AB office-transform
Extract or edit a selection from xlsx, docx, pdf, or pptx into a new file; the source is never modified.
Extract or edit a selection from xlsx, docx, pdf, or pptx into a new file; the source is never modified.
As a process B 65/100 · Nearly there — weak spots: when it triggers, 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: 12. 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 65/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 11 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4553 tokens
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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 104: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 21 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.
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 8 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 7 не дошли до работы, и об их поведении мы ничего не узнали.
scripts/office_extract.py | не запустился: office_extract.py: error: the following arguments are required: --file, --anchor, --out |
scripts/office_patch_copy.py | не запустился: office_patch_copy.py: error: the following arguments are required: --file, --edits, --out |
scripts/office/common.py | ничего за пределами своей папки |
scripts/office/docx.py | не запустился: ModuleNotFoundError: No module named 'office' |
scripts/office/ooxml.py | не запустился: ModuleNotFoundError: No module named 'office' |
scripts/office/pdf.py | не запустился: ModuleNotFoundError: No module named 'office' |
scripts/office/pptx.py | не запустился: ModuleNotFoundError: No module named 'office' |
scripts/office/xlsx.py | не запустился: ModuleNotFoundError: No module named 'office' |
29 Sept 2026