CC academic-figures
Stop redoing figures. One command renders publication-ready charts: 15 chart types (bar, scatter, heatmap, forest, KM, ROC, violin, composite, PRISMA 2020 review flow...), 7 curated themes incl. colorblind-safe Okabe-Ito/GLM, 9 journal presets (Nature/Lancet/Science/Cell/NEJM/JAMA/IEEE + Chinese CMA and CN-core with auto CJK), built-in PDF verification (text-overlap + minimum font-size gates) that catches rejection-worthy flaws before you export, a --suggest analyzer that picks the right chart type from your data, --stats auto significance brackets, --alt accessibility text, Excel (xlsx) input, and 10 scenario templates. 600dpi PNG/SVG/PDF/TIFF/EPS output, 100% local, data never leaves your machine. Triggers: make figure, generate chart, plot data, bar chart, scatter plot, heatmap, forest plot, Kaplan-Meier, ROC curve, survival curve, violin plot, composite figure, flow diagram, PRISMA flow, systematic review, publication-ready figure, journal figure, publication figure, hatching, colorblind-safe palette, 600dpi export.
Stop redoing figures.
As a process C 57/100 · Has gaps — weak spots: inputs and preconditions, execution cost, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 52. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1036 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 10226 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "date" - note
frontmatter-keyunknown frontmatter key "requires" - note
edit-residuethe text marks something as outdated (lines 378): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 10 mutating operations with no state check
- 40Execution cost. Instruction body is 10226 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 94 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 27 top-level sections: this looks like several domains in one skill
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1035: 120–800 characters recommended
- -32 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 35 headings
- +3Step-by-step instructions: 94 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (5 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 36.