diagram-generator

generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. use for flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, class diagrams, architecture/c4-style diagrams, dependency graphs, gantt charts, mind maps, user journeys, sankey-style flows, org charts, network graphs, and other visual models. supports mermaid by default, graphviz dot for complex graph layout, plantuml for uml-heavy engineering diagrams, and svg output when direct markup is more reliable.

Quality

81%

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

72%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.

Highly actionable and well-structured with a real reference and executable rendering commands, but it loses points on conciseness (meta/process padding) and workflow clarity (implicit rather than explicit render error-recovery loop).

Suggestions

Remove or trim the meta/process sections ('ACTION REQUIRED', '路由上下文', '任务完成自检') to cut tokens that do not aid diagram generation.

Make the render validation loop explicit: after running render_diagram.py, if it fails, fix the source and re-run until the output file exists and is non-empty.

Replace 'validate the syntax mentally' with a concrete check (e.g., run render_diagram.py in a check/dry mode) so validation is verifiable rather than subjective.

Dimension	Reasoning	Score
Conciseness	The core (decision table, per-language rules, rendering commands) is lean and assumes Claude's competence, but meta/process sections like 'ACTION REQUIRED', '按需自举', '路由上下文', and the redundant '任务完成自检' add overhead that does not earn its place.	2 / 3
Actionability	Provides concrete, executable guidance — rendering commands ('python ... render_diagram.py input.mmd --format svg --out output.svg') and specific syntax rules ('flowchart TD', 'decision{Condition?}', '@startuml/@enduml', 'digraph G' with 'rankdir=LR').	3 / 3
Workflow Clarity	A clear 6-step default workflow plus a validation checklist exists, but the main-path validation is weak ('validate the syntax mentally') and the render-fails -> fix -> re-render feedback loop is only implied rather than explicit.	2 / 3
Progressive Disclosure	The body is a self-contained overview with one clearly signaled, one-level-deep reference ('Consult references/diagram-patterns.md for compact templates') pointing to real files, plus scripts referenced by path.	3 / 3
	Total	10 / 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.

A strong, specific description with explicit 'use for' triggers and broad natural-language terms. The only weakness is imperative voice instead of the recommended third-person voice, which costs a specificity point.

Suggestions

Rewrite the description in third person ('Generates, refines, validates, and renders diagrams...') to match the rubric's voice guideline.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source'), which meets the level-3 anchor, but the voice is imperative rather than the third-person form ('Generates/Supports') the rubric guideline recommends, so a one-point specificity penalty applies.	2 / 3
Completeness	Explicitly answers both 'what' (generate/refine/validate/render diagrams) and 'when' via the 'use for flowcharts, swimlanes, ...' trigger clause, matching the level-3 anchor.	3 / 3
Trigger Term Quality	Covers many natural terms users actually say — 'flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, ... gantt charts, mind maps, user journeys' — with broad, not missing, common variations.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche (diagram generation) with specific diagram-type and language triggers, making it unlikely to fire for unrelated skills.	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: zhaoxuya520/reverse-skill
Path: skills/diagram-generator/SKILL.md
Commit: 6aa1362

Reviewed: 7 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.