skillpacks 0.1.0 → 0.1.1

package/packs/product-design/claude/feature-interview/archive/v0.4/SKILL.md

@@ -0,0 +1,148 @@
+---
+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: v0.4
+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>` 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]`.
+6. 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.
+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.
+   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, prepend `/pack install <pack-name>` to the recommendation.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/product-design/claude/feature-interview/archive/v0.5/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: v0.5
+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>` 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, prepend `/pack install <pack-name>` to the recommendation.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

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

@@ -9,7 +9,7 @@ When this skill produces durable deliverables (research, specs, plans, reports,
 
 The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected by the upgrade script). The bundled ALIGNMENT-PAGE.md receives tier-appropriate rendering guidance from the generator.
 
-**Alignment lifecycle.** Alignment pages have three lifecycle states. `review` is the draft/pre-approval page: it contains the complete deliverable preview, evidence, required inline gate questions, section feedback controls, feedback-only YAML, and final compile controls. `confirmed` is the post-approval page after the agent has consumed final compiled YAML, made any approved user-requested edits, and written or updated the approved canonical artifacts. A confirmed page is finished and current for the completed alignment cycle, but it remains amendable when later research changes or extends the conclusions. `amended` is a future revision of a confirmed page: archive the previous confirmed page first, mark what changed, preserve the prior approval record, and highlight the new evidence, decisions, or scope that changed the earlier conclusion.
+**Alignment lifecycle.** Alignment pages have three lifecycle states. `review` is the draft/pre-approval page: it contains the complete deliverable preview, evidence, required inline gate questions, section feedback controls, local section-feedback YAML only after a section feedback choice is selected, and one bottom `Compile Responses` control. `confirmed` is the post-approval page after the agent has consumed final compiled response YAML, made any approved user-requested edits, and written or updated the approved canonical artifacts. A confirmed page is finished and current for the completed alignment cycle, but it remains amendable when later research changes or extends the conclusions. `amended` is a future revision of a confirmed page: archive the previous confirmed page first, mark what changed, preserve the prior approval record, and highlight the new evidence, decisions, or scope that changed the earlier conclusion.
 
 **Central alignment index.** When a research-producing skill writes or updates an HTML alignment page, also maintain the repository's central alignment index. Look for `alignment/index.html` at the repository root; if the target repo documents a different central alignment-index path, use that path and report it. If the index does not exist, create it as a self-contained HTML page that works from `file://`, links to every active `alignment/*.html` page except itself, and includes the newly written page. Every index entry must include the page's alignment date in a muted meta span after the link, formatted `YYYY-MM-DD`, for example `<a href="page.html">Title</a> <span class="meta">2026-06-09</span>`. The alignment date is the review or confirmed date written inside the page itself; new pages use today's date. If the index exists, update it instead of blindly appending: preserve valid existing entries, metadata, and entry dates; remove duplicate entries for the same page path; keep links repo-relative; and include the new or updated page. When updating an existing index, add a date only to entries that are missing one, deriving it from the page's internal alignment date, or from file history when the page has no internal date. If a `new` marker is used, combine it with the date as `<span class="meta">new · YYYY-MM-DD</span>`, and remove stale `new` markers from entries that are no longer the latest addition.
 
@@ -29,7 +29,7 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Category and product-path grouping.** In product-line or product-path repositories, identify product from `research/.progress.yaml` `product_paths[]`, active `research/{slug}/` or `specs/{slug}/` scopes, page metadata, page title, or the alignment page path. Group index entries by category first, then by product/product path within each category, with the repo's existing secondary sort preserved when clear. In flat repositories, group by category, then preserve the existing index organization within each category or use a clear newest-first or title order when creating a new index.
 
