Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →bartsoj/WEB_IA.md
Generate a web information architecture registry — page inventory, URL strategy, navigation, per-page blueprints, flows, and use-case traceability.
Passed 18 of 23 test cases with the skill, and 10 of 23 without it.
and 8 more in the full report
10 fixed8 passed either way3 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
When generating WEB_IA.md for our customer portal, what exact YAML frontmatter header fields must be populated at the top of the file?
| Checked | Without skill | With skill |
|---|---|---|
| Includes YAML frontmatter with fields `pages_documented`, `flows_documented`, `shared_surfaces`, `use_cases_covered`, and `use_cases_total`. | Missed | Passed |
The instructions your model reads when the skill loads.
Produce a WEB_IA.md that serves as the single source of truth for a web application's information architecture: the full page-template inventory, URL strategy, global navigation, per-page blueprint (purpose, sections, primary CTA, data dependencies, state matrix, entry/exit points), cross-page flows, shared UI surfaces, and bidirectional traceability from product use cases to pages. An agent or designer reading this document knows exactly what pages exist, what lives on each page, how users move between them, and how every use case is realized on the web surface — without making any independent architectural or content decisions. WEB_IA sits between product requirements (proposal, use cases) and per-unit web SPECs, the same way INTERFACES sits between architecture and per-unit backend SPECs.
pages/ or app/ directories, router config). Treat as reference only — WEB_IA is the target state, not a mirror of the current state.EP-name.The user may override scope (e.g., "only the authenticated app area, not marketing site"). Support that by recording the narrowed scope in the Identity & Context section and excluding out-of-scope surfaces from the inventory.
Web IA generation proceeds in seven phases: scope, URL and navigation, inventory, per-page blueprint, flows and shared surfaces, global states and responsive, traceability and validation. Phases are sequential — later phases depend on earlier decisions — but revisit earlier phases if a later phase reveals a gap.
Derive from the product doc and use cases document the target web surface (marketing site, authenticated app, admin back-office, embedded widget, or some combination) and the audiences the IA serves. Record explicitly what is not in scope for this WEB_IA document. Keep audience treatment thin — named user types and their 3–7 top tasks per audience. No deep persona work.
Decide routing conventions and global chrome before enumerating pages. This prevents per-page drift where each page invents its own URL shape or navigation.
Decide:
/api, /_next, /assets)test cases passed, vs 10 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.