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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A well-organized, token-efficient body that uses progressive disclosure effectively and assumes Claude's intelligence. The main gap is workflow clarity: the review steps are sequenced but lack explicit validation checkpoints, and the instruction-only guidance is concrete yet not maximally executable.

Suggestions

Add explicit validation/checkpoint steps to the Review Workflow (e.g. after mapping the current state, confirm orphan/duplicate/gap lists are complete before evaluating systems) to push workflow clarity toward the anchor with feedback loops.

Include one short worked example of a completed 'IA Review' output so the output template is demonstrated end-to-end rather than only schematized.

Tie the Diataxis and Four-Systems evaluations to concrete go/no-go decisions in the Recommend step, so the workflow closes the loop from evaluation to prescribed action.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it names Rosenfeld/Morville and Diataxis without re-explaining them, uses terse heuristics (e.g. 'README exceeds ~200 lines', 'three clicks'), and every section earns its place with no concept padding.	3 / 3
Actionability	Concrete heuristics, a Diataxis classification table, a placement decision tree, and a copy-paste output template provide specific guidance, but the skill is instruction-only with no executable commands or worked examples, so it stops short of the fully executable anchor.	2 / 3
Workflow Clarity	The 'Review Workflow' gives a clear three-step sequence (Map → Evaluate → Recommend), but there are no explicit validation checkpoints or feedback loops between steps, fitting the 'sequence present but checkpoints missing' anchor rather than the checkpoint-driven one.	2 / 3
Progressive Disclosure	SKILL.md is an overview that signals the real one-level-deep reference `references/rosenfeld-morville.md` (verified to exist) twice, keeping the full treatment out of the body while preserving a working summary — clean one-level navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%

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: third-person, concise, with both a clear capability statement and an explicit 'Use when...' clause listing natural trigger phrases. It covers what and when without padding or over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Evaluate and improve how information is organized for findability' — covering both assessment and remediation, matching the anchor for listing specific concrete actions.	3 / 3
Completeness	Explicitly answers what ('Evaluate and improve how information is organized for findability') and when ('Use when the user asks to...'), satisfying the what-AND-when anchor with explicit triggers.	3 / 3
Trigger Term Quality	Quotes natural user phrases verbatim ('organize this', 'restructure docs', 'improve navigation', 'where should this go', 'review file structure') plus a condition users would describe ('documentation grows beyond a single page'), giving strong coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The IA niche and its specific trigger phrases are unlikely to fire for adjacent skills; the organization/findability framing is distinct from generic doc or naming skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 12 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
Commit: 436824a

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.