CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-figure

Generate publication-quality figures and tables from experiment results. Use when user says \"画图\", \"作图\", \"generate figures\", \"paper figures\", or needs plots for a paper.

69

Quality

84%

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 highly actionable, well-sequenced skill body with executable code and validation checkpoints for batch figure generation. Its main weaknesses are structural redundancy between sections and a lack of progressive disclosure into separate reference files despite its length.

Suggestions

Move the Figure Type Reference table and full per-figure code templates into a references/ file (e.g. FIGURE_TYPES.md), keeping SKILL.md as an overview that links one level deep, to improve progressive disclosure.

De-duplicate the Step 3 decision tree with the Figure Type Reference table and merge overlapping items between Key Rules and the Step 8 checklist to tighten conciseness.

Add an explicit fix-and-retry feedback loop after the Step 5 render-then-verify check (e.g. "if any label is clipped or legend overlaps data, adjust the script and re-run before proceeding to review") to lift workflow clarity.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes Claude's competence (no explaining of matplotlib or PDF basics), but the Step 3 decision tree duplicates the Figure Type Reference table and Key Rules repeats several Step 8 checklist items, so it could be trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready code for the shared style config, line plots, bar charts, LaTeX tables, include snippets, and a bash run loop, covering the common figure cases.

5 / 5

Workflow Clarity

Eight clearly sequenced steps with an explicit render-then-verify validation checkpoint and a quality checklist; the batch operation has validation so avoids the 3-cap, but it lacks an explicit fix-and-retry feedback loop.

4 / 5

Progressive Disclosure

No bundle files exist and the ~310-line skill is monolithic; it has good internal section headers, but content such as the Figure Type Reference table and full code templates that could live in separate referenced files is inlined.

3 / 5

Total

16

/

20

Passed

Description

90%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.

A strong, well-formed description that clearly states the skill's purpose and provides concrete, natural trigger phrases in both Chinese and English. The only minor gap is that it lists just two actions rather than a fuller enumeration of capabilities.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ("Generate publication-quality figures and tables from experiment results"), but does not enumerate the range of figure/table types, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what (generate publication-quality figures and tables from experiment results) and when (concrete "Use when user says..." trigger phrases).

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage across two languages with synonyms ("画图"/"作图", "generate figures"/"paper figures"/"plots for a paper") that users would naturally say.

5 / 5

Distinctiveness Conflict Risk

Clear niche of publication-quality paper figures/tables from experiment data with distinct bilingual triggers, giving minimal overlap risk with other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
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.