-**Research quality contract.** For research-producing outputs, do not synthesize research findings, recommendations, candidate rankings, or working packets until the user approves the research scope from the `review` alignment page's final compiled YAML. Before scope approval, do only minimal discovery needed to propose the research scope, source plan, assumptions, output paths, and approval questions; label any observed files or source availability as scope evidence, not findings. After scope approval, perform the synthesized research and separate and label `claims` (what the report concludes), `evidence` (source, repo artifact or file path, quote or observation, date, and confidence), `inference` (why that evidence supports the claim), `assumptions` (what remains unproven), and `decision impact` (what the user should approve, reject, or correct). Do not collapse evidence and inference into unsupported summary prose.
+**Research quality contract.** For research-producing outputs, do not synthesize research findings, recommendations, candidate rankings, or working packets until the user approves the research scope from the `review` alignment page's final compiled response YAML. Before scope approval, do only minimal discovery needed to propose the research scope, source plan, assumptions, output paths, and approval questions; label any observed files or source availability as scope evidence, not findings. After scope approval, perform the synthesized research and separate and label `claims` (what the report concludes), `evidence` (source, repo artifact or file path, quote or observation, date, and confidence), `inference` (why that evidence supports the claim), `assumptions` (what remains unproven), and `decision impact` (what the user should approve, reject, or correct). Do not collapse evidence and inference into unsupported summary prose.
 
 **Embed prohibition.** Do not use `<object>`, `<iframe>`, `<embed>`, or "open working packet" / "view full document" links as the primary rendering of any proposed deliverable, evidence matrix, interview log, or manifest entry. The alignment page HTML must contain the rendered content directly. Embedded or linked external documents are permitted only as supplemental references alongside the fully rendered content already present in the page. **Exception:** Self-contained inline `<canvas>` and `<svg>` elements are permitted for charts and diagrams within the same HTML file.
 
@@ -57,7 +57,7 @@ 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 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 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. Feedback-only YAML revises the working packet and review page, then remains in Stage 2. Stage 3 consumes final compiled YAML for artifact approval only when it has 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, 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.
 
 **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.
 
@@ -65,24 +65,24 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Required inline questions.** In `review` pages, each gate must contain at least one required inline question placed directly under the content it governs, inside a visually distinct question block. Each question must use radio-button inputs and include two standing options after the skill-generated choices: "Other / None of the above" backed by a multi-line text box for free-form input, and "Need clarification" backed by an optional notes box where the user can explain what is unclear. When any radio option other than "Other" or "Need clarification" is selected, show an optional "Additional notes" text box beneath it so the user can qualify their choice. Generate questions based on what genuinely needs user input -- do not add filler questions. Do not create a separate bottom "Decisions & Clarifications" section. Confirmed pages must not keep these as required input controls; render the answered decisions as read-only records.
 
-**Section feedback controls.** Every major section of the page (each deliverable section, evidence matrix, confidence register, gate, and any anchor-linked top-level heading) carries a lightweight section-feedback control near its heading: three mutually exclusive choices -- "emphasize" (add more weight to this section or to the point named in the notes), thumbs down (reject or flag a concern), and "clarification needed". Selecting any one reveals a multi-line section-feedback textarea placed directly under or beside that section's emphasize/down/clarify controls; deselecting hides the textarea and any local feedback YAML output for that section. This textarea is separate from required gate-question text inputs: even when the same section has gate questions with their own text boxes, selecting emphasize/down/clarify must still reveal the section-feedback textarea near the feedback controls. Use `--green` for active "emphasize", `--red` for the active thumbs-down, and `--orange` for active "clarification needed", with muted/inactive states otherwise. These controls are optional for final approval and do not replace required gate questions. They also power the separate feedback-only YAML path so the user can send emphasis requests, concerns, or clarification requests before answering every required gate question. When a section contains nested subsections (h3 or deeper), duplicate the section-feedback control at the bottom of the section, just before the closing `</section>` tag. The bottom copy mirrors the top copy — same `data-section`, same id with a `-bottom` suffix, same button set. Sections without nested subsections keep only the top control. Pair top and bottom controls by matching `data-section` attribute. When a feedback button is clicked on one copy, mirror the active state, `has-feedback` class, and `dataset.feedback` value to the paired copy. Textarea content should sync on compile — whichever textarea has content takes precedence (prefer the one the user last typed in). Both copies' local compile/copy buttons produce the same YAML. Use the top copy's `id` (without `-bottom`) as the canonical feedback id for YAML output.
+**Section feedback controls.** Every major section of the page (each deliverable section, evidence matrix, confidence register, gate, and any anchor-linked top-level heading) carries a lightweight section-feedback control near its heading: three mutually exclusive choices -- "emphasize" (add more weight to this section or to the point named in the notes), thumbs down (reject or flag a concern), and "clarification needed". The section feedback textarea, local compile/copy controls, and local read-only YAML output are hidden by default. Selecting any one feedback choice reveals a multi-line section-feedback textarea plus local "Compile Feedback YAML", "Copy YAML", and read-only YAML controls placed directly under or beside that section's emphasize/down/clarify controls; deselecting the active choice hides the textarea, local compile/copy controls, and local read-only YAML output again and omits that section from compiled responses. This textarea is separate from required gate-question text inputs: even when the same section has gate questions with their own text boxes, selecting emphasize/down/clarify must still reveal the section-feedback textarea near the feedback controls. Use `--green` for active "emphasize", `--red` for the active thumbs-down, and `--orange` for active "clarification needed", with muted/inactive states otherwise. These controls are optional for final approval and do not replace required gate questions. They also contribute `section_feedback` entries to the unified response payload so the user can send emphasis requests, concerns, or clarification requests before answering every required gate question. When a section contains nested subsections (h3 or deeper), duplicate the section-feedback control at the bottom of the section, just before the closing `</section>` tag. The bottom copy mirrors the top copy — same `data-section`, same id with a `-bottom` suffix, same button set. Sections without nested subsections keep only the top control. Pair top and bottom controls by matching `data-section` attribute. When a feedback button is clicked on one copy, mirror the active state, `has-feedback` class, and `dataset.feedback` value to the paired copy. Textarea content should sync on compile — whichever textarea has content takes precedence (prefer the one the user last typed in). Both copies' local compile/copy buttons produce the same YAML. Use the top copy's `id` (without `-bottom`) as the canonical feedback id for YAML output.
 
