skillpacks 0.1.0 → 0.1.1

package/packs/alignment-page-admin/codex/upgrade-alignment-pages/SKILL.md

@@ -2,7 +2,7 @@
 name: upgrade-alignment-pages
 description: Audit and explicitly upgrade generated alignment/*.html review pages to the current local alignment-page standard while preserving page-specific context
 type: ops
-version: v0.1
+version: v0.2
 argument-hint: "[--repo <path>] [--apply] [alignment/*.html...]"
 ---
 
@@ -35,7 +35,7 @@ Use this skill when a repository already has generated `alignment/*.html` review
 2. Load local standards:
    - Read applicable local convention sources from `AGENTS.md`, `CLAUDE.md`, and active bundled `ALIGNMENT-PAGE.md` files found under `global/`, `packs/`, `.claude/skills/`, and `.codex/skills/`.
    - Treat those local files as read-only standards. Do not fetch external standards.
-   - Extract the current required HTML behaviors: dark-mode styling, inline approval gates, section feedback controls, feedback-only YAML, final answer YAML, copy fallback behavior, unanswered-question handling, archive-before-replace behavior, and diff/change highlighting for updates.
+   - Extract the current required HTML behaviors: dark-mode styling, inline approval gates, section feedback controls, local section feedback YAML, unified response YAML, copy fallback behavior, unanswered-question handling, archive-before-replace behavior, and diff/change highlighting for updates.
 
 3. Audit every selected page:
    - Read the whole HTML file before judging it.

package/packs/alignment-page-admin/codex/upgrade-alignment-pages/archive/v0.1/SKILL.md

