figure-legend-writer

Writes complete, publication-grade figure legends that can stand on their own. Use when writing or revising figure legends for any scientific figure — bar charts, line graphs, scatter plots, box plots, heatmaps, survival curves, flow cytometry plots, western blots, microscopy images, or schematic diagrams. Also triggers on "write a figure legend for", "help me describe this figure", "my figure needs a legend", "write Figure 1 legend", or "what should a figure legend include".

Quality

88%

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

82%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.

Well-structured, actionable instruction skill with a clear workflow and verification checklist. The main gaps are the absence of an explicit fix-retry feedback loop and an unreferenced bundle script (main.py).

Suggestions

Add an explicit validate-and-revise feedback loop after the Step 3 checklist (e.g., 'if any checkbox fails, revise the legend and re-run the checklist') to reach full workflow_clarity.

Reference scripts/main.py from the body (e.g., note that an automated generator script is available in scripts/) so every bundle file is navigable and discoverable.

Trim the blockquote on line 30 and any restating prose to tighten conciseness toward the lean anchor-5 bar.

Dimension	Reasoning	Score
Conciseness	The body is dense and task-focused with little padding and no explanation of concepts Claude already knows, but a few elements (the blockquote restating purpose, some explanatory prose) could be trimmed, keeping it just below the anchor-5 'every token earns its place' bar.	4 / 5
Actionability	As an instruction-only writing skill it provides copy-paste-ready templates with explicit placeholders, a per-figure-type element table, and a concrete legend structure block, fully covering common cases per the anchor-5 standard.	5 / 5
Workflow Clarity	A clear three-step sequence (Identify, Write, Quality Check) with a verification checklist is present, but there is no explicit validate-fix-retry feedback loop, so it falls short of the anchor-5 'feedback loops for error recovery' criterion; this is not a destructive/batch skill so the cap-3 rule does not apply.	4 / 5
Progressive Disclosure	Two reference files are clearly signaled with one-level-deep links at the end and both exist, but the bundled scripts/main.py is never referenced or navigated from the body, a minor organization gap that holds it below anchor-5.	4 / 5
	Total	17 / 20 Passed

Description

95%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 description: it states the capability, scope, and explicit natural-language triggers clearly and concisely. The only mild gap is that the distinct actions (write/revise) are fewer than the broad domain list implies.

Dimension	Reasoning	Score
Specificity	Names a clear action ('Writes complete, publication-grade figure legends that can stand on their own' and 'writing or revising figure legends') with extensive domain enumeration, but the distinct action set is narrower than the anchor-5 example's multi-action coverage, so it sits below 5.	4 / 5
Completeness	It explicitly answers 'what' (writes publication-grade, self-contained legends) and 'when' (a 'Use when...' clause plus an 'Also triggers on...' list of concrete phrases), matching the anchor-5 example structure exactly.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases are given verbatim ('write a figure legend for', 'help me describe this figure', 'my figure needs a legend', 'write Figure 1 legend', 'what should a figure legend include') alongside broad figure-type vocabulary, matching the anchor-5 expectation of synonyms and common phrasings.	5 / 5
Distinctiveness Conflict Risk	The niche is narrow and specific (scientific figure legends) with figure-type-specific triggers, making overlap with other skills minimal and matching the anchor-5 'clear niche with distinct triggers' description.	5 / 5
	Total	19 / 20 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: aipoch/medical-research-skills
Path: awesome-med-research-skills/Academic Writing/figure-legend-writer/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.