academic-plotting

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

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-structured skill with strong progressive disclosure and clear workflows. Its main weakness is conciseness: the inline body is heavy with four full style blocks and light editorializing that could be trimmed or moved to references.

Suggestions

Move the four full visual-style blocks (Style A–D) into references/diagram-generation.md, keeping only a one-line style summary plus selection guidance inline, to cut body length.

Trim editorializing such as "this is the single biggest factor in whether the figure looks professional or generic" and "reproducibility is critical" — state the rules directly instead.

Condense the inline generation script template to the essential structure (API key check + 3-attempt loop) and defer the full template to the diagram reference file.

Dimension	Reasoning	Score
Conciseness	The body is competent and free of basic-concept explanations, but at ~470 lines it carries four full inline visual-style blocks plus minor editorializing ("this is the single biggest factor", "reproducibility is critical") that could be tightened or deferred, so it sits at mostly-efficient rather than lean.	2 / 3
Actionability	Provides a fully executable Gemini generation script with API-key handling and a 3-attempt loop, a complete matplotlib rcParams template, and several copy-paste-ready chart patterns (line, grouped bar, heatmap, horizontal bar).	3 / 3
Workflow Clarity	Both workflows are clearly sequenced with explicit checklists, a numbered extraction process, a generate-3-then-review/select feedback loop, and a Common Issues troubleshooting table for error recovery.	3 / 3
Progressive Disclosure	The body is an overview that clearly signals three real, one-level-deep references (diagram-generation.md, data-visualization.md, style-guide.md, all verified to exist) carrying the full prompt examples, pattern library, and venue details.	3 / 3
	Total	11 / 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, third-person description that concretely names its two workflows and provides an explicit trigger. It is information-dense without padding and clearly distinct from adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "extracts system components and relationships to generate architecture diagrams via Gemini" and "auto-selects chart type and generates data-driven figures via matplotlib/seaborn" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what it does (publication figures via Gemini diagrams and matplotlib/seaborn data charts) and when to use it with an explicit "Use when..." clause, satisfying both halves.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "figures", "ML papers", "conference paper", "architecture diagrams", "chart" — with a genuine "Use when creating any figure for a conference paper" trigger; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (ML/conference-paper figures, AI diagram generation + data charts) unlikely to conflict with generic plotting or document skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 20-ml-paper-writing/academic-plotting/SKILL.md
Commit: 773a529

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

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.