AD text2echart
Chart generator skill. When triggered: - Default: CONSTRUCT ECharts option JSON and output HTML string directly and render by mermaid and support preview. - Image / vector (图片/矢量图): use CLI with --svg-output (or --svg --embed for offline). - Screenshot (截图): use CLI with --screenshot (needs Playwright). - Fine-tuning (微调/修改): open browser for interactive adjustment. Supports 6 chart types: bar, line, pie, scatter, radar, wordcloud (via JSON). Trigger words: chart, graph, visualize, plot, draw, wordcloud, vent draw图表, 画图, 可视化, 图片, 矢量图, 词云.
Chart generator skill.
As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokencli.js:110High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const base = embed ? loadLocal() : `<script src="https://cdn.jsdelivr.net/npm/ec…@….6.0/dist/echarts.min.js" integrity="sha3…Du6+JXW/C68U…UtU+7zon…Rss" cro
quoted
Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "name-zh" - note
frontmatter-keyunknown frontmatter key "provider"
Process rating: all ten parameters 42/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4220 tokens
- 85Steps. 34 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low The response is described with custom markup (11 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
- +5Description has no quoted example phrases that should trigger the skill
- +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
- +3Description length 544: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (19 of 19)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.