CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

scientific-figure-making

Covers publication-ready matplotlib figures for academic papers, slides, and reports—bars, trends, scatter, heatmaps, and multi-panel layouts—with this repository’s house style, print/vector export conventions, and parity with figures4papers demos. Use when the user is finalizing or creating such figures in matplotlib. Do not use for interactive dashboards or web viz (Plotly, Altair, Bokeh), exploratory-only plots without a publication target, dominant 3D or geographic mapping, or Illustrator/Figma-first infographic workflows.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-structured navigation hub: excellent conciseness and progressive disclosure with a verified, one-level reference table. Its main weakness is that the body itself is pure directory — it gives no concrete starting point, snippet, or task-level workflow, so a reader must open a reference before doing anything.

Suggestions

Add one concrete first step for the commonest task, e.g. 'Creating a figure from scratch: open tutorials.md and follow the walkthrough for your figure type; check api.md for signatures and PALETTE.'

Inline a minimal anchor of the house style (one short code or config snippet showing the palette import / export call) so the skill is actionable without opening a reference first.

State an ordering convention for the table (e.g. tutorials → common-patterns → api → design-theory → demos) so multi-reference tasks have an explicit sequence.

DimensionReasoningScore

Conciseness

The body is ~25 lines with zero padding: no matplotlib tutorials, no explanation of concepts Claude already knows. Phrases like 'Open `references/` only as needed; do not preload every file' and the compact two-column table mean every token earns its place.

5 / 5

Actionability

The guidance is concrete as navigation ('Open when' conditions per file, e.g. 'references/api.md | Function signatures, `PALETTE`, validation rules') but the body contains no executable content itself — no code snippet, command, or concrete first step for actually producing a figure; everything actionable is deferred to references. This sits between anchor 4 ('mostly executable guidance') and the 'describes rather than instructs' end, landing on 3: some concrete guidance but incomplete in the body.

3 / 5

Workflow Clarity

There is a clear navigation sequence — 'Start from the table below, then follow links inside the document you opened' — with explicit load conditions per reference. It is not a 5 because the body never sequences a figure-making task end-to-end (e.g. which reference to open first when creating a new figure), and there are no checkpoints; the simple-skill exception is partially earned since the single action (pick the right reference) is nearly unambiguous.

4 / 5

Progressive Disclosure

Clear overview with a well-signaled, one-level-deep reference table; all five referenced files (tutorials.md, api.md, common-patterns.md, design-theory.md, demos.md) exist in references/ and contain the promised content (verified PALETTE in api.md, figure_* demos in demos.md). The body explicitly instructs progressive loading rather than preloading, and cross-links between references are surfaced rather than buried. This matches the anchor-5 example structure exactly.

5 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: concrete domain coverage, explicit use and do-not-use triggers, and sharp boundaries against adjacent viz tools. Only minor gap is a few natural synonyms (plot, chart, camera-ready, .pdf) that users might say instead of 'figures'.

DimensionReasoningScore

Specificity

Concrete specifics are enumerated: figure types ('bars, trends, scatter, heatmaps, and multi-panel layouts'), outputs ('print/vector export conventions'), and scope ('this repository's house style... parity with figures4papers demos'). Coverage of the domain is comprehensive with no generic filler — matches the anchor-5 'multiple specific concrete actions; comprehensive coverage'.

5 / 5

Completeness

Explicitly answers what ('Covers publication-ready matplotlib figures... with this repository's house style, print/vector export conventions') and when ('Use when the user is finalizing or creating such figures in matplotlib'), plus an explicit when-not list. This matches the anchor-5 example structure of concrete what + explicit trigger phrases.

5 / 5

Trigger Term Quality

Strong natural terms: 'matplotlib figures', 'publication-ready', 'academic papers', 'slides', 'reports', 'PDF/SVG', plus exclusion terms (Plotly, Altair, Bokeh) that catch near-miss phrasings. A few natural synonyms are missing — users might say 'plot', 'chart', '.pdf', 'camera-ready', or 'journal figure' — so it lands at anchor 4 ('good keyword coverage; a few natural terms missing') rather than 5.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply delimited by 'this repository's house style' and the explicit exclusions ('Do not use for interactive dashboards or web viz (Plotly, Altair, Bokeh), exploratory-only plots... dominant 3D or geographic mapping, or Illustrator/Figma-first infographic workflows'), which name and dismiss the closest competing skills. Minimal conflict risk, matching anchor 5.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

ChenLiu-1996/figures4papers

Path

scientific-figure-making/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.