skillpacks 0.1.1 → 0.1.2

package/packs/business-ops/codex/mvp-gap/archive/v0.8/SKILL.md

@@ -0,0 +1,130 @@
+---
+name: mvp-gap
+description: Evaluate codebase against ICP to identify gaps blocking first sales and retention
+type: research
+version: v0.8
+interview_depth: none
+visual_tier: visual
+---
+
+## Pack Availability Guard
+
+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 `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# MVP Gap — Startup Readiness Audit
+
+Invoke as `$mvp-gap`.
+
+## Report-First Approval Gate
+
+Default to scope-first approval: before synthesized research, inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions in a `review` alignment page plus a concise conversation summary.
+
+Do not perform synthesized research, rank candidates, make recommendations, or write working packets or canonical deliverables until final compiled YAML approves the research scope. Minimal pre-approval discovery may identify available files, source categories, and open questions; label it as scope evidence, not findings.
+
+After approved research-scope YAML, perform the research and write only the non-canonical working packet defined in the staged workflow. Then update the `review` alignment page with findings and stop again for feedback-only YAML or final compiled YAML artifact approval before creating or updating canonical research, spec, or task files.
+
+Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.
+
+## Staged Research Workflow
+
+Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
+
+1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML 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 perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML 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-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+3. **Stage 3 - Finalize approved artifacts.** Consume 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 below, and convert the alignment page to `confirmed` with the approval record preserved.
+
+Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.
+
+## Evidence And Feedback Handling
+
+Treat user feedback as input to evaluate, not as automatic ground truth.
+
+- For factual, evidentiary, technical, or source-backed claims: verify against available evidence. If the user appears to misunderstand the evidence or states something factually incorrect, push back clearly and cite the evidence. Do not rewrite findings merely to agree.
+- For taste, brand, positioning preference, risk appetite, prioritization, or other subjective judgment calls: weigh user feedback heavily and adapt the recommendation unless it conflicts with verified evidence.
+- When feedback mixes facts and preference, separate them explicitly: correct the factual part, then incorporate the preference where it is a legitimate judgment call.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## Prerequisites
+
+`research/icp.md` (or `research/{slug}/icp.md`) must exist. If not, tell the user to run `$customer-discovery` first.
+
+## 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. Load Context & Evaluate
+
+1. Read `research/icp.md` (or `research/{slug}/icp.md`), `research/metrics.md` (or `research/{slug}/metrics.md`) (if it exists — check if defined metrics can actually be measured), codebase, README, existing specs (from `specs/` or `specs/{slug}/`), and any in-progress or advisory work from `tasks/` (`tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, `tasks/recurring-todo.md` if they exist).
+2. Evaluate the codebase against the ICP across these dimensions:
+   - **User Journey Coverage** — Can the product replace each step in the current-state journey? If `research/journey-map.md` exists, map each gap to its journey stage.
+   - **Customer Journey Coverage** — Discovery, evaluation, trial, purchase, provisioning, onboarding
+   - **Table-Stakes Gaps** — Auth, error handling, data export, accessibility, docs, notifications
+   - **Integration Gaps** — Required integrations from the ICP's current workflow
+   - **Competitive Differentiation** — Does it deliver the stated value drivers?
