Tessl • The management layer for AI agent skills

SkillPublic

ia

Evaluate and improve how information is organized for findability. Use when the user asks to "organize this", "restructure docs", "improve navigation", "where should this go", "review file structure", or when documentation grows beyond a single page.

Quality

85%

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

78%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.

A well-structured, token-efficient IA review skill that defers framework depth to real reference files and supplies actionable heuristics plus an output template. The main gaps are a missing worked example and an explicit verification step in the review workflow.

Suggestions

Add a short worked example showing a before/after IA review to lift actionability from concrete guidance to fully exemplified.

Insert an explicit 'verify recommendations' checkpoint (e.g. re-check the four systems against the proposed structure) at the end of the Review Workflow.

Tighten the prose restatements of LATCH and Diataxis definitions, which Claude can derive, to push conciseness to lean.

Dimension	Reasoning	Score
Conciseness	Dense, table-driven working summaries of specialized IA frameworks (LATCH, Brown's principles, Diataxis) that mostly earn their tokens rather than re-explaining basics; not a 5 because a few prose passages restate framework definitions Claude could derive.	4 / 5
Actionability	Provides concrete heuristics (five taxonomy test questions, a placement decision tree, and a copy-paste output template) that are directly usable; not a 5 because there is no worked example of a completed review illustrating the common case.	4 / 5
Workflow Clarity	The Review Workflow is clearly sequenced (Map → Evaluate → Recommend) with structured sub-steps and an output schema; not a 5 because it lacks an explicit verify/review checkpoint on the recommendations, though the non-destructive nature means the destructive-cap does not apply.	4 / 5
Progressive Disclosure	Clear overview body with well-signaled, verified one-level-deep references (references/rosenfeld-morville.md and references/organizing-principles.md both exist), appropriately splitting detailed framework treatment from the working summary.	5 / 5
	Total	17 / 20 Passed

Description

86%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.

A strong description that clearly states what the skill does and gives rich, natural trigger phrases for when to use it. Its main weakness is specificity — only two generic verbs (evaluate, improve) rather than a fuller enumeration of concrete actions.

Suggestions

Expand the 'what' clause beyond 'Evaluate and improve' to list concrete actions such as auditing organization schemes, labeling, navigation, and recommending restructures.

Add a domain noun earlier (e.g. 'information architecture') so the niche is named explicitly rather than implied via 'findability'.

Dimension	Reasoning	Score
Specificity	Names the domain ('how information is organized for findability') and two concrete actions ('Evaluate and improve'), but the actions are generic rather than a list of several specific operations, matching the 'names domain and 1-2 concrete actions' anchor; not a 4 because it lacks multiple distinct specific actions.	3 / 5
Completeness	Explicitly answers both 'what' ('Evaluate and improve how information is organized for findability') and 'when' ('Use when the user asks to...') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Quotes several natural phrases users would actually say — 'organize this', 'restructure docs', 'improve navigation', 'where should this go', 'review file structure' — giving comprehensive coverage of natural trigger language including varied phrasings.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (information organization for findability) with distinct triggers and minimal conflict risk; not a 5 because the See Also section reveals closely related skills (wayfinding, naming, lexicon) creating minor overlap risk.	4 / 5
	Total	17 / 20 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: tslateman/duet
Path: skills/ia/SKILL.md
Revision: 504b3b1

Reviewed: 1 month ago

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.

ia

Table of Contents

Is this your skill?