-**Feedback-only YAML contract.** Provide feedback-only YAML in two places: locally under each selected section-feedback textarea, and globally in the bottom compile section. When a section-feedback control is selected, show local "Compile Feedback YAML" and "Copy YAML" controls plus a read-only YAML textarea directly under that section's feedback textarea. The local feedback compile generates YAML with `alignment_page: alignment/prototype-{topic}.html`, `feedback_status: revision-request`, `approval_status: not-approved`, `unanswered_required_questions`, and a `section_feedback` list containing the single selected section-feedback entry for that local control. The bottom "Compile Feedback YAML" control generates the same YAML shape but aggregates every selected section-feedback entry on the page. Enable both local and bottom feedback compile controls as soon as at least one section-feedback control is set, even if required inline gate questions are unanswered. Populate `alignment_page` from the known repo-relative output path used to write the HTML page, not from the page title, browser URL, window location, or any display label. Each feedback entry uses the shape `section`, `feedback` (`emphasize`, `down`, or `needs-clarification`), optional `notes` from that section's feedback textarea, and `requested_agent_action` (`add-weight-to-section`, `investigate-and-revise`, or `clarify-before-approval`). For `emphasize` feedback, the YAML must make clear that the agent should add more weight, prominence, evidence, detail, or recommendation emphasis to that section or to the specific point named in the notes; this is a revision request, not approval of the section as-is. For `down` and `needs-clarification` feedback, the YAML must make clear that the agent should evaluate the feedback, investigate further when needed, and contextually amend the HTML alignment page before asking again for final approval answers. Automatically attempt to copy feedback YAML to the clipboard, display local or bottom copy status, display it in the matching read-only textarea, and provide a "Copy YAML" button with the same retry and fallback behavior as final gate YAML. Do not render the bottom feedback compile controls as a sticky or fixed banner.
+**Section feedback YAML contract.** Provide local section-feedback YAML only under each selected section-feedback textarea. When a section-feedback control is selected, show local "Compile Feedback YAML" and "Copy YAML" controls plus a read-only YAML textarea directly under that section's feedback textarea; when the control is deselected, hide those local controls and output again. The local feedback compile generates YAML with `alignment_page: alignment/prototype-{topic}.html`, `feedback_status: revision-request`, `approval_status: not-approved`, `unanswered_required_questions`, and a `section_feedback` list containing the single selected section-feedback entry for that local control. Enable local feedback compile controls as soon as that section-feedback control is set, even if required inline gate questions are unanswered. Populate `alignment_page` from the known repo-relative output path used to write the HTML page, not from the page title, browser URL, window location, or any display label. Each feedback entry uses the shape `section`, `feedback` (`emphasize`, `down`, or `needs-clarification`), optional `notes` from that section's feedback textarea, and `requested_agent_action` (`add-weight-to-section`, `investigate-and-revise`, or `clarify-before-approval`). For `emphasize` feedback, the YAML must make clear that the agent should add more weight, prominence, evidence, detail, or recommendation emphasis to that section or to the specific point named in the notes; this is a revision request, not approval of the section as-is. For `down` and `needs-clarification` feedback, the YAML must make clear that the agent should evaluate the feedback, investigate further when needed, and contextually amend the HTML alignment page before asking again for final approval responses. Automatically attempt to copy local feedback YAML to the clipboard, display local copy status, display it in the matching read-only textarea, and provide a "Copy YAML" button with the same retry and fallback behavior as response YAML.
 