+   - **Spec Validation** — For each gap, check `specs/` for existing coverage: "Spec exists — ready to build", "Spec exists — needs expansion", or no spec (suggest `$user-flow-map` when flow/design shape is missing, then `$ux-variations --layout-mode` after flow and UI requirements exist).
+   - **Metrics Tie-In** — If `research/metrics.md` exists, identify which metric(s) indicate each gap is closed. Flag gaps with no closure metric as instrumentation gaps.
+3. Tag each gap: `blocks-first-sale`, `blocks-retention`, or `nice-to-have`. Estimate effort (S/M/L).
+4. If `research/gtm.md` exists, cross-reference build sequence against GTM launch gates. Flag conflicts and gaps deferrable to post-launch.
+5. Provide a prioritised build sequence.
+
+## Deliverables
+
+- `research/mvp-gap.md` (or `research/{slug}/mvp-gap.md`) — Gap analysis with priority tags, evidence, effort estimates, journey stage, closure metric, and spec status for each gap
+
+Each gap in the output should include:
+- _Journey stage:_ [stage from journey-map, or "N/A"]
+- _Closure metric:_ [metric from metrics.md, or "⚠ No metric defined"]
+- _Spec:_ [link to spec + status, or `$user-flow-map [topic]`]
+
+The output file must include a `## Downstream Impact` section (only if conflicts found) and end with a `## Next Steps` section with a **Recommended** item and 2–4 other contextual options. Choose the recommendation by the first matching condition:
+
+1. IF downstream impact is **Major**: `$reconcile-research` — audit and fix affected downstream research documents.
+2. IF a `blocks-first-sale` gap lacks flow/design shape or a full spec: `$user-flow-map [top gap]` — map the highest-priority gap into concrete screen flow, decisions, branches, states, and recovery paths before UI/layout planning.
+3. IF any other gap lacks flow/design shape or a full spec: `$user-flow-map [top gap]` — map the highest-priority unspecced gap from `research/mvp-gap.md` before UI/layout planning.
+4. IF required context is missing: the corresponding research skill (`$journey-map`, `$competitive-analysis`, `$metrics`, or `$brainstorm` when creative alternatives could reduce high-effort gaps).
+5. OTHERWISE: `$roadmap` — sequence the existing specs into implementation phases.
+
+Only recommend `$roadmap` as the primary next step when the MVP gap analysis found no unspecced priority gaps.
+If downstream impact has not been classified yet, run the downstream impact check before finalizing `## Next Steps`.
+
+### Downstream Impact Check
+
+Before finalizing the output, scan existing downstream docs (`research/journey-map.md`, `research/metrics.md`, `research/gtm.md`, `research/monetization.md`, `tasks/roadmap.md`) for conflicts with what was just decided. Classify as None/Minor/Major. If Major (3+ conflicts or foundational gap changes build sequence), recommend `$reconcile-research`.
+
+## Task Classification
+
+When this skill produces follow-up work, file it by execution semantics:
+
+- Immediately actionable implementation or documentation work goes in `tasks/todo.md`.
+- Human-only external actions tied to automated steps go in `tasks/manual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI/API work stay in `tasks/todo.md`.
+- One-time condition-gated records, baselines, or future measurements go in `tasks/record-todo.md` with source, condition, non-blocking reason, evidence, and promotion rule.
+- Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in `tasks/recurring-todo.md` with cadence, owner/agent, next due, evidence path, and escalation conditions.
+- Do not put non-blocking records or recurring obligations in `tasks/todo.md` unless they have been explicitly promoted into current execution work.
+
+## Constraints
+
+- Analysis only — do not make code changes.
+- Every gap must cite specific evidence from the codebase.
+- Prioritise by market impact, not technical interest.
+- Include `$user-flow-map <topic>` prompts for gaps lacking flow/design shape or full specs. Use `$ux-variations --layout-mode <topic>` only when flow and UI requirements already exist but layout alternatives are missing.
+- `## Next Steps` must be the final section in the output file, with a recommended next step and 2–4 other contextual options.
+
+## 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/mvp-gap-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/codex/mvp-gap/archive/v0.9/SKILL.md

