skillpacks 0.1.1 → 0.1.2

package/packs/product-design/claude/feature-interview/archive/v0.6/SKILL.md

@@ -0,0 +1,149 @@
+---
+name: feature-interview
+description: Interview a feature idea with evidence-backed alignment, then decide whether to create/update docs, specs, roadmap, or tasks
+type: planning
+version: v0.6
+argument-hint: "[feature idea or tasks/ideas.md entry]"
+interview_depth: full
+---
+
+## Pack Availability Guard
+
+Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `/pack install <pack>` inside Claude Code, or `npx skillpacks install <pack>` from the project shell, instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Feature Interview
+
+Use this skill when the user has a feature idea, brainstorm suggestion, research gap, bug-shaped improvement, or implementation direction that needs evidence-backed alignment before deciding whether to write or update research docs, journey docs, specs, roadmap entries, task queues, or route directly to another planning skill. This skill is also the primary entry point for post-ship feature work, where scope determines the re-entry depth into the pipeline.
+
+This is narrower than `/spec-interview`: it performs the same assumption surfacing and user interrogation needed for human/agent alignment, but it does not assume the output must be a full new implementation spec. It borrows `/investigate`'s evidence discipline for claims, codebase fit, and technical gotchas, but it does not fix bugs or implement the feature.
+
+Use `/feature-interview` especially after a production spec already exists and the user wants to add, adjust, or triage a smaller feature. In post-spec use, treat existing specs as the baseline contract: prefer a scoped add-on spec or a tightly bounded update to an existing spec over re-running `/spec-interview` for the whole product. Only route to `/spec-interview` when the existing spec is absent, obsolete, or too incomplete to support the new feature decision.
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$ARGUMENTS` names a non-archived `research/{slug}/` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product/app name, not the ICP, audience, or segment label.
+2. If `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
+3. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
+4. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
+5. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
+6. If no product directories exist, use flat `research/` single-product mode.
+7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
+
+1. Resolve the feature input:
+   - If `$ARGUMENTS` names or quotes an idea, use it as the seed.
+   - If `$ARGUMENTS` references `tasks/ideas.md`, read matching entries and ask the user to choose one when multiple entries match.
+   - If no feature is provided, read `tasks/ideas.md` and present the top unspecced candidates; ask the user which one to interview.
+2. Gather context before asking deep questions:
+   - Read `.agents/project.json`, CLAUDE.md or AGENTS.md, README, package config, and key source files relevant to the idea.
+   - Read `research/.progress.yaml` when present. Treat product-path entries as product/app/ICP divergence state, not git branches.
+   - Read `tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, `tasks/recurring-todo.md`, `tasks/history.md`, and `tasks/ideas.md` when they exist.
+   - Read existing specs from `specs/`, `spec.md`, or `docs/specifications/`, plus relevant research docs such as ICP, journey map, competitive analysis, customer feedback, metrics, and MVP gap artifacts.
+   - Read git evidence (`git log`, `git diff`, `git blame`) only where it can confirm related prior decisions, recent regressions, ownership, or why the current system shape exists.
+   - Avoid re-interviewing on facts already covered by current concept, research, journey, UX, UI, or spec docs.
+3. Run an evidence-backed intake pass before deciding what to ask:
+   - Extract the user's explicit claims, hypotheses, constraints, and desired outcomes. Do not treat a desired outcome as a factual claim.
+   - Validate factual claims against code, docs, research, task state, and git history. Classify each as `confirmed`, `partially supported`, `not supported`, or `unknown / needs user context`.
+   - Identify likely technical gotchas: architecture fit, shared modules, data model, API/contracts, migrations, security/privacy, permissions, performance, observability, tests, rollout, external dependencies, and backwards compatibility.
+   - Identify how the feature fits into the user story, customer journey, developer workflow, game loop, or other project-specific journey artifact. If no credible journey exists for user-facing work, flag that as a planning gap.
+   - For new user-facing product, SaaS, marketplace, dashboard, internal tool, product-experience work, or substantial new feature work, add a prototype-first gate to the intake: default the first build artifact to a clickable local/static prototype with fake, fixture, or in-memory data unless the user explicitly opts into production infrastructure or the core interaction cannot be tested without it. Treat durable storage, auth, payments, analytics, deployment, admin tooling, multi-tenancy, and production observability as deferred infrastructure decisions until the prototype calibrates taste, feel, workflow density, and one accepted journey.
+   - When the feature direction is uncertain, recommend multiple route-based experiments instead of one over-specified implementation. Name the routes or route pattern, such as `/experiments/table-first`, `/experiments/board-first`, or the project's equivalent, and identify the hypothesis each route tests.
