information-architecture-reviewer — Claude Code skill: setup & use
information-architecture-reviewer is a Claude Code skill that audits navigation and content hierarchy against user tasks. It identifies dead ends and ambiguous labels along target flows.
MIT ★ 529 updated 2026-11-17
npx skills add ShuaiMXu/happyhands --skill information-architecture-reviewer -a claude-codeWhat information-architecture-reviewer does
The skill checks navigation structures, category groupings, and labels against a specific critical task. It consumes landmark counts and heading hierarchies from captured DOM to spot structural barriers that block user progress.
A single capture of the homepage is insufficient to evaluate information architecture. The review requires representative routes, interface states, and full navigation hierarchy. When inputs are missing, the skill marks findings as needs-evidence. It outputs directly into the ongoing audit run instead of generating a separate report, and it forbids invented experience scores.
What it helps with
- identify navigation dead ends and ambiguous categories
- trace the user path to complete a critical product task
- inspect heading hierarchy and landmark counts from DOM
- record route evidence and consequences of structural defects
Example prompts for the agent
- Review navigation hierarchy for the checkout flow
- Trace the user route to password reset and flag dead ends
- Inspect headings and menu grouping for the report export task
How to install information-architecture-reviewer
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill information-architecture-reviewer -a claude-code2Manually: put the files in place
~/.claude/skills/information-architecture-reviewer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/information-architecture-reviewer/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill information-architecture-reviewer -a codex2Manually: put the files in place
.agents/skills/information-architecture-reviewer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill information-architecture-reviewer -a cursor2Manually: put the files in place
.cursor/skills/information-architecture-reviewer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ShuaiMXu/happyhands skills/product-design/information-architecture-reviewer2Manually: put the files in place
.github/skills/information-architecture-reviewer/SKILL.md1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill information-architecture-reviewer -a gemini-cli2Platform CLI
gemini skills install https://github.com/ShuaiMXu/happyhands --path skills/product-design/information-architecture-reviewerManually: put the files in place
.devin/skills/information-architecture-reviewer/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about information-architecture-reviewer
How to install information-architecture-reviewer in Claude Code?
Run npx skills add ShuaiMXu/happyhands --skill information-architecture-reviewer -a claude-code.
What does information-architecture-reviewer do?
It inspects navigation labels, page hierarchies, and DOM landmarks to locate obstacles in critical user paths.
What evidence does information-architecture-reviewer require?
The review requires a defined critical task, representative routes, screen states, and navigation labels. A single homepage capture is not enough.
Source text
SKILL.md · MIT
--- name: information-architecture-reviewer description: "Review navigation, grouping and content structure against a product critical task." --- # Information Architecture Reviewer Find structural obstacles that prevent users from locating or understanding the next step. ## Required evidence - critical task - representative routes and states - navigation labels and hierarchy ## Decisions - Trace the path to the task - Identify ambiguous categories and dead ends - Cite route and state evidence ## Boundary A single homepage capture cannot establish full information architecture. Return structured evidence, findings, proposed updates and limitations. Use `needs-evidence` when required inputs or professional review are missing. Never invent an Experience Score or promote a project observation into a universal rule. ## Execution contract and admission The bounded handler supplies: Landmark counts and heading-order candidates from reached capture DOM. The professional method still requires: Inspect the task navigation, grouping, labels and recovery on original pages; counts do not demonstrate an information-architecture defect. Deliver into the current Run's existing experience audit or decision; do not create a competing report. Cite the frozen Skill path and exact rule, original state and source, observed failure, task consequence and the reasoning connecting them. Record preservation/counterevidence. With no demonstrated defect, keep the candidate unadmitted and make no change. `complete` describes this handler's bounded output, not professional review or human acceptance.
© ShuaiMXu · MIT · ShuaiMXu/happyhands