@@ -0,0 +1,130 @@
+---
+name: mvp-gap
+description: Evaluate codebase against ICP to identify gaps blocking first sales and retention
+type: research
+version: v0.9
+interview_depth: none
+visual_tier: visual
+---
+
+## Pack Availability Guard
+
+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 `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# MVP Gap — Startup Readiness Audit
+
+Invoke as `$mvp-gap`.
+
+## Report-First Approval Gate
+
+Default to scope-first approval: before synthesized research, inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions in a `review` alignment page plus a concise conversation summary.
+
+Do not perform synthesized research, rank candidates, make recommendations, or write working packets or canonical deliverables until final compiled YAML approves the research scope. Minimal pre-approval discovery may identify available files, source categories, and open questions; label it as scope evidence, not findings.
+
+After approved research-scope YAML, perform the research and write only the non-canonical working packet defined in the staged workflow. Then update the `review` alignment page with findings and stop again for feedback-only YAML or final compiled YAML artifact approval before creating or updating canonical research, spec, or task files.
+
+Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.
+
+## Staged Research Workflow
+
+Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
+
+1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML 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 perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML 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-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+3. **Stage 3 - Finalize approved artifacts.** Consume 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 below, and convert the alignment page to `confirmed` with the approval record preserved.
+
+Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.
+
+## Evidence And Feedback Handling
+
+Treat user feedback as input to evaluate, not as automatic ground truth.
+
+- For factual, evidentiary, technical, or source-backed claims: verify against available evidence. If the user appears to misunderstand the evidence or states something factually incorrect, push back clearly and cite the evidence. Do not rewrite findings merely to agree.
+- For taste, brand, positioning preference, risk appetite, prioritization, or other subjective judgment calls: weigh user feedback heavily and adapt the recommendation unless it conflicts with verified evidence.
+- When feedback mixes facts and preference, separate them explicitly: correct the factual part, then incorporate the preference where it is a legitimate judgment call.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## Prerequisites
+
+`research/icp.md` (or `research/{slug}/icp.md`) must exist. If not, tell the user to run `$customer-discovery` first.
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$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. Load Context & Evaluate
+
+1. Read `research/icp.md` (or `research/{slug}/icp.md`), `research/metrics.md` (or `research/{slug}/metrics.md`) (if it exists — check if defined metrics can actually be measured), codebase, README, existing specs (from `specs/` or `specs/{slug}/`), and any in-progress or advisory work from `tasks/` (`tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, `tasks/recurring-todo.md` if they exist).
+2. Evaluate the codebase against the ICP across these dimensions:
+   - **User Journey Coverage** — Can the product replace each step in the current-state journey? If `research/journey-map.md` exists, map each gap to its journey stage.
+   - **Customer Journey Coverage** — Discovery, evaluation, trial, purchase, provisioning, onboarding
+   - **Table-Stakes Gaps** — Auth, error handling, data export, accessibility, docs, notifications
+   - **Integration Gaps** — Required integrations from the ICP's current workflow
+   - **Competitive Differentiation** — Does it deliver the stated value drivers?
+   - **Spec Validation** — For each gap, check `specs/` for existing coverage: "Spec exists — ready to build", "Spec exists — needs expansion", or no spec (suggest `$user-flow-map` when flow/design shape is missing, then `$ux-variations --layout-mode` after flow and UI requirements exist).
+   - **Metrics Tie-In** — If `research/metrics.md` exists, identify which metric(s) indicate each gap is closed. Flag gaps with no closure metric as instrumentation gaps.
+3. Tag each gap: `blocks-first-sale`, `blocks-retention`, or `nice-to-have`. Estimate effort (S/M/L).
+4. If `research/gtm.md` exists, cross-reference build sequence against GTM launch gates. Flag conflicts and gaps deferrable to post-launch.
+5. Provide a prioritised build sequence.
+
+## Deliverables
+
+- `research/mvp-gap.md` (or `research/{slug}/mvp-gap.md`) — Gap analysis with priority tags, evidence, effort estimates, journey stage, closure metric, and spec status for each gap
+
+Each gap in the output should include:
+- _Journey stage:_ [stage from journey-map, or "N/A"]
+- _Closure metric:_ [metric from metrics.md, or "⚠ No metric defined"]
+- _Spec:_ [link to spec + status, or `$user-flow-map [topic]`]
+
+The output file must include a `## Downstream Impact` section (only if conflicts found) and end with a `## Next Steps` section with a **Recommended** item and 2–4 other contextual options. Choose the recommendation by the first matching condition:
+
+1. IF downstream impact is **Major**: `$reconcile-research` — audit and fix affected downstream research documents.
+2. IF a `blocks-first-sale` gap lacks flow/design shape or a full spec: `$user-flow-map [top gap]` — map the highest-priority gap into concrete screen flow, decisions, branches, states, and recovery paths before UI/layout planning.
+3. IF any other gap lacks flow/design shape or a full spec: `$user-flow-map [top gap]` — map the highest-priority unspecced gap from `research/mvp-gap.md` before UI/layout planning.
+4. IF required context is missing: the corresponding research skill (`$journey-map`, `$competitive-analysis`, `$metrics`, or `$brainstorm` when creative alternatives could reduce high-effort gaps).
+5. OTHERWISE: `$roadmap` — sequence the existing specs into implementation phases.
+
+Only recommend `$roadmap` as the primary next step when the MVP gap analysis found no unspecced priority gaps.
+If downstream impact has not been classified yet, run the downstream impact check before finalizing `## Next Steps`.
+
+### Downstream Impact Check
+
+Before finalizing the output, scan existing downstream docs (`research/journey-map.md`, `research/metrics.md`, `research/gtm.md`, `research/monetization.md`, `tasks/roadmap.md`) for conflicts with what was just decided. Classify as None/Minor/Major. If Major (3+ conflicts or foundational gap changes build sequence), recommend `$reconcile-research`.
+
+## 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
+
+- Analysis only — do not make code changes.
+- Every gap must cite specific evidence from the codebase.
+- Prioritise by market impact, not technical interest.
+- Include `$user-flow-map <topic>` prompts for gaps lacking flow/design shape or full specs. Use `$ux-variations --layout-mode <topic>` only when flow and UI requirements already exist but layout alternatives are missing.
+- `## Next Steps` must be the final section in the output file, with a recommended next step and 2–4 other contextual options.
+
+## 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/mvp-gap-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/codex/platform-strategy/ALIGNMENT-PAGE.md

