CtrlK
BlogDocsLog inGet started
Tessl Logo

figure-polish

Use when a quest needs a polished milestone chart, paper-facing figure, appendix figure, or a mandatory render-inspect-revise pass before treating a figure as final.

69

Quality

85%

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

70%

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

A well-structured, actionable skill body with a clear workflow and validation loop. The main gaps are minor redundancy around the core principle and a lack of executable example code in the Python pattern section.

Suggestions

Consolidate the 'restrained/clarity over fancy' guidance into the Core principle section and remove the restatements in Chart selection and the 'Do not…' lines to tighten conciseness.

Replace the descriptive 'Suggested Python pattern' with a minimal executable snippet (plt.style.use with the asset path, figure size, and both vector+png export) so it is copy-paste ready.

Consider moving the surface-class definitions and practical figure-size table into a referenced reference file so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is directive and free of concept-explanation padding, but the 'restrained/not fancy' principle is restated across Core principle, Chart selection, and several 'Do not…' lines, so it could be tightened.

2 / 3

Actionability

Concrete rules, exact figure sizes, and export formats are given, but the 'Suggested Python pattern' is descriptive ('prefer: plt.style.use…, explicit figure size') with no executable copy-paste code block.

2 / 3

Workflow Clarity

The numbered render-inspect-revise sequence and the self-review checklist with an explicit feedback loop ('If any answer is negative, revise before calling complete') provide clear validation checkpoints.

3 / 3

Progressive Disclosure

Sections are well organized, the referenced style asset (assets/deepscientist-academic.mplstyle) is a real one-level bundle file, and the internal-policy references are clearly signaled with no nested indirection.

3 / 3

Total

10

/

12

Passed

Description

100%

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 description with an explicit 'Use when' trigger, concrete deliverable types, and a clear niche. Minor internal jargon ('quest', 'render-inspect-revise') does not undermine the natural trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete items — 'polished milestone chart, paper-facing figure, appendix figure' plus the named 'render-inspect-revise pass' — rather than vague language.

3 / 3

Completeness

Explicit 'Use when…' trigger answers when, and the deliverable list answers what, satisfying both halves.

3 / 3

Trigger Term Quality

Natural figure-related terms users would say ('milestone chart', 'paper-facing figure', 'appendix figure') are well covered, despite some internal jargon ('quest').

3 / 3

Distinctiveness Conflict Risk

The figure-polishing niche with distinct surface-class triggers is clearly distinguishable and unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation15 / 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
ResearAI/DeepScientist
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.