generate-sitemap

Generate hierarchical site structure and navigation maps. Creates visual representations of information architecture and content relationships.

Quality

33%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/generate-sitemap/SKILL.md

Quality

Discovery

32%

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 identifies a clear domain (site structure and information architecture) and names some concrete outputs, but it lacks a 'Use when...' clause which significantly hurts completeness. It also misses common user-facing trigger terms like 'sitemap' and could be more specific about the concrete deliverables it produces.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for a sitemap, site structure, navigation hierarchy, or information architecture diagram.'

Include more natural trigger terms users would say, such as 'sitemap', 'site map', 'page hierarchy', 'IA diagram', 'website navigation', or 'content tree'.

List more specific concrete actions, e.g., 'Generate XML sitemaps, create hierarchical page trees, map navigation flows, visualize content taxonomies.'

Dimension	Reasoning	Score
Specificity	Names the domain (site structure, navigation maps) and some actions (generate, create visual representations), but lacks comprehensive specific actions like 'create sitemaps, define page hierarchies, map user flows, export wireframes'.	2 / 3
Completeness	Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'site structure', 'navigation maps', 'information architecture', and 'content relationships', but misses common user terms like 'sitemap', 'IA diagram', 'page hierarchy', 'site map', or 'website structure'.	2 / 3
Distinctiveness Conflict Risk	Somewhat specific to site architecture and navigation mapping, but terms like 'visual representations' and 'content relationships' could overlap with diagramming, wireframing, or general visualization skills.	2 / 3
	Total	7 / 12 Passed

Implementation

35%

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

This skill reads more like a product specification than an actionable skill for Claude. It describes what should happen at each step but lacks concrete implementation—no code for directory traversal, no templates for each output format, and no validation steps. The Mermaid example is helpful but insufficient to make the skill truly executable.

Suggestions

Add executable code examples for the core operations: directory traversal (e.g., using os.walk or glob), link extraction from markdown/HTML files, and output generation for each format.

Include concrete templates or generation code for each EXPORT_FORMAT (especially XML sitemap schema and SVG structure), not just a single Mermaid example.

Add validation steps: verify the traversal found expected index files, validate generated XML against sitemap schema, check for broken cross-references.

Remove the abstract descriptions ('Build a tree representation', 'Map internal links between nodes') and replace with specific implementation patterns Claude can directly execute.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary framing (e.g., 'This skill visualizes the information architecture to support user experience design and content organization') and the inputs section describes parameters in a way that's somewhat verbose, but overall it's not egregiously padded.	2 / 3
Actionability	The skill describes what to do at a high level ('Traverse the PATH', 'analyze links within content') but provides no executable code, no concrete commands, and no specific implementation details. The Mermaid example shows output format but not how to generate it. Steps like 'Build a tree representation' and 'Map internal links between nodes' are vague directions, not actionable instructions.	1 / 3
Workflow Clarity	Steps are listed in a logical sequence, but there are no validation checkpoints—no step to verify the traversal is complete, no validation of the generated output format, and no error handling or feedback loops for cases like broken links or inaccessible directories.	2 / 3
Progressive Disclosure	The content is reasonably structured with clear sections, but everything is inline in a single file. For a skill of this complexity with multiple export formats, the format-specific details (XML schema, Mermaid syntax patterns, SVG generation) could be split into referenced files. The Quick Reference section at the end adds little value.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: dandye/ai-runbooks
Commit: 086cbf6

Reviewed: 13 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.