AC boardraw
Turn a natural-language description into a real Excalidraw whiteboard file (.excalidraw) — flowcharts, mind maps, architecture/system diagrams, org charts, wireframes, sticky-note brainstorms, sequence diagrams. Always use this skill whenever the user asks to draw, sketch, diagram, whiteboard, mind-map, or map something out, or mentions "excalidraw", "boardraw", "白板", "画一个", "流程图", "思维导图", "架构图", "组织架构图", "线框图", "泳道图", "看板", or wants a file they can open in Excalidraw or Boardraw. Do NOT hand-write raw .excalidraw JSON directly — the schema has fragile id/seed/binding requirements — always build it with the bundled scripts/excalidraw_builder.py helper instead.
Turn a natural-language description into a real Excalidraw whiteboard file (.excalidraw) — flowcharts, mind maps, architecture/system diagrams, org charts…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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: 5. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1701 tokens
- 100Running it twice. No mutating operations
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 2 example trigger phrases
- +3Description length 668: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.