-**Gate YAML contract.** In `review` pages, at the bottom of the page, include an ordinary in-flow compile section with a "Compile Feedback YAML" button for selected section feedback and a separate "Compile Answers" button for final approval answers. The bottom compile section must not be sticky, fixed, floating, or styled as a persistent banner. The "Compile Answers" button aggregates answers from all inline gate questions throughout the page, including free-text notes. The final approval button remains disabled until every required question has a selection, shows a count of remaining unanswered questions, and scrolls to the first unanswered question if clicked early. When every question is answered, generate a structured YAML block with `alignment_page: alignment/prototype-{topic}.html`, `approval_status: ready-for-agent-review`, one item per gate answer using this stable shape: `section`, `gate_type`, `status` (`answered`, `other`, or `needs-clarification`), `answer`, optional `notes`, and optional `target_artifact` or `target_path` when the gate controls file output. Populate `alignment_page` from the known repo-relative output path used to write the HTML page, not from the page title, browser URL, window location, or any display label. The same final compiled output also includes any section-feedback controls that the user set, using the `section_feedback` shape from the feedback-only YAML contract. After successful compilation, automatically attempt to copy the YAML to the clipboard with the Clipboard API, display copy status, and display the YAML in a read-only textarea with an explicit "Copy YAML" button. The copy button must retry clipboard copy when supported and fall back to selecting the textarea contents when clipboard access is unavailable or blocked.
+**Response YAML contract.** In `review` pages, at the bottom of the page, include an ordinary in-flow compile section with a single "Compile Responses" button. The bottom compile section must not be sticky, fixed, floating, or styled as a persistent banner. "Compile Responses" aggregates all answered inline gate questions throughout the page, including free-text notes, plus every selected section-feedback entry. Enable it as soon as at least one gate question has an answer or at least one section-feedback control is selected; do not require every required gate question to be answered before compiling partial responses. If clicked with no answered gates and no selected section feedback, show a response status that asks the user to answer a gate question or select section feedback. The compiled YAML is a mixed response payload with `alignment_page: alignment/prototype-{topic}.html`, `response_status` (`partial` or `complete`), `approval_status` (`not-approved` or `ready-for-agent-review`), `required_gate_status` (`incomplete` or `complete`), and `unanswered_required_questions`. It may include a `gate_answers` list where each answered gate item preserves the stable gate-answer shape: `section`, `gate_type`, `status` (`answered`, `other`, or `needs-clarification`), `answer`, optional `notes`, and optional `target_artifact` or `target_path` when the gate controls file output. It may also include a `section_feedback` list using the section-feedback shape from the section feedback YAML contract. Set `approval_status: ready-for-agent-review` only when every required gate is answered and there are no unresolved `down`, unresolved `needs-clarification`, or other unresolved negative feedback items; otherwise set `approval_status: not-approved` and keep the response in review. Populate `alignment_page` from the known repo-relative output path used to write the HTML page, not from the page title, browser URL, window location, or any display label. After successful compilation, automatically attempt to copy the YAML to the clipboard with the Clipboard API, display copy status, and display the YAML in a read-only textarea with an explicit "Copy YAML" button. The copy button must retry clipboard copy when supported and fall back to selecting the textarea contents when clipboard access is unavailable or blocked.
 