@@ -0,0 +1,106 @@
+---
+name: upgrade-alignment-pages
+description: Audit and explicitly upgrade generated alignment/*.html review pages to the current local alignment-page standard while preserving page-specific context
+type: ops
+version: v0.1
+argument-hint: "[--repo <path>] [--apply] [alignment/*.html...]"
+---
+
+# Upgrade Alignment Pages
+
+Invoke as `$upgrade-alignment-pages`.
+
+Use this skill when a repository already has generated `alignment/*.html` review pages and the user wants to audit or update them against the current local alignment-page convention. This skill targets generated alignment HTML artifacts only.
+
+## Inputs
+
+- Default target repository: current working directory.
+- Optional `--repo <path>` to target another repository.
+- Optional explicit page paths under the target repository's `alignment/` directory.
+- Optional `--apply`, or clear user wording such as "apply the upgrade" or "upgrade these pages", to allow page rewrites.
+
+## Mode
+
+- Default mode is audit/dry-run.
+- The skill name alone is not apply intent; do not modify files unless the visible user request explicitly asks to apply or upgrade existing pages.
+- In audit/dry-run mode, inspect pages and report drift without creating, editing, moving, or deleting any files.
+
+## Process
+
+1. Resolve scope:
+   - Locate the project-root `alignment/` directory; stop if absent.
+   - Enumerate `alignment/*.html`, excluding `alignment/index.html`.
+   - If the user provided page paths, include only those paths after confirming they are inside the project-root `alignment/` directory.
+
+2. Load local standards:
+   - Read applicable local convention sources from `AGENTS.md`, `CLAUDE.md`, and active bundled `ALIGNMENT-PAGE.md` files found under `global/`, `packs/`, `.claude/skills/`, and `.codex/skills/`.
+   - Treat those local files as read-only standards. Do not fetch external standards.
+   - Extract the current required HTML behaviors: dark-mode styling, inline approval gates, section feedback controls, feedback-only YAML, final answer YAML, copy fallback behavior, unanswered-question handling, archive-before-replace behavior, and diff/change highlighting for updates.
+
+3. Audit every selected page:
+   - Read the whole HTML file before judging it.
+   - Identify page-specific substance: title, meta/context, research findings, evidence/source matrices, assumptions, decisions, open questions, approval gates, review notes, proposed file changes, prior user feedback, and any page-specific scripts.
+   - Report missing or stale standard features per page.
+   - Classify each page as `current`, `upgrade-needed`, or `blocked-content-loss-risk`.
+
+4. Stop on content-loss risk:
+   - If a page's structure is too ambiguous to upgrade while preserving substantive content, do not rewrite it.
+   - Report exactly what content could not be mapped and what human decision is needed.
+
+4b. Batch-mode handoff (apply mode only):
+   - Count pages classified as `upgrade-needed` (excluding `blocked-content-loss-risk`).
+   - If count > 2:
+     - Generate a phase in `tasks/todo.md` titled "## Phase: Upgrade Alignment Pages" with:
+       - Execution Profile: serial
+       - A Context block listing the standards sources discovered in step 2 and the archive timestamp path (`docs/history/archive/YYYY-MM-DD/HHMMSS/`)
+       - One checklist step per upgrade-needed page: `- [ ] Upgrade alignment/<filename>.html — archive original, rewrite to current standard preserving all content, verify content preservation`
+       - A final step: `- [ ] Run $compile-central-alignment and verify all archives; commit and push`
+       - Acceptance criteria matching the audit findings
+     - If `tasks/todo.md` already has unchecked items, append the phase at the bottom with a separator (`---`) and warn the user about pre-existing items.
+     - Output the full audit report.
+     - Report: "Generated exec-loop task plan with N steps. Recommended next command: $exec"
+     - Stop. Do not modify any HTML files.
+   - If count <= 2: proceed to step 5 (inline apply).
+
+5. Apply only when explicit:
+   - Before replacing each page, archive the original to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/<filename>.html`.
+   - Rewrite the page contextually from the original, preserving page-specific research, decisions, questions, gates, review context, and user feedback.
+   - Add or modernize missing standard elements without replacing the page with a generic template.
+   - Preserve relative links and keep the page self-contained unless the original already used explicit external resources.
+   - Highlight upgrade changes where useful with inline notes, a change summary section, or scoped diff styling.
+
+6. Verify after apply:
+   - Confirm every changed page has a matching archive copy.
+   - Re-open each changed page textually and confirm the preserved title, decisions/findings, questions, and gates still exist.
+   - Run or recommend `$compile-central-alignment` so `alignment/index.html` reflects updated page metadata.
+
+## Audit Report
+
+Include:
+
+- Target repository and mode.
+- Standards sources read.
+- Pages inspected and pages excluded.
+- Per-page status with missing standard features.
+- Content preservation risks or blockers.
+- In apply mode, archive paths and changed page paths.
+- Verification performed.
+- Next action: usually `$compile-central-alignment` after successful apply, or no mutation needed when all pages are current.
+- In batch mode: the generated `tasks/todo.md` phase with exec-loop steps and the recommended `$exec` command.
+
+## Constraints
+
+- Do not edit `CLAUDE.md`, `AGENTS.md`, any `SKILL.md`, or any bundled `ALIGNMENT-PAGE.md` file.
+- Do not modify non-alignment HTML files.
+- Do not modify `alignment/index.html`; leave index regeneration to `$compile-central-alignment`.
+- Do not rewrite pages in audit/dry-run mode.
+- Do not replace page-specific content with a generic template.
+- Stop and report when an upgrade is likely to lose research, decisions, questions, gates, or review context.
+- Do not create or modify GitHub Actions workflows.
+
+## Default Shipping Contract
+
+- **Audit mode:** no file mutations; no commit or push.
+- **Apply mode (inline, ≤2 pages):** modified generated alignment pages and archive copies are normal repo artifacts. Follow the target repository's shipping rules after verification.
+- **Apply mode (batch, >2 pages):** generates `tasks/todo.md` phase only; does not modify any HTML files. Commit the task plan, then hand off to `$exec`.
+- **Default next-step routing:** after successful inline apply, `Recommended next command: $compile-central-alignment`; after batch-mode handoff, `Recommended next command: $exec`; otherwise report the audit result and recommend no follow-up skill when no upgrades are needed.

package/packs/business-growth/claude/experiment/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.
 
@@ -57,30 +57,30 @@ 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-experiment-research.md`; product-path mode uses `research/{slug}/_working/preliminary-experiment-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-experiment-research.md`; product-path mode uses `research/{slug}/_working/preliminary-experiment-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.
 
 **Risk-validation gates.** Render assumption/risk evidence coverage, confidence, candidate verdicts or mitigations, output-location/change-scope decisions, coverage checkpoint, and post-approval route as gates. Durable tracker outputs remain canonical markdown artifacts and must also be fully rendered in the alignment page. 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.
 
