PDF" in any context involving file creation, editing, or data extraction — even if they don't say "PDF skill" explicitly.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 25. 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 53/100
- 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
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 16 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 2848 tokens
- low 10 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- -227 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 795: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 18 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.