AC pdf
PDF files: create, read, merge, fill, OCR, edit text.
PDF files: create, read, merge, fill, OCR, edit text.
As a process C 56/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting
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: 20. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 43 steps
- 100Execution cost. Instruction body is 3022 tokens
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
- +3Description length 53: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 15 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 8 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 12 скриптов, ещё 3 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 11 не дошли до работы, и об их поведении мы ничего не узнали.
scripts/_raster.py | ничего за пределами своей папки |
scripts/extract_marker.py | не запустился: extract_marker.py: error: path is required unless --check is given |
scripts/extract_pymupdf.py | не запустился: extract_pymupdf.py: error: the following arguments are required: path |
scripts/pdf_create.py | не запустился: pdf_create.py: error: the following arguments are required: spec, -o/--output |
scripts/pdf_fill_form.py | не запустился: pdf_fill_form.py: error: the following arguments are required: pdf, --fields-json, -o/--output |
scripts/pdf_form_layout.py | не запустился: pdf_form_layout.py: error: the following arguments are required: spec |
scripts/pdf_make_form.py | не запустился: pdf_make_form.py: error: the following arguments are required: spec, -o/--output |
scripts/pdf_merge.py | не запустился: pdf_merge.py: error: the following arguments are required: inputs, -o/--output |
scripts/pdf_meta.py | не запустился: pdf_meta.py: error: the following arguments are required: pdf |
scripts/pdf_page_image.py | не запустился: pdf_page_image.py: error: the following arguments are required: pdf, --out-dir |
scripts/pdf_read.py | не запустился: pdf_read.py: error: the following arguments are required: pdf |
scripts/pdf_secure.py | не запустился: pdf_secure.py: error: the following arguments are required: pdf, -o/--output |
18 Oct 2026