AC draw-skills
Academic figure generation assistant. Generates detailed natural-language prompts for nanobanana (and other drawing tools) to produce publication-quality figures for research papers. Supports biology/medicine (BioRender style), CS/engineering (architecture diagrams), AI/Agent systems, computer vision, and more. Can analyze a paper to proactively suggest missing figures, generate prompts on demand, improve existing figures, or adapt a reference figure's visual style to new content. Trigger keywords: draw figure, generate figure, draw diagram, paper figure, 画图, 绘图, 论文配图, 生成图, 绘制示意图, 流程图, 架构图, BioRender, 机制图, nanobanana prompt, figure prompt, 参考图风格, 图表建议, 补图
As a process C 58/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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: 3. 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
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 75Steps. 3 steps
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2098 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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)
- +1No license
- +2Single-language instructions
- +3Description length 663: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 3 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.