 **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/experiment-{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/experiment-{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/experiment-{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/experiment-{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/experiment-{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/experiment-{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/experiment-{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/experiment-{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/experiment-{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/experiment-{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/business-growth/claude/experiment/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v0.5 - 2026-06-10
+
+- Added npm-aware install-route guidance to the Pack Availability Guard while preserving the runner-specific `/pack install <pack>` route.
+
 ## v0.4 - 2026-06-07
 
 - Routed invalidated customer-fit assumptions to `/customer-discovery` instead of the retired `/icp` executable while preserving `research/icp.md` evidence usage.

package/packs/business-growth/claude/experiment/SKILL.md

@@ -2,14 +2,14 @@
 name: experiment
 description: Design lean validation experiments — hypothesis, method, success criteria, sample size, timeline, and decision rules
 type: planning
-version: v0.4
+version: v0.5
 argument-hint: <hypothesis or assumption to test>
 interview_depth: light
 ---
 
 ## 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.
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `/pack install <pack>` inside Claude Code, or `npx skillpacks install <pack>` from the project shell. After install, tell Claude users to run `/reload-skills`, then `/clear` or restart if the skill remains invisible. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # Experiment — Lean Validation Design
 

package/packs/business-growth/claude/experiment/archive/v0.4/SKILL.md

@@ -0,0 +1,282 @@
+---
+name: experiment
+description: Design lean validation experiments — hypothesis, method, success criteria, sample size, timeline, and decision rules
+type: planning
+version: v0.4
+argument-hint: <hypothesis or assumption to test>
+interview_depth: light
+---
+
+## 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.
+
+# Experiment — Lean Validation Design
+
+Takes a hypothesis (from `/assumption-tracker` or user) and designs a cheap, fast validation experiment. Covers landing page tests, fake-door tests, concierge MVPs, surveys, A/B tests, pricing tests, and smoke tests. Outputs a structured plan with hypothesis, method, success criteria, sample size, timeline, and decision rules.
+
+## Soft Prerequisites
+
+- Read `research/assumption-tracker.md` if it exists — pulls the highest-priority unvalidated assumption
+- Read `research/icp.md` if it exists — grounds experiment design in who the target is
+- Read `research/metrics.md` if it exists — aligns success criteria with existing metric definitions
+- Read `research/gtm.md` if it exists — leverages channel strategy for reaching test subjects
+
+## 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. Product Path Manifest
+
+Read `research/.progress.yaml` when present. Normalize `active_path` (singular legacy) to `active_paths` (plural list) when reading; treat legacy `abandoned` as `archived` and exclude archived/deferred/revisit/promoted paths plus `research/_archive/` scopes from active target selection. Scope experiment design to the active product path by default. When experiment results validate or invalidate assumptions about a deferred product path, add a `## Product Path Implications` section recommending `/product-line activate` or `/product-line archive` as appropriate.
+
+### 2. Parse Input & Load Context
+
+**Read `$ARGUMENTS`:**
+- If it's a specific hypothesis or assumption: use it directly
+- If it's a reference to an assumption number (e.g., "#3"): look it up in `research/assumption-tracker.md`
+- If empty: check `research/assumption-tracker.md` for the highest-priority unvalidated assumption. If no tracker exists, ask the user what they want to test.
+
+**Load context:** Read available research docs to understand the ICP, channels, metrics, and existing knowledge.
+
+### 3. Structure the Hypothesis
+
+Convert the input into a structured hypothesis:
+
+**Format**: "We believe that [target segment] will [expected behavior] because [rationale]. We'll know this is true when [measurable outcome]."
+
+Use AskUserQuestion to present and refine:
+- "Here's how I've structured the hypothesis. Does this capture what you want to test?"
+- If the hypothesis is too broad, help narrow it to something testable in 1-2 weeks
+
+### 4. Research Experiment Methods
