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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/ia/SKILL.md

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 tight, well-organized IA skill that uses progressive disclosure cleanly: the body is an actionable working summary and the single reference file holds the full theoretical treatment. Scores are held at 4 only by minor conciseness trim and the absence of an explicit review-validation loop.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and IA-specific — taxonomy heuristics, the Diataxis table, thresholded patterns, and a decision tree all earn their tokens. It is a 4 rather than 5 because a few lines restate concepts Claude already knows (e.g. the opening "Information architecture is the structural design of shared information environments") that could be trimmed.	4 / 5
Actionability	As an instruction-only skill it supplies concrete, specific guidance: a five-question taxonomy diagnostic, a four-system evaluation matrix, a structured output template, a placement decision tree, and four named patterns with numeric thresholds. It is a 4 rather than 5 because the evaluation steps are framed as open questions rather than unambiguous commands, leaving minor execution gaps.	4 / 5
Workflow Clarity	The Review Workflow is a clear three-step sequence (Map → Evaluate → Recommend) anchored by an output template that doubles as a completeness check. It is a 4 rather than 5 because there is no explicit validation/feedback loop step (e.g. "re-check that every orphan now has a path"); the destructive/batch cap does not apply since this is an analysis-only skill.	4 / 5
Progressive Disclosure	SKILL.md is a working overview that signals a single one-level-deep reference ("See `references/rosenfeld-morville.md` for the core systems"; "carries the full treatment ... this is the working summary"), and that file exists in the bundle. Content is appropriately split with easy navigation, matching the 5 anchor; it is not a 4 because the reference is exactly one level deep and unambiguously signaled.	5 / 5
	Total	17 / 20 Passed

Description

78%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 well-constructed description that clearly states what the skill does and when to use it, with a strong set of natural trigger phrases. Its main weakness is the somewhat abstract action vocabulary, which keeps specificity at the midpoint.

Suggestions

Replace the generic verbs in the "what" clause with concrete capabilities, e.g. "Audit a project's organization, labeling, navigation, and search; recommend restructuring and placement decisions for content."

Add a couple more natural synonyms to the trigger list (e.g. "reorganize the docs", "sort out the wiki") to push trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	"Evaluate and improve how information is organized for findability" names the domain and two fairly abstract actions (evaluate, improve) but, unlike a 5-anchor example, does not enumerate concrete capabilities. It sits at the 3 anchor ("names domain and 1-2 concrete actions, but not comprehensive") rather than 4 because the actions are generic verbs rather than specific moves like "audit taxonomy" or "restructure navigation."	3 / 5
Completeness	It 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 5 anchor pattern. It is not a 4 because the "when" is not merely implied or partial — it lists five explicit trigger phrases plus a growth condition.	5 / 5
Trigger Term Quality	It lists several natural user phrases ("organize this", "restructure docs", "improve navigation", "where should this go", "review file structure") plus a behavioral trigger, giving good keyword coverage. It falls short of 5 because common synonyms (e.g. "tidy up the docs", "sort out the wiki", "reorganize") are absent, and the 5 anchor's file-extension completeness does not apply to this conceptual skill.	4 / 5
Distinctiveness Conflict Risk	The IA niche and its findability-oriented triggers are mostly distinct from other skills. It only reaches 4 rather than 5 because the body's own "See Also" acknowledges adjacent skills (/naming, /design, /prose) that "organize this" or "restructure docs" could conceivably also match.	4 / 5
	Total	16 / 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
Commit: 5647baf

Reviewed: 3 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.