-**Confirmed page contract.** After final approval has been applied, convert the active alignment page from `review` to `confirmed`. Include a visible status block with `alignment_status: confirmed`, confirmation date, confirmed artifact paths, approval source summary, and explicit finished but amendable language: the page is current for the completed alignment cycle, and later research can amend it only by archiving the prior confirmed page and highlighting the amendment. Remove required gate-question controls, the final "Compile Answers" button, unanswered-question counters, disabled approval buttons, and approval-blocking language. Preserve the full research and approval record: answered decisions, user requests, evidence matrix, assumptions/confidence register, source gaps, proposed file changes, final compiled YAML or faithful approval summary, and what changed during confirmation. Keep research caveats visible; `confirmed` means approved/current, not immutable or permanently true.
+**Confirmed page contract.** After final approval has been applied, convert the active alignment page from `review` to `confirmed`. Include a visible status block with `alignment_status: confirmed`, confirmation date, confirmed artifact paths, approval source summary, and explicit finished but amendable language: the page is current for the completed alignment cycle, and later research can amend it only by archiving the prior confirmed page and highlighting the amendment. Remove required gate-question controls, section feedback input controls, local compile/copy controls, local read-only YAML outputs, the final "Compile Responses" button, response counters, disabled approval buttons, and approval-blocking language. Preserve the full research and approval record: answered decisions, user requests, evidence matrix, assumptions/confidence register, source gaps, proposed file changes, final compiled response YAML or faithful approval summary, and what changed during confirmation. Keep research caveats visible; `confirmed` means approved/current, not immutable or permanently true.
 
-**Pre-approval stop.** While an alignment page is in `review`, the next action is review of the HTML alignment page, not downstream routing. Ask the user to review the page and provide either local or bottom feedback-only YAML for emphasis requests, concerns, or clarification, or final compiled YAML answers when ready. Do not require the user to answer every gate before sending emphasis requests, negative feedback, or clarification needs. When feedback-only YAML is provided, treat it as a revision request: evaluate the feedback, investigate further when needed, archive and amend the HTML page contextually, highlight the changes, and ask again for review. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language until after final compiled YAML has been provided and the approved artifacts have been written or updated.
+**Pre-approval stop.** While an alignment page is in `review`, the next action is review of the HTML alignment page, not downstream routing. Ask the user to review the page and provide either local section-feedback YAML for one section or bottom compiled response YAML for gate answers and/or selected section feedback. Do not require the user to answer every gate before sending emphasis requests, negative feedback, clarification needs, or other partial responses. When compiled response YAML is partial or has `approval_status: not-approved`, treat it as a revision request: evaluate the feedback, investigate further when needed, archive and amend the HTML page contextually, highlight the changes, and ask again for review. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language until after final compiled response YAML with `approval_status: ready-for-agent-review` has been provided and the approved artifacts have been written or updated.
 
-**After approval handling.** When final compiled YAML is provided, inspect it before confirming the page. If it contains approvals plus user-requested edits, first update the page, research, and proposed canonical artifacts to satisfy the request; then write or update the approved canonical artifacts and confirm the page. If it contains `needs-clarification`, unresolved `down` feedback, or any unresolved negative feedback, revise the page and return it to `review` instead of marking it `confirmed`. Before replacing any existing alignment page, archive it to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/prototype-{topic}.html`. Future amendments to confirmed pages follow the same archive-first rule and must show what changed from the prior confirmed record.
+**After approval handling.** When final compiled response YAML with `approval_status: ready-for-agent-review` is provided, inspect it before confirming the page. If it contains approvals plus user-requested edits, first update the page, research, and proposed canonical artifacts to satisfy the request; then write or update the approved canonical artifacts and confirm the page. If it contains `needs-clarification`, unresolved `down` feedback, or any unresolved negative feedback, revise the page and return it to `review` instead of marking it `confirmed`. Before replacing any existing alignment page, archive it to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/prototype-{topic}.html`. Future amendments to confirmed pages follow the same archive-first rule and must show what changed from the prior confirmed record.
 
 **Diff highlighting on updates.** When the agent updates an existing alignment page after receiving feedback, compiled answers, confirmation edits, or later amendment evidence, the rendered HTML must visibly indicate what changed since the previous version. Highlight changed sections or blocks in-place with a `Changed`/`Updated` badge, distinct border or background, `<ins>`/`<del>` markup, or a side-by-side before/after comparison when that is clearer. A top-level change summary is useful but not sufficient by itself unless the changed content is also visibly marked where the reader reviews it. Remove or refresh stale change markers on later updates so the highlights describe the current revision only.
 
 **Archiving.** Before replacing an existing alignment page, archive it to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/prototype-{topic}.html`.
 
