publication-chart-skill

This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants an existing scientific figure/table reviewed and upgraded.

Quality

85%

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

70%

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

Well-structured workflow with strong sequencing, validation, and a clean reference hierarchy, but it is held back by inline redundancy and abstract (rather than executable) figure/table generation examples in the body.

Suggestions

Consolidate the duplicated dependency/install guidance — step 0 and the 'Missing dependency behavior' section restate the same probe-and-install flow; reference it once and keep the rest lean.

Add one complete runnable pubfig and one pubtab snippet inline (or clearly point to the recipes as the copy-paste source) so the core artifact step is executable, not just descriptive.

Trim 'Output style rules' and 'Recommended response shape' where they restate steps 5–7 to reduce token cost without losing the workflow.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but repeats material across step 0, the 'Missing dependency behavior' section, and 'Output style rules' (install/probe behavior and route rules stated multiple times), so it could be tightened rather than earning the lean level 3.	2 / 3
Actionability	Environment probe and install commands are copy-paste ready, but the core artifact-generation guidance is abstract in-body ('one pubfig call + one save_figure(...)') with no complete runnable snippet, leaving the main deliverable incomplete per the level 2 anchor.	2 / 3
Workflow Clarity	A clearly numbered 0–7 sequence with explicit validation checkpoints (availability probe, re-probe after install) and a QA checklist plus install→re-check→degrade feedback loop matches the level 3 anchor.	3 / 3
Progressive Disclosure	The Resources section signals one-level-deep references with per-file descriptions, and every referenced path (references/.md, references/source-guides/.md, scripts/ensure_publication_tooling.py) exists, giving clear navigation off a concise overview.	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, third-person description with explicit trigger guidance and a comprehensive set of concrete capabilities. Its only weakness is verbosity — one long run-on sentence chaining many 'or wants' clauses — but this does not reduce any dimension below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'publication-quality scientific figure or table', 'choosing the right chart for results', 'Excel sheet turned into publication-ready LaTeX', 'reviewed and upgraded' — matching the multi-action anchor rather than the domain-only level 2.	3 / 3
Completeness	'This skill should be used when the user asks for...' gives an explicit when clause and the enumerated list gives the what, satisfying both halves; the Use-when guidance is present so it is not capped at 2.	3 / 3
Trigger Term Quality	Natural phrasings a user would say dominate ('choose the right chart', 'paper-ready', 'Excel sheet...LaTeX', 'reviewed and upgraded'); the single 'pubfig or pubtab workflow' clause is jargon but does not undermine overall coverage, so it clears level 2.	3 / 3
Distinctiveness Conflict Risk	The publication figure/table niche with tool-specific triggers is clearly distinct from generic data or document skills and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 6 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/publication-chart-skill/SKILL.md
Commit: 2f7766f

Reviewed: about 13 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.