generate-taxonomy

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

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/generate-taxonomy/SKILL.md

Quality

Content

52%Weight 40%Scale 1-5

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

The skill is concise and well-structured for a simple instruction-only task, but its guidance is abstract and lacks executable specifics or validation steps. It tells Claude what to produce but not concretely how.

Suggestions

Replace abstract hints with concrete methods (e.g., specific clustering/keyword-extraction techniques, output schema examples for TAXONOMY_DEFINITION in markdown/YAML).

Add a validation/review checkpoint in the workflow (e.g., verify coverage of all source content, check for orphan terms, confirm hierarchy depth before finalizing).

Provide at least one concrete output example so the deliverable format is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean (~45 lines), uses brief bullets, and avoids explaining what a taxonomy or hierarchy is — it assumes Claude's competence; only mild repetition of the opening purpose statement in 'Quick Reference' keeps it from a 5.	4 / 5
Actionability	It gives only high-level hints ('Cluster documents by similarity', 'Extract common tags and keywords', 'Output the defined taxonomy') with no concrete commands, code, methods, or specific tooling — fitting 'minimal concrete guidance; high-level hints but missing the specific steps to execute'.	2 / 5
Workflow Clarity	Four numbered steps are sequenced, but the workflow produces a taxonomy definition (a batch/structural output) with no validation, review, or user-testing checkpoint before output; per the feedback-loop guidance this keeps it at the cap of 3 rather than higher.	3 / 5
Progressive Disclosure	For a simple under-50-line skill with no external references, the content is well-organized into clear sections (Inputs, Workflow, Required Outputs, Quick Reference) and nothing is buried; minor lack of any referenced detail files keeps it just below 5.	4 / 5
	Total	13 / 20 Passed

Description

43%Weight 40%Scale 1-5

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 states a clear purpose but is generic, uses no natural user-facing trigger terms, and omits any 'Use when...' guidance. It reads as a domain label rather than a discoverable trigger phrase.

Suggestions

Add a 'Use when...' clause naming natural triggers (e.g., 'Use when organizing content into categories, building a taxonomy, or structuring a knowledge base for retrieval').

Add concrete action verbs beyond 'Develop'/'Creates' — e.g., extract terms, design hierarchies, validate via card sorting.

Include natural keywords users say ('taxonomy', 'categories', 'tagging', 'content hierarchy') rather than only technical phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain ('hierarchical classification systems') and one concrete action ('Creates parent-child categorical structures'), matching the score-3 anchor of 'domain and 1-2 concrete actions, but not comprehensive'; it lacks the multiple distinct actions (e.g., extract, fill, merge) seen at 4-5.	3 / 5
Completeness	It clearly answers 'what' (develop/create hierarchical classification structures) but provides no 'Use when...' trigger clause; per the guidelines a missing explicit trigger caps completeness at 3, so it cannot reach 4 even though the 'what' is clear.	3 / 5
Trigger Term Quality	The phrasing uses generic technical terms ('hierarchical classification systems', 'parent-child categorical structures') and no natural user-facing keywords like 'taxonomy', 'categories', 'tagging', or 'content organization' that a user would actually say; this fits 'one or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	The niche (taxonomy/classification) is somewhat specific but the generic phrasing ('classification systems', 'content organization') could overlap with related knowledge-management or tagging skills, fitting 'somewhat specific but could still overlap with similar skills'.	3 / 5
	Total	11 / 20 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: dandye/ai-runbooks
Path: skills/generate-taxonomy/SKILL.md
Commit: 72a6863

Reviewed: 6 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.