+
+Use WebSearch with **3-5 targeted queries** to find best practices for this type of validation:
+
+1. **Method-specific** — "[experiment type] validation method", "how to test [hypothesis type]"
+2. **Sample size** — "[experiment type] sample size calculator", "minimum viable test size"
+3. **Benchmarks** — "[category] conversion rate benchmark", "[experiment type] typical results"
+4. **Tools** — "[experiment type] tools", "cheapest way to test [hypothesis]"
+
+### 5. Design the Experiment — Present & Validate
+
+Select the most appropriate experiment type and design the full plan:
+
+#### Experiment Types
+
+| Type | Best For | Timeline | Cost |
+|------|----------|----------|------|
+| **Landing page test** | Demand validation, messaging | 1-2 weeks | $50-200 (ads) |
+| **Fake-door test** | Feature demand, willingness to explore | 1 week | $0 (in-product) |
+| **Concierge MVP** | Value delivery, willingness to pay | 2-4 weeks | Time only |
+| **Survey** | Broad sentiment, preference ranking | 3-5 days | $0-100 |
+| **A/B test** | Optimization, messaging variants | 1-2 weeks | $0 (in-product) |
+| **Pricing test** | Willingness to pay, price sensitivity | 1-2 weeks | $50-200 |
+| **Smoke test** | Demand for non-existent feature | 3-5 days | $0-50 |
+| **Pre-sale / LOI** | B2B willingness to pay | 1-2 weeks | Time only |
+| **Wizard of Oz** | Complex feature viability | 2-4 weeks | Time only |
+
+**Present the experiment design to the user.** Use AskUserQuestion to show:
+- Recommended experiment type with rationale (why this method over alternatives)
+- Detailed plan with timeline and cost estimate
+- Success criteria with specific numbers (citing benchmarks from research)
+- Decision rules for both outcomes
+
+Ask:
+- "Does this experiment design feel feasible? Too ambitious or too simple?"
+- "Any resource constraints I should know about? (budget, time, access to users)"
+
+Incorporate feedback before proceeding.
+
+### 6. Define Decision Rules
+
+For each possible outcome, define what happens next:
+
+- **If hypothesis is validated** (success criteria met): What's the next step? (e.g., build the feature, commit to the pricing, double down on the channel)
+- **If hypothesis is invalidated** (criteria not met): What's the pivot? (e.g., test alternative, revisit ICP, change approach)
+- **If results are inconclusive** (between thresholds): What additional data is needed? Run a follow-up experiment or extend the current one?
+
+### 7. Populate Next Steps
+
+Include a **Recommended** item for the current design-stage next step, followed by **Other options**. Separate current next steps from outcome-specific next steps:
+
+Use this format in the output:
+
+```markdown
+## Next Steps
+
+**Recommended:** Run the experiment — the plan is only useful after the evidence is collected
+
+Other options:
+- [2-4 applicable alternatives]
+```
+
+- ALWAYS: Run the experiment (manual step — the plan tells you how)
+- For a newly designed experiment, do not list validation/invalidation commands as current top-level next steps; put those under `## Decision Rules` because they are only valid after results exist.
+- In `### If Validated`: include the next valid command, usually `/customer-feedback [results]` to log evidence, `/assumption-tracker` to mark the assumption validated, or `/roadmap` if the result commits the team to build.
+- In `### If Invalidated`: include `/assumption-tracker` to mark the assumption invalidated, plus `/brainstorm`, `/customer-discovery`, `/gtm`, or `/monetization` only when the failed assumption belongs to that domain.
+- In `### If Inconclusive`: include `/experiment [follow-up]` if the test needs another run, or `/customer-feedback` if qualitative evidence is the missing signal.
+- IF more assumptions remain untested after this design: `/experiment [next assumption]` — Design the next experiment
+- IF enough assumptions are validated after completed results: `/research-roadmap` — Check if research docs need updating based on learnings
+
+### 8. Write Output
+
+Present final plan to user. Ask:
+- "Ready to write this experiment plan? Anything to adjust?"
+
+Only after confirmation, write the output file.
+
+## Output
+
+### `research/experiments/[experiment-name].md` (or `research/{slug}/experiments/[experiment-name].md`)
+
+```markdown
+# Experiment: [Descriptive Name]
+
+> Date designed: [current date]
+> Status: Designed | Running | Completed
+> Assumption: [from assumption-tracker, if applicable — include # reference]
+> Priority: [from assumption-tracker score, if applicable]
+
+## Hypothesis
+
+**We believe that** [target segment]
+**will** [expected behavior]
+**because** [rationale from research]
+
+**We'll know this is true when** [measurable outcome with specific threshold]
