figures-diagram

Use when creating flowcharts, architecture diagrams, or conceptual diagrams - generates prompts for image AI

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

87%Weight 40%Scale 1-3

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

The body is well-structured, lean, and highly actionable, offering ready-to-use templates, palettes, and tool guidance without over-explaining. Its single notable gap is the absence of a validation/verification checkpoint in the generation-and-iteration workflow.

Suggestions

Add an explicit validation checkpoint to the dialogue flow, e.g. after delivering the prompt ask the user to paste back the generated image so the skill can verify it matches the requested structure before iterating.

Convert the checklist into a numbered, gated sequence (collect info → draft prompt → confirm with user → deliver) so the workflow order and stopping points are unambiguous.

Document a small feedback loop for common failure cases (e.g. 'if labels are unreadable, regenerate with larger font') to turn the implicit iteration into an explicit validate→fix→retry step.

Dimension	Reasoning	Score
Conciseness	The body is lean reference material — templates, hex palettes, and tool tables — with no padding explaining concepts Claude already knows; every section earns its tokens. Not a 2 because it avoids unnecessary explanation and assumes competence throughout.	3 / 3
Actionability	It provides concrete fill-in-the-blank prompt templates (sections 3.1–3.3) with exact hex color codes, named tools, and a ready-to-use dialogue script — copy-paste ready guidance. Not a 2 because the templates are specific and executable rather than pseudocode.	3 / 3
Workflow Clarity	The checklist (section 二) and dialogue flow (section 六) sequence the process, but there is no validation or verification checkpoint for the generate-then-iterate loop, leaving checkpoints implicit. Capped at 2 per the destructive/feedback-loop guideline; not a 3 because explicit validation steps are missing, and not a 1 because the sequence is clearly listed.	2 / 3
Progressive Disclosure	It is a single-file skill with no bundle files, yet it is organized into clear labeled sections (适用场景, Checklist, templates, tools, palette, dialogue), satisfying the simple-skill allowance. Not a 2 because organization is clear with no nested or dangling references.	3 / 3
	Total	11 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 concise, third-person, and clearly pairs an explicit 'Use when...' trigger with a concrete action and natural trigger terms. Its main weakness is specificity, since it surfaces only one of the skill's several actual capabilities.

Suggestions

Expand the description to enumerate the concrete actions the skill performs, e.g. 'generates and tunes academic-grade drawing prompts and recommends an image-AI tool', to lift specificity.

Add common natural variations users might say (e.g. 'concept maps', 'schematics', 'block diagrams') to broaden trigger coverage.

Clarify the distinction from data-chart skills directly in the description (e.g. 'not for line/bar/pie charts') to further reduce conflict risk.

Dimension	Reasoning	Score
Specificity	The phrase "generates prompts for image AI" names one concrete action and the diagram domain, but it is not comprehensive — it omits the styling/tuning and tool-recommendation actions the body actually performs. Not a 1 because a concrete action is named; not a 3 because only a single thin action is listed rather than multiple specific ones.	2 / 3
Completeness	It explicitly answers both what ("generates prompts for image AI") and when ("Use when creating flowcharts, architecture diagrams, or conceptual diagrams") with an explicit trigger clause. Not a 2 because the trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	"flowcharts, architecture diagrams, or conceptual diagrams" are natural terms users would actually say when requesting these visuals, giving good coverage of common variations. Not below 3 because the listed terms are exactly the kind a user would verbalize.	3 / 3
Distinctiveness Conflict Risk	The trigger terms (flowcharts/architecture/conceptual diagrams) form a distinct niche that is unlikely to fire for data-chart skills, and the body reinforces this by redirecting data charts to figures-python. Not a 2 because the triggers are specific and clearly bounded.	3 / 3
	Total	11 / 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: Norman-bury/research-writing-skill
Path: skills/figures-diagram/SKILL.md
Commit: 6f79595

Reviewed: 10 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.