+   - If those route experiments imply materially different products, apps, ICPs, or product lines rather than alternative UX for the same product path, record them in `research/.progress.yaml` as `product_paths[]` with `id`, `label`, `source_skill: feature-interview`, `scope_path`, `status: deferred` or `status: revisit_candidate`, `reason`, `archive_reason`, `archived_at`, `promoted_at`, `evidence_refs`, `revisit_trigger`, `next_skill`, `pipeline_stage: feature-interview`, and `last_touched`.
+   - Identify whether research docs, journey docs, specs, roadmap, or task queues need a durable update if the feature proceeds.
+4. Match the feature against existing planning artifacts:
+   - Identify whether the repo is in a post-spec state: one or more credible `specs/*.md`, `spec.md`, or `docs/specifications/*.md` files already define the product or area this feature extends.
+   - Identify whether the feature is already fully represented in an existing spec, partially represented in a spec, should become a scoped add-on spec, is only present as an idea/research gap, or is already sequenced in the roadmap.
+   - In post-spec state, default to `update existing spec` or `new smaller-scope add-on spec` as the planning destination. Do not discard the existing spec baseline or route back to full `/spec-interview` unless the existing spec is stale, contradicted, or missing the product area needed to make the decision.
+   - If it duplicates planned work, stop and recommend the existing route (`/roadmap` (requires agent-work-admin pack), `/plan-phase N` (requires agent-work-admin pack), `/exec` (requires exec-loop pack), or `/ship` (requires exec-loop pack)) with evidence.
+5. Present a **Feature Evidence Brief + Assumptions Manifest** before probing:
+   - Evidence sources: files, docs, research artifacts, task docs, and git history consulted.
+   - Claim validation: verdict for each factual claim or hypothesis, with concise evidence.
+   - Technical gotchas: likely integration risks, operational risks, unknowns, and what would break if each assumption is wrong.
+   - Journey placement: where this feature belongs in the user story, journey map, workflow, or loop; note missing or conflicting journey evidence.
+   - Documentation destination: likely `new spec`, `update existing spec`, `update research/journey docs`, `roadmap/task update`, `interview log only`, `run another planning/research skill first`, or `no action`.
+   - Source context: idea/research/spec/roadmap inputs used.
+   - Human intent: what outcome the user appears to want and who benefits.
+   - Agent interpretation: the concrete capability or change the agent would plan from the input.
+   - Existing-system fit: code paths, specs, tasks, and research artifacts likely affected.
+   - Post-spec fit: whether the feature extends an existing spec, needs a smaller-scope add-on spec, updates research/journey docs first, or is already covered.
+   - Planning destination: likely `update existing spec`, `new smaller-scope add-on spec`, `new full spec`, `roadmap/task update`, `research/design skill first`, or `no new planning needed`.
+   - Priority hypothesis: recommended priority relative to current roadmap/todo, with dependency and risk rationale.
+   - Implementation shape: product behavior, design/UX needs, data model, APIs/contracts, migrations, tests, operations, and rollout surface as far as they can be inferred.
+   - Prototype-first gate for product and feature work: state whether the next artifact should be `multiple route experiments`, `single clickable prototype`, `production implementation`, or `research/spec only`. If there is no accepted prototype or user-approved infrastructure opt-in, recommend route experiments or a clickable prototype and explicitly defer database/storage, auth, payments, analytics, deployment, admin tooling, multi-tenancy, and production observability.
+   - Risks and unknowns: ambiguity, integration risk, user-facing risk, external dependencies, and what breaks if the assumption is wrong.
+   Tag each assumption with `[from idea]`, `[from spec]`, `[from codebase]`, `[from research]`, `[from roadmap]`, `[from git]`, or `[inferred]`.
+   Deliver the brief and manifest inline as the final message text of their own turn; ask the step 6 confirmation in the next turn. AskUserQuestion option previews may mirror the content as a supplement but are never the sole channel. Never emit the brief only as mid-turn text in a turn that ends with a tool call — harness rendering does not guarantee mid-turn text is shown.
+6. In the turn after the brief is shown, ask the user to confirm, correct, or flag the evidence brief, claim verdicts, assumptions, journey placement, documentation destination, and priority hypothesis before continuing. Do not proceed past this checkpoint until the user has reviewed it. A confirmation question must never reference content the user has not been shown.
+7. Interview in focused passes, 1 to 3 questions per turn. If the session is already in Plan mode and there are 2-3 concrete options, prefer `request_user_input`; otherwise ask concise direct questions.
+8. Cover only the areas needed to choose and prepare the planning destination:
+   - Intent and success criteria.
+   - Target users, jobs, and journey/design implications.
+   - Feature behavior and scope boundaries.
+   - Existing spec fit: whether to create a new spec, update an existing spec, or split the work.
+   - Implementation constraints: architecture, data model, API/contract surface, migrations, security, privacy, performance, observability, test strategy, and rollout.
+   - Research and journey implications: whether canonical research, journey, UX, UI, or customer/developer docs need updates.
+   - Roadmap coupling: dependencies, phase fit, priority, ordering, parallelization, manual blockers, and the smallest useful implementation slice.
+9. Research and recommend by default. Use codebase evidence, existing docs, and web search when the decision depends on current external facts. Present options with pros/cons, state a recommendation, and ask the user to approve, adjust, or override.