+
+## Method
+
+**Type**: [Landing page test / Fake-door / Concierge MVP / Survey / A/B test / Pricing test / Smoke test / Pre-sale / Wizard of Oz]
+**Why this method**: [rationale — why this is the cheapest/fastest way to test this hypothesis]
+
+### Setup
+[Step-by-step instructions for setting up the experiment]
+
+1. [Step 1]
+2. [Step 2]
+3. ...
+
+### Tools Needed
+- [Tool 1] — [purpose]
+- [Tool 2] — [purpose]
+
+### Audience
+**Who**: [specific segment from ICP]
+**How to reach them**: [channel — from GTM if available]
+**Sample size**: [number needed for statistical significance]
+**Recruitment method**: [how to get participants]
+
+## Success Criteria
+
+| Metric | Failure | Inconclusive | Success |
+|--------|---------|--------------|---------|
+| [Primary metric] | < [threshold] | [range] | ≥ [threshold] |
+| [Secondary metric] | < [threshold] | [range] | ≥ [threshold] |
+
+**Benchmarks**: [what industry/competitor data says is typical]
+
+## Timeline
+
+| Phase | Duration | Tasks |
+|-------|----------|-------|
+| Setup | [days] | [what to prepare] |
+| Run | [days] | [data collection period] |
+| Analyze | [days] | [how to analyze results] |
+| **Total** | **[days]** | |
+
+## Budget
+
+| Item | Cost |
+|------|------|
+| [item] | [amount] |
+| **Total** | **[amount]** |
+
+## Decision Rules
+
+### If Validated (success criteria met)
+[Specific next actions — what to build, commit to, or double down on]
+
+### If Invalidated (failure criteria met)
+[Specific pivot — what to change, test next, or abandon]
+
+### If Inconclusive
+[What additional data is needed, whether to extend or redesign]
+
+## Results
+
+> Fill this section after the experiment completes.
+
+**Status**: [Validated / Invalidated / Inconclusive]
+**Date completed**: [date]
+
+### Raw Data
+[Key numbers and observations]
+
+### Analysis
+[What the data shows — connect back to hypothesis]
+
+### Decision
+[What was decided based on the results]
+
+### Learnings
+[What was learned beyond the hypothesis — surprises, side findings]
+
+## Next Steps
+
+**Recommended:** [recommended next step] — [one-line reason grounded in this artifact]
+
+Other options:
+- [conditional items from step 6 — only include items whose conditions are met]
+```
+
+Create the `research/experiments/` directory if it doesn't exist.
+
+## Task Classification
+
+When this skill produces follow-up work, file it by execution semantics:
+
+- Immediately actionable implementation or documentation work goes in `tasks/todo.md`.
+- Human-only external actions tied to automated steps go in `tasks/manual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI/API work stay in `tasks/todo.md`.
+- One-time condition-gated records, baselines, or future measurements go in `tasks/record-todo.md` with source, condition, non-blocking reason, evidence, and promotion rule.
+- Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in `tasks/recurring-todo.md` with cadence, owner/agent, next due, evidence path, and escalation conditions.
+- Do not put non-blocking records or recurring obligations in `tasks/todo.md` unless they have been explicitly promoted into current execution work.
+
+## Constraints
+
+- **One hypothesis per experiment.** If the user has multiple things to test, design separate experiments. Don't bundle.
+- **Cheap and fast.** Every experiment should be completable in 1-4 weeks with minimal budget. If the design is expensive or slow, simplify.
+- **Specific success criteria.** "Users like it" is not a success criterion. "≥40% of landing page visitors click 'Get Early Access'" is.
+- **Present before writing.** Never write output files until the experiment design has been presented and validated.
+- **Include decision rules.** Every experiment must specify what happens for each possible outcome. No experiment should end with "we'll figure it out."
+- **Reference benchmarks.** Success thresholds should be grounded in industry benchmarks or competitor data, not arbitrary numbers.
+- **Don't overdesign.** A simple survey can validate an assumption just as well as an elaborate A/B test. Recommend the simplest method that produces a clear signal.
+
+## Context Gathering
+
+**Step 1 — Scope questions.** Before researching, ask the user 1–3 questions via `AskUserQuestion` to understand: their product/service, target audience, and what they hope to learn or decide from this research.
+
+**Step 2 — Research.** Conduct research scoped by the user's answers.
+
+**Step 3 — Findings validation.** Before building the alignment page, present the 3–5 most important findings and ask the user to validate or correct any critical assumptions.
+
+## 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/experiment-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.