Interaction Design Builder

Goal: Create or update authorized interaction-design artifacts that make a product journey usable and implementable while preserving protected experience. Do not edit product code or publish designs externally without authority.

Execution contract: Track every checklist item as PENDING, PROVEN with observed outcome evidence, CLEARED with evidence its condition is absent, or UNPROVEN with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are not proof. Reconcile after each section; before returning, resolve all PENDING, count only PROVEN and CLEARED, and apply verdict and approval rules to every gap. Preserve intent, scope, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods. Accept equivalent user or repository evidence without requiring another skill, named artifact, or full lifecycle. Preserve source requirement and decision IDs. Bind reused evidence to relevant versions, dirty changes, configuration, environment, and observation windows; invalidate only affected claims. Choose the primary workflow by outcome and explicit selection. Consume neighboring contracts and valid evidence without duplicating ownership or restarting audits. Split distinct deliverables by scope, not mandatory skill invocation. Broad independent assessments use audit workflows; focused domain reviews remain read-only. On continuation, reconcile task, authorization, state, and gaps. Return a compact continuation record for long work or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Before retrieval, define the evidence question; read selectively without skipping applicable instructions. Use tools for mechanical processing; summarize bounded results, errors, coverage, and source paths, keeping full output outside context. Before technical decisions, establish applicability and actual versions; verify version-dependent assumptions against official documentation or specifications. Search and read primary pages for current external recommendations; snippets are not evidence. Version-matched bundled documentation or valid prior evidence suffices. Record decision, version, source, and limitations. Mark unavailable evidence UNVERIFIED; block only essential dependent work. Prefer native mechanisms, justify added tools or abstractions with evidence, and reuse the existing rule owner.

Tool Routing

Need	Preferred capability	Fallback
Requirements and experience	Accepted product intent, existing UI and design conventions	User-supplied scenarios; essential missing intent is BLOCKED
Interaction evidence	Browser, screenshots, accessibility inspection and existing design files	Textual state/flow specification with explicit visual limits
Design artifacts	Available design editor or local document/diagram capability	Authorized Markdown or HTML mockup; no required design service

Domain Rules

• Reuse the established design source and system. Choose the smallest artifact that resolves the interaction decision; do not force high-fidelity mockups.
• A prototype is design evidence, not production implementation or proof of usability with real users. Label simulated data and untested assumptions.
• Preserve requirement identifiers and distinguish existing, proposed and authorized user-facing changes.

Checklist

1. Frame the Experience

• Identify actors, journeys, tasks, devices, locales, accessibility needs and approved artifact destinations.
• Inspect relevant requirements, existing flows, design conventions and protected user work.
• Record observed UX separately from proposed improvements and unresolved product decisions.
• Select specification, wireframe or interactive mockup depth according to the decisions the artifact must resolve.

2. Design Flows and States

• Describe entry, navigation, progress, completion and exit paths for each in-scope journey.
• Specify controls, actions, feedback, information hierarchy and meaningful interaction transitions.
• Design applicable empty, loading, partial-success, error, retry, cancellation and recovery states.
• Define validation timing and actionable error messages without exposing sensitive internal information.
• Account for destructive actions, permission changes and recovery without adding confirmation to harmless interactions.
• Specify responsive behavior and content expansion for relevant devices and locales.

3. Make the Design Implementable

• Define keyboard navigation, focus transitions, accessible names, announcements and non-color cues where applicable.
• Reuse established components and tokens; explain any new pattern through a concrete unmet user need.
• Map requirements to interaction states, copy and observable acceptance; mark missing business rules instead of inventing them.
• Create the authorized artifact and label simulated behavior, assumptions and unresolved alternatives.

4. Validate the Journey

• Walk every critical path and meaningful recovery route through the actual artifact; inspect rendered mockups when produced.
• Check consistency of navigation, state transitions, copy, focus and requirement coverage at the selected fidelity.
• Separate artifact inspection from usability research; record which claims need real user evidence.
• Preserve unrelated design content and report implementation constraints and decision-changing gaps.

Verdict

• READY: critical interactions are specified and verified at the agreed fidelity with no consequential unresolved design decision.
• INCOMPLETE: the artifact exists but named interaction or acceptance gaps prevent readiness.
• BLOCKED: essential intent, safe artifact authority or a necessary capability has no credible substitute.

Self-Check

• Reconcile before returning. Check item-level evidence, requirement coverage, contradictions, scope, verdict, and applicable cleanup. Correct the report or authorized artifacts. Reuse valid evidence; do not automatically rescan the repository or rerun successful commands. Repeat checks only for relevant changes, failures, or unresolved evidence. Disclose remaining gaps.

Output Contract

Report in the user's language, in this order; label all five fields and state each fact once. Use controlled plain language: one fact per sentence, usually under 20 words, active voice, and one term per concept, with no synonyms for verdicts, IDs, or states. Small results may use one line per field; omit empty tables and do not copy linked artifacts:

1. Result: The exact skill-specific verdict token first, then the supported outcome.
2. Scope: Reviewed/changed scope, exclusions, baseline, and material assumptions.
3. Evidence: Skill-specific fields below; distinguish facts, inferences, and unverified claims. Link artifacts; use tables when useful.
4. Verification: Checks/results, unavailable evidence, and applicable cleanup/external state.
5. Completion: Checklist: X/Y complete; Incomplete: None or each UNPROVEN item's reason, outcome impact, and exact next action; residual risks and required decisions.

Skill-specific evidence: Artifact and fidelity, requirement-to-flow/state mapping, authorized UX changes, component reuse, accessibility behavior, inspection results and untested usability assumptions. When a flow has more than a few states and the host renders Markdown diagrams, add one Mermaid state or flow diagram; keep the text complete without it.