AC svg-architecture-diagram
Create professional, publication-quality technical architecture diagrams using pure SVG in HTML, then screenshot via Playwright. Produces crisp, pixel-perfect diagrams with precise connection lines, color-coded modules, and clear text at any resolution. Use when: (1) user asks for a system architecture diagram, (2) user wants a technical component diagram or flow chart, (3) user needs a data flow or pipeline visualization, (4) any diagram requiring accurate text labels and precise connecting lines. Triggers: "architecture diagram", "架构图", "技术架构", "system diagram", "component diagram", "flow diagram", "数据流图", "模块图", "draw architecture", "画架构图", "technical diagram". Prefer this over AI image generation for any diagram with text labels.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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: 6. 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 64/100
- 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
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 31 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1727 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (7 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 743: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.