code-to-diagram

Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a module diagram from source code.

Quality

86%

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%

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

A solid, highly actionable tool skill body with concrete commands and good file structure. Its main weaknesses are mild verbosity (a Use Cases marketing section and intro restatement) and the absence of validation checkpoints in the How-It-Works workflow.

Suggestions

Remove or condense the 'Use Cases' section — those benefit statements are marketing fluff that does not help execute the task, and trimming them would lift conciseness.

Add an explicit validation checkpoint in 'How It Works', e.g. checking that mmdc is installed before the Render step and falling back to Mermaid-only output if absent, to give the workflow a feedback loop.

Drop the intro paragraph that restates the frontmatter description; let the frontmatter carry the summary and start the body at 'Usage' to avoid redundant tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (direct bash commands, a compact parameter table, specific per-language parse notes), but the intro restates the frontmatter description and the 'Use Cases' section is user-benefit marketing ('Quickly understand the module structure of an unfamiliar project') that does not earn its place; not a 3 because of this tightening opportunity, not a 1 because no generic concepts Claude already knows are explained.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands ('python3 scripts/analyze_codebase.py /path/to/project --type architecture', '--format svg', '--json') plus a concrete parameter table; not a 2 because the examples are real and complete rather than pseudocode or abstract.	3 / 3
Workflow Clarity	'How It Works' gives a clear numbered sequence (Scan, Parse, Resolve, Generate, Render), but there are no validation checkpoints or error-recovery feedback loops (e.g., verifying mmdc is present before SVG render); not a 1 because the sequence is explicit, not a 3 because checkpoints are missing.	2 / 3
Progressive Disclosure	A single bundle file (scripts/analyze_codebase.py) is referenced one level deep and clearly signaled via the usage commands and How-It-Works section, with the ~95-line overview appropriately kept inline under well-organized section headers; not a 2 because navigation is clear and nothing is over-split or deeply nested.	3 / 3
	Total	10 / 12 Passed

Description

100%

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: concrete capabilities, an explicit trigger clause covering natural user phrasing, and a distinctive niche with low conflict risk. Voice is consistently third person, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts', 'Uses AST parsing to map import dependencies', 'outputting Mermaid or SVG files' — matching the multiple-specific-actions anchor; not a 2 because coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both 'what' ('Analyze codebases... generate architecture diagrams, flowcharts, and org charts') and 'when' ('Triggered when users ask to...'), with an explicit trigger clause; not a 2 because the when is stated directly rather than merely implied.	3 / 3
Trigger Term Quality	The 'Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a module diagram' clause gives good coverage of natural phrases a user would actually say; not a 2 because it spans several common variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	A clear niche — AST import-dependency parsing for named languages producing specific diagram types — with distinct triggers makes it unlikely to fire for unrelated skills; not a 2 because the scope is narrow and specific rather than overlapping.	3 / 3
	Total	12 / 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: zebbern/claude-code-guide
Path: skills/code-to-diagram/SKILL.md
Commit: af7d491

Reviewed: about 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.