CD ppt-script-authoring
Design and build a deck as a python-pptx program: your own layout system, the source's own figures, charts you draw, and a template's design when the user gave one.
Design and build a deck as a python-pptx program: your own layout system, the source's own figures, charts you draw, and a template's design when the user…
As a process D 47/100 · Unfinished process — References files that are not bundled: deck/build/references/tables.md, deck/build/references/design-requirements.md, deck/build/references/layouts.md
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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 38228 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: deck/build/references/tables.md - warning
missing-refreference to a missing file: deck/build/references/design-requirements.md - warning
missing-refreference to a missing file: deck/build/references/layouts.md - warning
missing-refreference to a missing file: deck/build/references/charts.md - warning
missing-refreference to a missing file: deck/build/references/shapes.md - warning
missing-refreference to a missing file: deck/build/references/icons.md - warning
missing-refreference to a missing file: deck/build/references/formulas.md
Process rating: all ten parameters 47/100
- 0Tools and files. 7 referenced file(s) missing: deck/build/references/tables.md, deck/build/references/design-requirements.md, deck/build/references/layouts.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 38228 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 42 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 164: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (22 code blocks)
- +4Reference files are cited in the instructions (7 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.