figure-style

Publication-grade figure correctness and legibility rules. Load before drawing any plot and call `apply_figure_style()` — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded data never enters summaries), label economy (floor and ceiling), colour threading, chart-choice-by-data-shape, layout, and a render-then-verify QA loop (bbox collision + per-panel perceptual check). Ships helpers: focal_palette, bar_with_points, strip_with_median, end_of_line_labels, panel_letter, set_frame, panel_crops. For multi-panel figures load `figure-composer`; for whole-paper figure arc load `paper-narrative`.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/claude-science/figure-style/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a strong render-then-verify workflow and concrete code, but it is a monolithic wall of rules that could be tightened, and it names helpers and sibling skills without providing or linking to the corresponding bundle files.

Suggestions

Ship the named helpers as actual scripts in ./scripts/ (or a reference module) and link to them from the body, so the cited functions (focal_palette, bar_with_points, panel_crops, etc.) exist and are discoverable.

Move the per-chart-family detail (§6) or the colour/typography guidance into a reference file and keep SKILL.md as a lean overview with one-level-deep links, improving both conciseness and progressive disclosure.

Tighten the rule prose — several rules explain rationale that an expert reader already infers — to raise token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of concepts Claude already knows, but the rule catalogue is long and frequently elaborates beyond what is needed (e.g., verbose rationale on label economy and chart-family selection), so it is mostly efficient yet could be tightened.	2 / 3
Actionability	It provides concrete, executable guidance throughout — `ax.margins(0.04)`, `apply_figure_style(sizes=(8,7,6))`, a complete bbox-overlap verification snippet, and a panel-crop perceptual-check recipe — copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	§9 lays out a clear render-then-verify sequence with an explicit geometric validation step, a follow-on perceptual check, and a fix-and-re-save feedback loop ('Fix (move, shorten, stagger) and re-save until clean'), matching the anchor with explicit validation checkpoints and error recovery.	3 / 3
Progressive Disclosure	The body is a single self-contained checklist with clear internal sectioning, but no references/, scripts/, or assets/ bundle files exist despite the description and body naming helpers (focal_palette, bar_with_points, panel_crops, etc.) and sibling skills (figure-composer, paper-narrative); helper implementations are referenced but not provided, and navigation to those details is not signaled.	2 / 3
	Total	10 / 12 Passed

Description

65%

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 specific, concrete, and well-differentiated with explicit sibling-skill boundaries, but it lacks a clear 'Use when...' trigger clause and natural user-facing keywords, which cap trigger-term quality and completeness at 2.

Suggestions

Add an explicit 'Use when...' clause with natural triggers (e.g., 'Use when creating publication-quality matplotlib figures, preparing panel plots for a paper, or fixing figure legibility/correctness').

Surface common user phrasings — 'plot', 'matplotlib figure', 'panel', 'figure for a paper' — so the skill triggers on the words users actually say.

Trim the helper-function catalogue from the description into the body; it inflates length without aiding trigger matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — a role-mapped font-size ladder, outward ticks, frameless legends, 300-dpi output, a render-then-verify QA loop (bbox collision + per-panel perceptual check) — plus named helper functions, matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers 'what does this do' (rules + helpers), but the 'when' is only implied via 'Load before drawing any plot' rather than an explicit 'Use when...' clause, which the guidelines say caps completeness at 2.	2 / 3
Trigger Term Quality	It names concrete objects (plots, panels, heatmap, scatters) and helper functions, but the natural user-facing triggers are largely absent; a user would rarely say 'apply_figure_style' or 'chart-choice-by-data-shape' when reaching for the skill, and common phrasings like 'make a figure', 'plot', 'matplotlib' are under-covered.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply drawn — publication-grade figure correctness/legibility with a checklist framing — and it explicitly scopes away siblings (figure-composer for multi-panel, paper-narrative for whole-paper arc), so it is unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/claude-science/figure-style/SKILL.md
Commit: f618458

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.