+10. Before concluding, present a **Planning Destination + Priority Checkpoint**:
+   - Decision: update existing spec, create a new smaller-scope add-on spec, create a new full spec, update research/journey docs, update roadmap/tasks only, run another named planning/research skill first, interview log only, or no action.
+   - Target artifact path(s).
+   - Existing spec relationship: the parent spec or product-area spec this feature extends, supersedes, or leaves unchanged.
+   - Journey/workflow placement to record.
+   - Scope to include now and explicitly defer.
+   - For user-facing product or feature work, confirm the prototype-first decision: what users can click through first, whether multiple experiments should live on separate routes, what data can be fake or fixture-backed, which infrastructure is intentionally deferred, and what evidence would justify promoting one deferred infrastructure item into a later production phase.
+   - Scope triage for post-ship features:
+     - Small (config, copy, toggle) → `/spec-interview` + `/exec` directly
+     - Medium (new component, screen, workflow) → single-variation mini-prototype (`/prototype --variant 1`)
+     - Large (new product area, major redesign) → full pipeline starting at `/ux-variations`
+   - Priority decision: user-confirmed priority, dependencies, and whether the feature should interrupt, follow, or remain parked relative to current roadmap/todo work.
+   - Roadmap/task impact and recommended next command.
+   Deliver the checkpoint inline as the final message text of its own turn; in the next turn, ask: "Does this destination, priority, and scope match what you want?"
+
+## Deliverables
+
+After confirmation, write the minimum durable artifact needed:
+
+- New spec: write `specs/[topic].md` using the `/spec-interview` canonical section headings.
+- Add-on spec: write `specs/[parent-topic]-[feature-topic].md` or the repo's equivalent scoped path. State the parent spec it extends, the inherited assumptions, what is intentionally out of scope because the parent spec already owns it, and the exact integration points back to the parent.
+- Existing spec update: archive the existing canonical spec first, then update only the relevant sections.
+- Research or journey update: archive the existing canonical research/journey document first when replacing or substantively rewriting sections, then make the smallest scoped update. If the missing research requires a named skill, write the interview log and recommend that skill instead of inventing unsupported research.
+- Roadmap/task-only change: update `tasks/roadmap.md`, `tasks/todo.md`, `tasks/record-todo.md`, or `tasks/manual-todo.md` only when no spec/research change is needed and the user has confirmed priority.
+- Upstream planning/research needed: write an interview log and recommend the named skill instead of inventing a placeholder spec.
+- No action: write an interview log explaining why the idea is already covered, duplicate, deferred, or intentionally parked.
+- Product path divergence: update `research/.progress.yaml` with `id`, `label`, `source_skill`, `scope_path`, `status`, `reason`, `archive_reason`, `archived_at`, `promoted_at`, `evidence_refs`, `revisit_trigger`, `next_skill`, `pipeline_stage`, and `last_touched`; do not force all divergent paths through downstream research.
+
+Always write an interview log to `specs/[topic]-feature-interview.md` (or `docs/specifications/[topic]-feature-interview.md` if that is the repo's canonical spec location). Include:
+
+- Artifact path: the exact path of this interview log.
+- The Feature Evidence Brief and Assumptions Manifest with user corrections.
+- Claim validation verdicts and evidence.
+- Technical gotchas, mitigations, and unresolved unknowns.
+- Journey/user-story/workflow placement and any research or journey doc changes needed.
+- Questions asked and answers received.
+- Options and recommendations presented.
+- Planning Destination + Priority Checkpoint and confirmed decision.
+- Post-spec relationship: parent spec, add-on spec path, or updated spec section, including why this path is smaller and safer than re-running full `/spec-interview`.
+- The exact next command for sequencing.
+
+### Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment/feature-interview-{topic}.html`.
+
+## Constraints
+
+- Do not default to a new spec when an existing spec should be updated.
+- Do not route post-spec feature additions back to full `/spec-interview` by default. Use `/feature-interview` to create a scoped add-on spec or update the existing spec unless the baseline spec is missing or unfit.
+- Do not update roadmap or task sequencing until the planning destination and priority are confirmed by the user.
+- Do not produce a full implementation spec unless the interview proves a new or rewritten spec is the right destination.
+- Do not route brainstorm ideas directly to `/spec-interview`; use `/feature-interview` for triage unless the user explicitly asks for a full spec.
+- Do not implement fixes or feature code from this skill. If the evidence pass uncovers a bug, route to `/investigate` (requires code-debug pack); if it uncovers buildable planned work, route through `/roadmap` (requires agent-work-admin pack), `/plan-phase` (requires agent-work-admin pack), or `/exec` (requires exec-loop pack).
+- When recommending a skill from another pack, verify the pack is installed via `.agents/project.json` `enabled_packs`. If not installed, recommend `/pack install <pack-name>` inside Claude Code, or `npx skillpacks install <pack-name>` from the project shell, before the target skill.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/product-design/claude/prototype/ALIGNMENT-PAGE.md