@@ -9,6 +9,8 @@ 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.
 
+**Context intake.** This skill declares `context_intake: scoped` (Scoped intake). Ask only the focused questions needed to scope the research or analysis, then validate critical findings before building review artifacts.
+
 **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.
@@ -57,7 +59,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-platform-strategy-research.md`; product-path mode uses `research/{slug}/_working/preliminary-platform-strategy-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-platform-strategy-research.md`; product-path mode uses `research/{slug}/_working/preliminary-platform-strategy-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Research-pack translation.** For business, devtool, game, creator, and media research packs, render the claim/evidence/inference/assumption/decision-impact structure, source coverage categories appropriate to the domain, lower-confidence findings, and downstream implications before asking for approval or routing to the next skill.
 

package/packs/business-ops/codex/platform-strategy/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## v0.11 - 2026-06-12
+
+- Clarified staged research review pages must render complete working-packet substance as structured HTML UI, with raw Markdown packet text allowed only as a supplemental source view.
+
+## v0.10 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.9 - 2026-06-10
 
 - Added npm-aware install-route guidance for business-ops cross-pack recommendations, preserving `$pack install <pack>` inside Codex while offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-ops/codex/platform-strategy/SKILL.md

@@ -2,15 +2,15 @@
 name: platform-strategy
 description: Expand from a single product into a multi-product platform — map vertical and horizontal growth vectors, score candidates, design validation experiments, and sequence the portfolio
 type: research
-version: v0.9
+version: v0.11
 argument-hint: "[optional: expansion direction e.g. \"vertical\", \"horizontal\", or specific adjacent market]"
-interview_depth: light
+context_intake: scoped
 visual_tier: visual
 ---
 
 ## Pack Availability Guard
 
-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 `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. 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 `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # Platform Strategy — Multi-Product Expansion Planning
 
@@ -31,7 +31,7 @@ Do not include `Recommended next skill`, `Recommended next command`, or downstre
 Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
 
 1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML 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 perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
-2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML 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-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML 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-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
 3. **Stage 3 - Finalize approved artifacts.** Consume 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 below, and convert the alignment page to `confirmed` with the approval record preserved.
 
 Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.

package/packs/business-ops/codex/platform-strategy/archive/v0.10/SKILL.md

@@ -0,0 +1,182 @@
+---
+name: platform-strategy
+description: Expand from a single product into a multi-product platform — map vertical and horizontal growth vectors, score candidates, design validation experiments, and sequence the portfolio
+type: research
+version: v0.10
+argument-hint: "[optional: expansion direction e.g. \"vertical\", \"horizontal\", or specific adjacent market]"
+interview_depth: light
+visual_tier: visual
+---
+
+## Pack Availability Guard
+
+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 `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Platform Strategy — Multi-Product Expansion Planning
+
+Invoke as `$platform-strategy`.
+
+## Report-First Approval Gate
+
+Default to scope-first approval: before synthesized research, inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions in a `review` alignment page plus a concise conversation summary.
+
+Do not perform synthesized research, rank candidates, make recommendations, or write working packets or canonical deliverables until final compiled YAML approves the research scope. Minimal pre-approval discovery may identify available files, source categories, and open questions; label it as scope evidence, not findings.
+
+After approved research-scope YAML, perform the research and write only the non-canonical working packet defined in the staged workflow. Then update the `review` alignment page with findings and stop again for feedback-only YAML or final compiled YAML artifact approval before creating or updating canonical research, spec, or task files.
+
+Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.
+
+## Staged Research Workflow
+
+Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
+
+1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML 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 perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML 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-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+3. **Stage 3 - Finalize approved artifacts.** Consume 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 below, and convert the alignment page to `confirmed` with the approval record preserved.
+
+Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.
+
+## Evidence And Feedback Handling
+
+Treat user feedback as input to evaluate, not as automatic ground truth.
+
+- For factual, evidentiary, technical, or source-backed claims: verify against available evidence. If the user appears to misunderstand the evidence or states something factually incorrect, push back clearly and cite the evidence. Do not rewrite findings merely to agree.
+- For taste, brand, positioning preference, risk appetite, prioritization, or other subjective judgment calls: weigh user feedback heavily and adapt the recommendation unless it conflicts with verified evidence.
+- When feedback mixes facts and preference, separate them explicitly: correct the factual part, then incorporate the preference where it is a legitimate judgment call.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## Prerequisites
+
+**Required (at least one):**
+- `research/icp.md` (or `research/{slug}/icp.md`) — who you serve today
+- A working product/codebase to analyse for extensibility
+
+If neither exists, tell the user: "Platform expansion requires a foundation. Run `$customer-discovery` first to define who you serve today, then come back."
+
+**Strongly recommended** (read if they exist):
+- `research/competitive-analysis.md` — market gaps
+- `research/journey-map.md` — user flows, drop-off points
+- `research/metrics.md` — retention, activation baselines
+
+**Optional:** `research/monetization.md`, `research/positioning.md`, `research/customer-feedback.md`, `research/enterprise-icp.md`, `research/assumption-tracker.md`
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$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. Assess Core Product Health
+
+Read the codebase, existing research, and metrics to evaluate: PMF signals (retention, activation, satisfaction), technical extensibility (shared infra — auth, billing, data — vs. tightly coupled), team/resource signals, revenue stability.
+
+**Checkpoint 1 — Present core health assessment.** Show health summary, shareable infrastructure, red flags. Ask: "Does this match your sense of where the core product is? Resource constraints to factor in?"
+
+### 2. Map Expansion Vectors
+
+Use web search with **8-12 diverse queries**: adjacent markets, vertical depth (enterprise features, advanced use cases), horizontal breadth (related categories, tools used alongside), platform precedents, user workflow gaps, ecosystem opportunities, acquisition patterns, market trends, adjacent pain points, bundling precedents.
+
+Also analyse codebase and existing research for internal signals: adjacent feature requests from customer feedback, competitor product lines, journey map drop-offs, data/infra that could power new products.
+
+### 3. Identify Expansion Candidates — Present & Validate
+
+Cluster findings into **4-8 candidates** across two axes:
+
