AF fec-drawio-studio
Use when creating editable technical diagrams with draw.io / diagrams.net sources, including architecture diagrams, ERD, UML, sequence diagrams, flowcharts, ML model diagrams, official shape lookup, brand symbols, Graphviz auto-layout, codebase structure maps, .drawio validation, or draw.io CLI export fallback. Do not use for ordinary raster image generation, freehand sketches, interactive canvas/Three.js scenes, or decorative SVG animation. Chinese triggers include draw.io, diagrams.net, editable architecture diagrams, .drawio, ER diagrams, UML, sequence diagrams, auto layout, shape retrieval, code structure diagrams.
io / diagrams.net sources, including architecture diagrams, ERD, UML, sequence diagrams, flowcharts, ML model diagrams, official shape lookup, brand symbols…
As a process F 57/100 · Will not run — References files that are not bundled: data/shape-index.json, styles/schema.json, styles/built-in/default.json
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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: data/shape-index.json - warning
missing-refreference to a missing file: styles/schema.json - warning
missing-refreference to a missing file: styles/built-in/default.json - warning
missing-refreference to a missing file: styles/built-in/corporate.json - warning
missing-refreference to a missing file: styles/built-in/handdrawn.json
Process rating: all ten parameters 57/100
- 0Tools and files. 5 referenced file(s) missing: data/shape-index.json, styles/schema.json, styles/built-in/default.json
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 35 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1623 tokens
- 100Running it twice. Mutating operations check current state
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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 626: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 35 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 11 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.