@@ -57,7 +57,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-prototype-research.md`; product-path mode uses `research/{slug}/_working/preliminary-prototype-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-prototype-research.md`; product-path mode uses `research/{slug}/_working/preliminary-prototype-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Prototype-specific gates.** Render source-spec coverage, prototype scope, non-goals and deferred infrastructure, route/file destinations, file mutation scope, validation plan, and post-approval UAT route as gates. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
 

package/packs/product-design/claude/prototype/CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## v0.14 - 2026-06-13
+
+- Moved prototype gates and source reads from pre-prototype `specs/` files to `design/` flow maps, UX variation plans, UI branch packets, and flow-tree manifests.
+- Clarified that prototype output remains under `prototypes/` and consumes design-phase branch approval state before post-prototype specification work.
+
+## v0.13 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.12 - 2026-06-11
 
 - Added npm-aware install-route wording for product-testing and cross-pack recommendations while preserving Claude `/pack install ...` routes.

package/packs/product-design/claude/prototype/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: prototype
-description: Build tangible, runnable prototypes from UX variation and UI specs — static HTML/CSS for UI projects, runnable scripts for CLI, endpoint stubs for API, or minimal configs for infra
+description: Build tangible, runnable prototypes from design-phase UX variation and UI branch packets — static HTML/CSS for UI projects, runnable scripts for CLI, endpoint stubs for API, or minimal configs for infra
 type: execution
-version: v0.12
+version: v0.14
 argument-hint: "[optional: topic, --variant N]"
 visual_tier: prototype
 ---
@@ -17,16 +17,16 @@ Build tangible, runnable prototypes before production spec work begins. Create t
 
 Before proceeding, verify the following files exist:
 
-- At least one `specs/ux-variations-*.md` file.
-- At least one `specs/ui-*.md` file (e.g., `specs/ui-[topic].md`, `specs/ui-layout-variations-[topic].md`, or `specs/ui-requirements-[topic].md`).
+- At least one `design/ux-variations-*.md` file or product-path-scoped equivalent.
+- At least one `design/ui-*.md` file or product-path-scoped equivalent (e.g., `design/ui-[topic].md`, `design/ui-layout-variations-[topic].md`, or `design/ui-requirements-[topic].md`).
 
-Also read `specs/user-flow-*.md` when present as an upstream screen-ordering and task-sequencing signal. It is preferred evidence, not a hard prerequisite for this gate.
+Also read `design/user-flow-*.md` and `design/**/flow-tree-*.yaml` when present as upstream screen-ordering, task-sequencing, branch-state, and approval-state signals. They are preferred evidence, not hard prerequisites for this gate.
 
