CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ds-figure-polish

Use when a research project needs a polished data figure (results chart, paper figure, appendix figure, progress summary plot) made with matplotlib, or a render-inspect-revise pass before treating a figure as final.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ds-figure-polish/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 well-structured, restrained instruction skill: concrete rules, real bundled styling asset, and an exemplary render-inspect-revise workflow with explicit validation and feedback loops. The only notable gaps are the absence of a complete executable example script and mild redundancy between the style contract and the self-review checklist.

DimensionReasoningScore

Conciseness

The body is directive throughout with no explanations of concepts Claude already knows, and sections are tight bullet lists. It is not a 5 because there is minor redundancy — the self-review checklist repeats style-contract items ('grid too strong', 'legend unnecessary') and lines like 'Do not rely entirely on defaults' could be trimmed.

4 / 5

Actionability

Concrete guidance throughout: specific figure sizes in inches, per-surface-class export formats, a real bundled style asset with a `plt.style.use("<absolute path>/assets/deepscientist-academic.mplstyle")` pattern, and a ten-item inspection checklist. It falls short of anchor 5 because no complete copy-paste example script is shown; the Python pattern is a semi-executable bullet list with a placeholder path.

4 / 5

Workflow Clarity

The mandatory render-inspect-revise workflow is a clearly numbered five-step sequence with an explicit validation checkpoint ('open the rendered figure yourself... inspect the actual result, not just the plotting code') and a feedback loop ('If any answer is negative, revise before calling the figure complete' followed by re-export), matching the anchor-5 pattern of explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

The body is well-sectioned cohesive guidance with one clearly signaled, one-level-deep bundle reference (`assets/deepscientist-academic.mplstyle`, verified to exist and correctly used via plt.style.use). It is good structure with minor gaps rather than anchor 5: at ~170 lines, some reference-style material (e.g. the full default-rules and size tables) could arguably live in a separate file, and no other reference files organize the detail.

4 / 5

Total

17

/

20

Passed

Description

70%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, trigger-focused description with an explicit 'Use when' clause and distinctive research-figure terminology. Its main weakness is that the 'what' is expressed through conditions rather than concrete action verbs, leaving capability coverage implied rather than explicit.

Suggestions

State capabilities as explicit third-person actions, e.g. 'Creates polished academic figures (line, bar, point-range) with matplotlib and runs a render-inspect-revise pass before finalizing them.'

Add common synonyms and formats users would naturally say: 'plot', 'graph', 'publication figure', and export formats like .pdf/.png.

Briefly note the boundary against generic charting (e.g. 'for research/paper-facing figures, not exploratory dashboards') to further reduce overlap with general dataviz skills.

DimensionReasoningScore

Specificity

The description names the domain (research figures, matplotlib) and figure types ('results chart, paper figure, appendix figure, progress summary plot') plus a 'render-inspect-revise pass', but capabilities are phrased as conditions ('needs a polished data figure') rather than a list of concrete actions, matching anchor 3 rather than the several-specific-actions pattern of anchor 4.

3 / 5

Completeness

It has an explicit 'Use when...' clause with concrete triggers, and the 'what' (making polished matplotlib figures, render-inspect-revise passes) is present but only implied through the needs-clause rather than stated as direct capabilities, so it falls just below the clearly-explicit-both anchor 5.

4 / 5

Trigger Term Quality

Natural terms like 'results chart', 'paper figure', 'appendix figure', 'progress summary plot', and 'matplotlib' give good keyword coverage. It is not anchor 5 because common variations such as 'graph', 'plot' (outside one compound), 'publication figure', and file extensions (.pdf/.png) are missing.

4 / 5

Distinctiveness Conflict Risk

The research/paper-figure polish niche with terms like 'appendix figure' and 'render-inspect-revise' is mostly distinct, but a generic 'make a chart with matplotlib' request could also plausibly trigger general plotting or dataviz skills, giving minor overlap risk consistent with anchor 4.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

OpenLAIR/dr-claw

Path

skills/ds-figure-polish/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.