AD blueprint-figure
Draws static SVG figures for lessons, READMEs and manuals in the AI Engineering from Scratch look: paper panel, blueprint accent, nine figure kinds, fixed hue meanings, eight arrow styles, and checks for legibility and markup. Trigger phrases: "draw a figure", "blueprint figure", "sequence figure", "state machine figure", "figure for this lesson", "add a diagram to the manual".
Draws SVG diagrams in 'AI Engineering from Scratch' style: paper panels, blueprint accents, nine figure types, eight arrow styles. Promises fixed color palette and legibility checks.
Grade A, no critical findings. Five files, one script, 2411 tokens of code. Passes on all major platforms. Broken references flag missing files in the repo—not critical for the skill itself, but may cause issues with external data. Quality score 87 against process score 38 means solid structure but narrow functionality.
Install if you need diagrams in exactly this style for docs. Otherwise—overkill.
Draws static SVG figures for lessons, READMEs and manuals in the AI Engineering from Scratch look: paper panel, blueprint accent, nine figure kinds, fixed hue…
As a process D 38/100 · Unfinished process — References files that are not bundled: scripts/audit_manuals.js
The same skill appears in 1 more place: ai-engineering-from-scratch
How to improve
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/audit_manuals.js
Process rating: all ten parameters 38/100
- 0Tools and files. 1 referenced file(s) missing: scripts/audit_manuals.js
- 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
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Steps. 78 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2411 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 380: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 78 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.