 If either is missing, halt with a clear message:
 
 > Prototyping requires UX variation planning and UI specification. Missing prerequisites:
-> - `specs/ux-variations-*.md` — run `/ux-variations` to create variation concepts.
-> - `specs/ui-*.md` — run `/ui-interview` to define the interface specification.
+> - `design/ux-variations-*.md` — run `/ux-variations` to create variation concepts.
+> - `design/ui-*.md` — run `/ui-interview` to define the interface specification.
 
 Do not proceed past this gate until both prerequisites exist.
 
@@ -44,7 +44,7 @@ Resolve research scope by product path before using code or app structure as a h
 6. If no product directories exist, use flat `research/` single-product mode.
 7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
 
-When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
+When product path `{slug}` is active, read research under `research/{slug}/`, read pre-prototype design artifacts under `design/{slug}/`, write prototype output under `prototypes/{topic}/`, and treat top-level `research/*.md` and `design/*.md` files as flat-mode documents or cross-path summaries.
 
 ### 1. Resolve context
 
@@ -54,10 +54,10 @@ When product path `{slug}` is active, read and write research under `research/{s
   - `research/icp.md` — ideal customer profile; informs copy density, terminology, and information hierarchy.
   - `research/competitive-analysis.md` — differentiation points the prototype should highlight.
   - `research/journey-map.md` — screen flow ordering, entry points, and task sequencing.
-- Read variation specs: `specs/ux-variations-[topic].md` for each relevant topic.
-- Read user-flow specs: `specs/user-flow-[topic].md` for screen ordering, entry points, branches, decision points, required states, failure/recovery paths, handoffs, and low-fidelity wireframe notes when present.
-- Read per-variation UI specs: `specs/ui-[topic].md`, `specs/ui-layout-variations-[topic].md`, and `specs/ui-requirements-[topic].md` when present.
-- If an argument is provided, use it as the topic filter. Otherwise, identify the topic from available specs.
+- Read variation plans: `design/ux-variations-[topic].md` or product-path-scoped equivalents for each relevant topic.
+- Read user-flow maps: `design/user-flow-[topic].md` and `design/**/flow-tree-*.yaml` for screen ordering, entry points, branches, decision points, required states, failure/recovery paths, handoffs, branch approval state, and low-fidelity wireframe notes when present.
+- Read per-variation UI branch packets: `design/ui-[topic].md`, `design/ui-layout-variations-[topic].md`, and `design/ui-requirements-[topic].md` when present.
+- If an argument is provided, use it as the topic filter. Otherwise, identify the topic from available design artifacts.
 
 ### 2. Research integration
 
@@ -65,7 +65,7 @@ Before building, extract actionable signals from research:
 
 - **ICP** (`research/icp.md`): Determine copy density (expert vs. novice), terminology choices, information hierarchy, and default density (compact vs. spacious). The prototype should feel like it was built for the target user, not a generic audience.
 - **Journey map** (`research/journey-map.md`): Derive screen flow ordering. The prototype's navigation and page sequence should follow the user's natural task progression, not an arbitrary menu order.
-- **User-flow map** (`specs/user-flow-[topic].md`): Derive concrete screen order, route inventory, branches, required states, failure/recovery behavior, and low-fidelity wireframe structure. The prototype should preserve the approved task sequence unless a variation spec explicitly changes it.
+- **User-flow map** (`design/user-flow-[topic].md` and `design/**/flow-tree-*.yaml`): Derive concrete screen order, route inventory, branches, required states, failure/recovery behavior, low-fidelity wireframe structure, and branch approval state. The prototype should preserve the approved task sequence unless a variation plan explicitly changes it.
 - **Competitive analysis** (`research/competitive-analysis.md`): Identify differentiation points the prototype must highlight. If the product's thesis is "faster than X" or "simpler than Y," the prototype should make that advantage viscerally obvious.
 - **Idea brief** (`research/idea-brief.md`): Surface assumptions the prototype is designed to test. Each prototype variation should help validate or invalidate at least one idea-brief assumption.
 
