figure-legend-gen

Generate standardized figure legends for scientific figures and charts; use when preparing publication-ready legends that summarize design, variables, sample size, and key statistical notes.

Quality

55%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/figure-legend-gen/SKILL.md

Quality

Content

35%

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

The body delivers solid actionable usage content (commands, parameters, chart types, legend structure) but is weighed down by extensive generic governance boilerplate and minor copy-paste errors. Trimming the boilerplate and fixing the example flags would materially raise quality.

Suggestions

Remove or externalize generic governance sections (Security Checklist, Risk Assessment, Lifecycle, Evaluation Criteria, Response Template, Output Contract) so SKILL.md stays a lean overview.

Fix the malformed example flag `--image.png` to `--input image.png` and drop the duplicate `--help`/`py_compile` lines.

Turn the Workflow's generic validation step into an explicit validate-fix-retry checkpoint tied to `python -m py_compile scripts/main.py`.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic governance boilerplate Claude already knows (Security Checklist, Risk Assessment table, Lifecycle with a hard-coded 'Next Review Date: 2026-03-06', Evaluation Criteria, Response Template, Output Contract), and repeats `python -m py_compile scripts/main.py` and `--help` verbatim, crowding the context window with low-value tokens.	1 / 3
Actionability	It provides concrete, mostly copy-paste-ready guidance (usage block, Parameters table, chart-type table, examples), but the example `python scripts/main.py --image.png --type scatter --language zh` uses a malformed flag (`--image.png` instead of `--input`), breaking copy-paste readiness.	2 / 3
Workflow Clarity	A 5-step Workflow and a Quick Validation section give a discernible sequence with some validation, but the checkpoints are generic ('Validate that the request matches the documented scope') and error handling is a fallback rather than an explicit validate-fix-retry loop.	2 / 3
Progressive Disclosure	It signals real one-level-deep references (`references/legend_templates.md`, `references/academic_style_guide.md`, both present) and `scripts/main.py`, but the SKILL.md itself is a long monolithic document with large inline governance sections that would be better split into separate reference files.	2 / 3
	Total	7 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-formed with an explicit use-when trigger and a clear, distinctive niche. Its main weakness is trigger-term breadth and listing only one primary action rather than multiple concrete capabilities.

Suggestions

Add common trigger synonyms such as 'figure caption' or 'figure label' so the description matches more natural user phrasings.

List a second concrete action (e.g., 'extract chart metadata and assemble structured legend text') to lift specificity toward multiple distinct capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain ('scientific figures and charts') and one concrete action ('Generate standardized figure legends') plus output attributes (design, variables, sample size, statistical notes), but lists a single primary action rather than multiple distinct concrete actions as the level-3 anchor requires.	2 / 3
Completeness	It clearly states what the skill does ('Generate standardized figure legends...') and gives an explicit 'use when' trigger clause ('use when preparing publication-ready legends...'), satisfying both what and when.	3 / 3
Trigger Term Quality	It includes relevant natural terms ('figure legends', 'scientific figures', 'charts', 'publication-ready legends'), but omits common variations a user might say such as 'figure caption', 'figure label', or 'caption'.	2 / 3
Distinctiveness Conflict Risk	The niche is specific (publication-ready legends for scientific figures/charts) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 days 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.