generate-taxonomy

Develop hierarchical classification systems. Creates parent-child categorical structures for content organization.

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-taxonomy/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 reasonably specific domain—hierarchical classification systems—but is too terse and lacks explicit trigger guidance ('Use when...'). It would benefit from listing more concrete actions, including natural user-facing trigger terms, and clearly stating when Claude should select this skill over others.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'taxonomy,' 'category tree,' 'nested categories,' 'classification hierarchy,' or 'organize content into categories.'

List more concrete actions such as 'Designs taxonomies, builds category trees, assigns items to nested levels, and validates classification consistency.'

Include common natural language variations users might use, e.g., 'tagging system,' 'ontology,' 'folder structure,' or 'content categorization.'

Dimension	Reasoning	Score
Specificity	Names the domain (hierarchical classification systems) and describes some actions (creates parent-child categorical structures), but lacks multiple concrete actions—doesn't specify formats, outputs, or detailed operations beyond 'creates structures.'	2 / 3
Completeness	Describes what it does (creates hierarchical classification systems) 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 the 'what' is also somewhat thin, warranting a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'hierarchical,' 'classification,' 'parent-child,' and 'categorical structures,' but misses common natural language variations users might say such as 'taxonomy,' 'category tree,' 'nested categories,' 'tagging system,' or 'ontology.'	2 / 3
Distinctiveness Conflict Risk	The focus on hierarchical classification and parent-child structures is somewhat specific, but 'content organization' is broad enough to overlap with skills related to tagging, information architecture, or general content management.	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 provides a reasonable high-level framework for taxonomy generation but lacks the concrete, actionable guidance needed for Claude to execute it effectively. There are no code examples, no sample taxonomy outputs, no specific commands or tools, and no validation steps. The content describes what to do conceptually but not how to do it.

Suggestions

Add a concrete example of a taxonomy output (e.g., a sample YAML or markdown taxonomy tree) so Claude knows exactly what format to produce.

Provide actionable instructions for content analysis—specify tools, commands, or concrete techniques for clustering and keyword extraction rather than abstract descriptions.

Include a validation step (e.g., check for orphan categories, verify depth limits, ensure mutual exclusivity) to create a feedback loop in the workflow.

Add a concrete example of a faceted taxonomy output alongside the hierarchical one to clarify the difference in practice.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes some unnecessary framing (e.g., 'This skill creates parent-child categorical structures to organize content effectively' restates the title). The Quick Reference section adds little value. Could be tighter overall.	2 / 3
Actionability	The skill is entirely abstract and descriptive—no concrete code, commands, file formats, or executable examples. Steps like 'Cluster documents by similarity' and 'Extract common tags and keywords' give no actionable guidance on how to actually perform these operations. No example taxonomy output is provided.	1 / 3
Workflow Clarity	Steps are listed in a logical sequence, but there are no validation checkpoints, no feedback loops for error recovery, and no concrete criteria for when a step is 'done.' The workflow reads more like a high-level process description than an actionable guide.	2 / 3
Progressive Disclosure	The content is organized into clear sections, which is good. However, there are no references to external files for detailed guidance (e.g., example taxonomies, YAML schemas, card sorting templates), and the Required Outputs section could benefit from a concrete example or link to a template.	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.