@@ -123,10 +123,10 @@ For CLI, API, and Infra modes, build exactly one core workflow demo with fixture
 
 ### 5. Build each variation
 
-For each variation defined in `specs/ux-variations-[topic].md`:
+For each variation defined in `design/ux-variations-[topic].md`:
 
 1. Read the variation's thesis, target user, layout/flow model, and prototype scope from the spec.
-2. Read the corresponding UI spec details from `specs/ui-[topic].md` or `specs/ui-layout-variations-[topic].md`.
+2. Read the corresponding UI branch details from `design/ui-[topic].md` or `design/ui-layout-variations-[topic].md`.
 3. Build the prototype artifact in `prototypes/{topic}/variation-{N}/`.
 4. Name the directory using the variation number from the spec (1-indexed).
 5. Ensure the prototype is immediately usable: open the HTML file, run the script, curl the endpoint, or read the config.
@@ -171,7 +171,7 @@ prototypes/{topic}/
 
 After prototypes are built, recommend:
 
-> Recommended next command: `/uat --variant-evaluation` (check `.agents/project.json.enabled_packs` for `product-testing` — if `product-testing` is not enabled, recommend `/pack install product-testing` inside Claude Code, or `npx skillpacks install product-testing` from the project shell, first)
+> Recommended next command: `/uat --variant-evaluation` (check `.agents/project.json.enabled_packs` for `product-testing` — if `product-testing` is not enabled, recommend `npx skillpacks install product-testing` from the project shell, first)
 
 The user should interact with each prototype variation hands-on before consolidating. UAT variant evaluation provides a structured comparison framework to capture evidence for each variation's strengths, friction points, and rejection signals.
 
@@ -183,7 +183,7 @@ The user should interact with each prototype variation hands-on before consolida
 - Do not skip variations. Build all variations defined in the spec unless `--variant N` is provided.
 - Do not choose a winning variation or recommend consolidation. That is the user's decision after UAT evaluation.
 - Do not modify specs, research documents, or task files. Only create files in the `prototypes/` directory.
-- When recommending a skill from another pack, verify the pack is installed via `.agents/project.json` `enabled_packs`. If not installed, recommend `/pack install <pack-name>` inside Claude Code, or `npx skillpacks install <pack-name>` from the project shell, before the target skill.
+- When recommending a skill from another pack, verify the pack is installed via `.agents/project.json` `enabled_packs`. If not installed, recommend `npx skillpacks install <pack-name>` from the project shell, before the target skill.
 