-**Brief Me (text-to-speech).** Every alignment page must include a `<script src="../scripts/alignment-tts-kokoro.js"></script>` tag before `</body>`. The script adds a "Brief Me" button that reads the page aloud section-by-section using Kokoro TTS (an 82M-parameter model running client-side via WebGPU/WASM from `kokoro-js`). The transport bar includes play/pause/stop/skip controls, a voice selector (persisted in localStorage), and speed selection. On first click the voice model downloads (~92MB quantized on WASM; ~326MB fp32 on WebGPU). Weights persist between visits via Cache API origin storage, and this works on `file://` origins in Chrome — including `file://wsl.localhost` UNC paths (verified 2026-06-09 with an instrumented probe in Windows Chrome: `caches` is available, entries survive reloads and browser restarts, and Chrome shares a single `file://` origin across all local pages, so one download serves every alignment page). Repeat visits pay model initialization only, not re-download. If `caches` is undefined (non-Chromium or locked-down browsers), the model re-downloads each visit; serving pages from a local HTTP origin (e.g. `node scripts/serve-alignment.mjs` in the repo root, then `http://localhost:8907/alignment/<page>.html`) guarantees caching there — note `http://localhost` is a separate origin from `file://`, so the first localhost visit downloads once even when the `file://` cache is already warm. After the first successful load on a machine, the script preloads the model during browser idle time on later page loads (gated by a `tts-kokoro-used` localStorage flag, so users who never click pay nothing). Text is prepared for speech before synthesis: block boundaries (headings, paragraphs, list items, table cells) get sentence punctuation so the model does not read them as run-ons, and speech-hostile symbols are normalized (`~92MB` reads as "approximately 92MB", `v0.3` as "version 0.3", em-dashes as comma pauses, `e.g.`/`i.e.`/`vs.` expanded). Synthesis is pipelined with small chunks: the first audio chunk is kept short (~250 chars) for fast time-to-first-audio, later chunks stay small (~300 chars, cut at sentence or clause boundaries) with up to two chunks synthesizing ahead during playback, and the next section's opening chunk is prefetched while the current section's last chunk plays, so chunk and section boundaries are gapless. If Kokoro fails to load (old browser, network error), it falls back to the Web Speech API automatically. It skips gate controls, compile UI, feedback textareas, and stat grids. Charts and tables use narrative summaries instead of raw data: containers with a `data-tts-narrative` attribute have the narrative read aloud; containers without the attribute are silently skipped. To inject TTS into existing pages, run `node scripts/inject-tts.mjs` (idempotent). Use `--force` to replace the existing TTS block with an updated version. Do not inline the TTS script; always use the `src` tag. Do not use `type="module"` — module scripts are blocked by CORS on `file://` URLs.
+**Brief Me (text-to-speech).** Every alignment page must include a `<script src="../scripts/alignment-tts-kokoro.js"></script>` tag before `</body>`. The script adds a "Brief Me" button that reads the page aloud section-by-section using Kokoro TTS (an 82M-parameter model running client-side via WebGPU/WASM from `kokoro-js`). The transport bar includes play/pause/stop/skip controls, a voice selector (persisted in localStorage), and speed selection. On first click the voice model downloads (~92MB quantized on WASM; ~326MB fp32 on WebGPU). Weights persist between visits via Cache API origin storage, and this works on `file://` origins in Chrome — including `file://wsl.localhost` UNC paths (verified 2026-06-09 with an instrumented probe in Windows Chrome: `caches` is available, entries survive reloads and browser restarts, and Chrome shares a single `file://` origin across all local pages, so one download serves every alignment page). Repeat visits pay model initialization only, not re-download. If `caches` is undefined (non-Chromium or locked-down browsers), the model re-downloads each visit; serving pages from a local HTTP origin (e.g. `node scripts/serve-alignment.mjs` in the repo root, then `http://localhost:8907/alignment/<page>.html`) guarantees caching there — note `http://localhost` is a separate origin from `file://`, so the first localhost visit downloads once even when the `file://` cache is already warm. After the first successful load on a machine, the script preloads the model during browser idle time on later page loads (gated by a `tts-kokoro-used` localStorage flag, so users who never click pay nothing). Text is prepared for speech before synthesis: block boundaries (headings, paragraphs, list items, table cells) get sentence punctuation so the model does not read them as run-ons, and speech-hostile symbols are normalized (`~92MB` reads as "approximately 92MB", `v0.3` as "version 0.3", em-dashes as comma pauses, `e.g.`/`i.e.`/`vs.` expanded). Synthesis is pipelined with small chunks: the first audio chunk is kept short (~250 chars) for fast time-to-first-audio, later chunks stay small (~300 chars, cut at sentence or clause boundaries) with up to two chunks synthesizing ahead during playback, and the next section's opening chunk is prefetched while the current section's last chunk plays, so chunk and section boundaries are gapless. If Kokoro fails to load (old browser, network error), it falls back to the Web Speech API automatically. It skips gate controls, compile UI, feedback textareas, and stat grids. Charts and tables use narrative summaries instead of raw data: containers with a `data-tts-narrative` attribute have the narrative read aloud; containers without the attribute are silently skipped. To inject TTS into existing pages, run `node scripts/inject-tts.mjs` (idempotent). Use `--force` to replace the existing TTS block with an updated version. Do not inline the TTS script; always use the `src` tag. Do not use `type="module"` — module scripts are blocked by CORS on `file://` URLs. Narration follows along visually: the blocks currently being read (paragraphs, list items, table rows, headings, chart narratives) receive a `.tts-active-chunk` highlight at ~1–2-sentence chunk granularity, and the page auto-scrolls to keep them centered (instantly rather than smoothly under `prefers-reduced-motion: reduce`), while the active section keeps a lightened outline frame. The Web Speech fallback stays section-level — outline plus section-start scroll, no per-chunk highlight.
 