+**Vertical:** advanced tiers, deeper workflow coverage, industry-specific variants, data products from existing data.
+
+**Horizontal:** complementary tools, adjacent persona products, same tech applied to different problem, marketplace/platform plays.
+
+For each: problem, audience, relationship to core, market signal, vertical vs. horizontal.
+
+Record the 4-8 candidates in `research/.progress.yaml` as `product_paths[]` entries with `source_skill: platform-strategy`. The top candidate may be `status: active` or `status: revisit_candidate` depending on whether the user is ready to validate it now; non-selected candidates should default to `status: deferred` with validation triggers. Include `id`, `label`, `source_skill: platform-strategy`, `pipeline_stage: platform-strategy`, `scope_path`, `status`, `reason`, `archive_reason`, `archived_at`, `promoted_at`, `evidence_refs`, `revisit_trigger`, `next_skill`, and `last_touched`.
+
+**Checkpoint 2 — Present candidates.** Group by vertical/horizontal with rationale and evidence. Ask: "Expansion directions I missed? Any clearly wrong? Internal signals pointing toward any of these?"
+
+### 4. Score Expansion Candidates
+
+Score each across five dimensions (1-5 each):
+
+- **Synergy** — shared users, data, infra, cross-sell potential
+- **Market Opportunity** — size, competitive density, willingness to pay, growth
+- **Effort & Risk** — build complexity, time to revenue, tech risk, cannibalization
+- **Strategic Value** — defensibility, brand coherence, sequencing value
+- **Validation Cost** — how cheaply can we test demand
+
+Build a scoring matrix with weighted totals.
+
+### 5. Design Validation Experiments for Top Candidates
+
+For **top 2-3 candidates**: cheapest test method (landing page, fake-door, survey, pre-sale, concierge), audience, success criteria, timeline (1-4 weeks), decision rules (proceed/pivot/kill). Reference `$experiment` for full experiment design.
+
+### 6. Sequence the Portfolio — Present & Validate
+
+Recommend a portfolio sequence: **Now** (next quarter), **Next** (quarter +1), **Later** (6-12 months), **Watch** (12+ months). For each: shared infra needed, dependencies, revenue expectation, kill criteria.
+
+**Checkpoint 3 — Present full portfolio plan.** Show scoring matrix, validation experiments, portfolio sequence, shared platform considerations. Ask: "Sequencing match your priorities? Different experiments to run first? Dependencies I'm missing?"
+
+### 7. Write Output
+
+Only after user validates, write the output files.
+
+## Deliverables
+
+- `research/platform-strategy.md` (or `research/{slug}/platform-strategy.md`) — Full platform strategy: summary, core health, expansion vector map, scoring matrix, validation experiments, portfolio sequence, shared platform considerations, next steps.
+- `research/platform-strategy-search-log.md` (or `research/{slug}/platform-strategy-search-log.md`) — Raw research log: every query, findings, source attribution, scoring rationale.
+- `research/.progress.yaml` — product-path manifest updated with 4-8 expansion candidates. This does not require every candidate to become a full research track.
+
+`## Next Steps` section with a **Recommended** item and **Other options** (2–4 alternatives). Use this format in the output:
+
+## Next Steps
+
+**Recommended:** `$experiment [top candidate]` — validate demand for the highest-scored expansion candidate before committing resources
+
+Other options:
+- `$assumption-tracker` — track which platform assumptions need validation (if no `research/assumption-tracker.md`)
+- `$competitive-analysis [adjacent category]` — research the competitive landscape for the top expansion candidate
+- `$customer-discovery [new audience]` — run customer discovery for the new audience the top candidate targets
+- `$enterprise-icp` — map enterprise requirements if the expansion targets enterprise (if no `research/enterprise-icp.md`)
+- `$roadmap` — sequence the expansion into the build plan (if `specs/` exist for the candidate)
+- `$roadmap` — sequence the expansion into the build plan (if `specs/` exist)
+
+The recommendation (`$experiment [top candidate]`) is always applicable — platform expansion should be validated before built.
+
+## 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
+
+- Use web search extensively — every market signal must trace to research evidence.
+- Cite sources for market signals, competitor product lines, trend data.
+- Be honest about uncertainty.
+- Stay in strategy mode — no architecture, features, or technical solutions.
+- Core health is gating — flag PMF problems directly.
+- Score honestly — low-synergy, high-effort candidates should score low.
+- Present before writing — never write until findings are validated.
+- Do not overwrite existing `research/platform-strategy.md` (or `research/{slug}/platform-strategy.md`) without asking.
+- Keep validation experiments lightweight — full design belongs in `$experiment`.
+- `## Next Steps` must be the final section in the output file, with a recommended next step and 2–4 other options.
+
+## 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/platform-strategy-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.