 ## Alignment Page
 

package/packs/product-design/claude/prototype/archive/v0.12/SKILL.md

@@ -0,0 +1,196 @@
+---
+name: prototype
+description: Build tangible, runnable prototypes from UX variation and UI specs — static HTML/CSS for UI projects, runnable scripts for CLI, endpoint stubs for API, or minimal configs for infra
+type: execution
+version: v0.12
+argument-hint: "[optional: topic, --variant N]"
+visual_tier: prototype
+---
+
+# Prototype
+
+Invoke as `/prototype`.
+
+Build tangible, runnable prototypes before production spec work begins. Create the first concrete artifact users can interact with, grounded in research and UX variation planning. Prototypes are cheap, disposable, and designed for evaluation — not production readiness. The goal is to give humans something to click, run, or curl so they can form opinions before committing to a direction.
+
+## Gate
+
+Before proceeding, verify the following files exist:
+
+- At least one `specs/ux-variations-*.md` file.
+- At least one `specs/ui-*.md` file (e.g., `specs/ui-[topic].md`, `specs/ui-layout-variations-[topic].md`, or `specs/ui-requirements-[topic].md`).
+
+Also read `specs/user-flow-*.md` when present as an upstream screen-ordering and task-sequencing signal. It is preferred evidence, not a hard prerequisite for this gate.
+
+If either is missing, halt with a clear message:
+
+> Prototyping requires UX variation planning and UI specification. Missing prerequisites:
+> - `specs/ux-variations-*.md` — run `/ux-variations` to create variation concepts.
+> - `specs/ui-*.md` — run `/ui-interview` to define the interface specification.
+
+Do not proceed past this gate until both prerequisites exist.
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$ARGUMENTS` names a non-archived `research/{slug}/` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product/app name, not the ICP, audience, or segment label.
+2. If `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
+3. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
+4. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
+5. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
+6. If no product directories exist, use flat `research/` single-product mode.
+7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
+
+### 1. Resolve context
+
+- Read `.agents/project.json` if it exists. Extract `project_type` for dispatch decisions.
+- Read research documents when present:
+  - `research/idea-brief.md` — assumptions to test, core value proposition, and hypothesis framing.
+  - `research/icp.md` — ideal customer profile; informs copy density, terminology, and information hierarchy.
+  - `research/competitive-analysis.md` — differentiation points the prototype should highlight.
+  - `research/journey-map.md` — screen flow ordering, entry points, and task sequencing.
+- Read variation specs: `specs/ux-variations-[topic].md` for each relevant topic.
+- Read user-flow specs: `specs/user-flow-[topic].md` for screen ordering, entry points, branches, decision points, required states, failure/recovery paths, handoffs, and low-fidelity wireframe notes when present.
+- Read per-variation UI specs: `specs/ui-[topic].md`, `specs/ui-layout-variations-[topic].md`, and `specs/ui-requirements-[topic].md` when present.
+- If an argument is provided, use it as the topic filter. Otherwise, identify the topic from available specs.
+
+### 2. Research integration
+
+Before building, extract actionable signals from research:
+
+- **ICP** (`research/icp.md`): Determine copy density (expert vs. novice), terminology choices, information hierarchy, and default density (compact vs. spacious). The prototype should feel like it was built for the target user, not a generic audience.
+- **Journey map** (`research/journey-map.md`): Derive screen flow ordering. The prototype's navigation and page sequence should follow the user's natural task progression, not an arbitrary menu order.
+- **User-flow map** (`specs/user-flow-[topic].md`): Derive concrete screen order, route inventory, branches, required states, failure/recovery behavior, and low-fidelity wireframe structure. The prototype should preserve the approved task sequence unless a variation spec explicitly changes it.
+- **Competitive analysis** (`research/competitive-analysis.md`): Identify differentiation points the prototype must highlight. If the product's thesis is "faster than X" or "simpler than Y," the prototype should make that advantage viscerally obvious.
+- **Idea brief** (`research/idea-brief.md`): Surface assumptions the prototype is designed to test. Each prototype variation should help validate or invalidate at least one idea-brief assumption.
+
+Document which research signals influenced which prototype decisions in a brief `## Research Integration` section at the top of the hub page.
+
+### 3. Project type dispatch
+
+Determine the project type from `.agents/project.json` `project_type` field. If the field is absent, infer from repository signals (package.json scripts, Dockerfile presence, CLI entry points, route files, etc.). Dispatch to one of the following modes:
+
+#### UI mode (business-app, or default when no project_type)
+
+Build static HTML/CSS prototypes for each variation:
+
+- One self-contained HTML file per variation at `prototypes/{topic}/variation-{N}/index.html`.
+- Inline CSS and minimal inline JS (no build tools, no bundler, no framework dependencies).
+- Fake but realistic data — use plausible names, dates, amounts, and content that matches the ICP.
+- Clickable navigation between pages/views within the variation. Use anchor links, hash routing, or multiple HTML files as appropriate.
+- Responsive layout when the UI spec defines responsive behavior.
+- Visual states: show default, empty, loading (static representation), and error states where the spec defines them.
+- Do not use CDN-hosted frameworks or libraries. The prototype must work offline from a file:// URL.
+- Include a brief `<!-- Variation N: [Name] — [Thesis] -->` comment at the top of each HTML file.
+
+#### CLI mode (devtool with CLI focus)
+
+Build runnable script prototypes for each variation:
+
+- One executable script per variation at `prototypes/{topic}/variation-{N}/demo.sh` (or `.py`, `.js`, etc., matching the project's primary language).
+- Include fixture data files alongside the script.
+- Demonstrate one core workflow end-to-end: the user runs a single command (or short sequence) and sees realistic output.
+- Include inline comments explaining which variation thesis this demonstrates.
+- Scripts must be runnable with standard tooling (bash, node, python) without additional dependencies.
+
+#### API mode (devtool with API focus)
+
+Build endpoint stub prototypes for each variation:
+
+- One lightweight server or mock per variation at `prototypes/{topic}/variation-{N}/server.{ext}`.
+- Fixture JSON responses for each endpoint.
+- A `curl-examples.sh` file with annotated curl commands demonstrating the core workflow.
+- Include a brief README in each variation directory explaining the API design thesis.
+- Endpoints return fixture data; no database or persistence required.
+
+#### Infra mode
+
+Build minimal configuration prototypes for each variation:
+
+- One `docker-compose.yml` or equivalent config per variation at `prototypes/{topic}/variation-{N}/`.
+- Include `.env.example`, config files, and documentation sufficient to understand the infrastructure concept.
+- Do not require running services; use placeholder images or mock services where possible.
+- Include a brief README explaining the infrastructure thesis and what a user would observe if they ran it.
+
+### 4. Scope rule (non-UI modes)
+
+For CLI, API, and Infra modes, build exactly one core workflow demo with fixture data per variation. Do not attempt full API coverage, complete CLI help systems, or production-ready infrastructure. The prototype exists to make the variation thesis tangible, not to implement the product.
+
+### 5. Build each variation
+
+For each variation defined in `specs/ux-variations-[topic].md`:
+
+1. Read the variation's thesis, target user, layout/flow model, and prototype scope from the spec.
+2. Read the corresponding UI spec details from `specs/ui-[topic].md` or `specs/ui-layout-variations-[topic].md`.
+3. Build the prototype artifact in `prototypes/{topic}/variation-{N}/`.
+4. Name the directory using the variation number from the spec (1-indexed).
+5. Ensure the prototype is immediately usable: open the HTML file, run the script, curl the endpoint, or read the config.
+
+### 6. Build the hub page
+
+Create a hub page at `prototypes/{topic}/index.html` that:
+
+- Lists every variation with its name, thesis, and a direct link to the variation's entry point.
+- Includes the research integration summary (which research signals drove which decisions).
+- Provides brief instructions for evaluating each variation.
+- For UI mode: links open the variation's `index.html` in the same browser.
+- For CLI/API/Infra modes: the hub page is a simple HTML document with copy-pasteable commands to run each variation.
+- After writing or updating the hub page, attempt to open `prototypes/{topic}/index.html` in the browser and report whether the browser open succeeded or was blocked. A blocked browser open does not make the prototype fail when the files were written correctly.
+
+### 7. `--variant N` flag
+
+When the user provides `--variant N` (or says "rebuild variation N", "only variation N", etc.):
+
+- Build or rebuild only variation N, preserving all other existing variations and the hub page.
+- Update the hub page to reflect any changes to the rebuilt variation.
+- Do not delete or modify other variation directories.
+
+## Output
+
+The skill produces the following file structure:
+
+```
+prototypes/{topic}/
+  index.html                    # Hub page listing all variations
+  variation-1/
+    index.html (or demo.sh, server.js, docker-compose.yml)
+    [supporting files: fixtures, styles, curl-examples, README]
+  variation-2/
+    index.html (or demo.sh, server.js, docker-compose.yml)
+    [supporting files]
+  variation-N/
+    ...
+```
+
+## Next Step
+
+After prototypes are built, recommend:
+
+> Recommended next command: `/uat --variant-evaluation` (check `.agents/project.json.enabled_packs` for `product-testing` — if `product-testing` is not enabled, recommend `/pack install product-testing` inside Claude Code, or `npx skillpacks install product-testing` from the project shell, first)
+
+The user should interact with each prototype variation hands-on before consolidating. UAT variant evaluation provides a structured comparison framework to capture evidence for each variation's strengths, friction points, and rejection signals.
+
+## Constraints
+
+- Do not introduce build tools, bundlers, package managers, or framework dependencies into prototypes. Prototypes must be immediately usable without installation steps.
+- Do not connect to real databases, APIs, or external services. All data must be fixture/fake data.
+- Do not build production-quality code. Prototypes are disposable artifacts for evaluation, not starting points for implementation.
+- Do not skip variations. Build all variations defined in the spec unless `--variant N` is provided.
+- Do not choose a winning variation or recommend consolidation. That is the user's decision after UAT evaluation.
+- Do not modify specs, research documents, or task files. Only create files in the `prototypes/` directory.
+- When recommending a skill from another pack, verify the pack is installed via `.agents/project.json` `enabled_packs`. If not installed, recommend `/pack install <pack-name>` inside Claude Code, or `npx skillpacks install <pack-name>` from the project shell, before the target skill.
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment/prototype-{topic}.html`.
+
+Prototype files may be created before the alignment page because the review needs runnable artifacts. After building or updating prototype files, build and attempt to open `alignment/prototype-{topic}.html` before downstream routing, UAT handoff, consolidation, spec updates, research updates, or task/roadmap changes.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.