 **TTS narrative contract.** Every `.chart-container` and `.table-wrap` element should carry a `data-tts-narrative` attribute with a 1-3 sentence human-readable summary of what the chart or table shows. Chart functions in `scripts/alignment-chart-snippets.js` auto-generate a baseline narrative from their data; author-provided `data-tts-narrative` attributes take precedence. When authoring alignment pages manually, add `data-tts-narrative` to chart containers and table wrappers so that Brief Me reads a meaningful summary instead of skipping the element.
 
-**Browser open.** After writing the resulting HTML page, run `node scripts/open-html-page.mjs alignment/prototype-{topic}.html --browser auto` from the repository root, replacing the path with the actual page path when needed. Report the script status (`focused`, `opened`, `fallback-opened`, `blocked`, or `failed`) in the handoff. Continue when opening is `blocked` if the files were written and verified correctly; a blocked browser-open attempt does not make the skill fail.
+**Browser open.** After writing the resulting HTML page, attempt to open it from the repository root with this ordered fallback, replacing `alignment/prototype-{topic}.html` with the actual page path when needed. First, if `scripts/open-html-page.mjs` exists, run `node scripts/open-html-page.mjs alignment/prototype-{topic}.html --browser auto`. If the helper is missing or cannot open the page and the environment is WSL (`grep -qi microsoft /proc/version`) with `/mnt/c/WINDOWS/System32/WindowsPowerShell/v1.0/powershell.exe` available, open a browser-friendly file URI through PowerShell: build `file://wsl.localhost/${WSL_DISTRO_NAME:-Ubuntu}/<absolute-linux-path>` from the HTML page's absolute path and run PowerShell `Start-Process '<file-uri>'`. Try `xdg-open <absolute-linux-path>` only after the helper path and WSL PowerShell bridge are unavailable or blocked. Report the final status (`focused`, `opened`, `fallback-opened`, `blocked`, or `failed`) in the handoff, and include the absolute path when the status is `blocked` or `failed`. Continue when opening is `blocked` if the files were written and verified correctly; a blocked browser-open attempt does not make the skill fail.

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

@@ -1,5 +1,9 @@
 # Changelog
 
+## v0.12 - 2026-06-11
+
+- Added npm-aware install-route wording for product-testing and cross-pack recommendations while preserving Claude `/pack install ...` routes.
+
 ## v0.11 - 2026-06-10
 
 - Converted the hand-authored alignment-page section to the generator-owned stub plus a bundled `ALIGNMENT-PAGE.md`; the page contract now follows the full shared convention (lifecycle states, central alignment index, section feedback, gate/feedback YAML, TTS, browser open) with the prototype-specific gates from the generator gate map.

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

@@ -2,7 +2,7 @@
 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: v0.11
+version: v0.12
 argument-hint: "[optional: topic, --variant N]"
 visual_tier: prototype
 ---
@@ -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` first)
+> 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.
 
@@ -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, prepend `/pack install <pack-name>` to the recommendation.
+- 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