skillpacks 0.1.1 → 0.1.2

package/packs/business-ops/claude/platform-strategy/archive/v0.9/SKILL.md

@@ -0,0 +1,461 @@
+---
+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
+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 `/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.
+
+# Platform Strategy — Multi-Product Expansion Planning
+
+## 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, their pain points, value props
+- 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 — they enrich the analysis):
+- `research/competitive-analysis.md` — where competitors are/aren't, market gaps
+- `research/journey-map.md` — current user flows, where users hit walls or leave
+- `research/metrics.md` — retention, activation, engagement baselines for the core product
+
+**Optional but enriching:**
+- `research/monetization.md` — current revenue model, pricing leverage points
+- `research/positioning.md` — current market category, unique attributes
+- `research/customer-feedback.md` — what users are asking for that's adjacent
+- `research/enterprise-icp.md` — if expanding upmarket is a vector
+- `research/assumption-tracker.md` — unvalidated assumptions that affect expansion
+
+## 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
+
+Before expanding, determine whether the foundation is solid enough. Read the codebase, existing research, and metrics to evaluate:
+
+- **Product-market fit signals** — retention, activation, NPS/satisfaction signals from `research/metrics.md` or `research/customer-feedback.md`
+- **Technical extensibility** — shared infrastructure (auth, billing, data models) that new products could build on vs. what's tightly coupled
+- **Team/resource signals** — monorepo structure, package boundaries, deployment independence
+- **Revenue stability** — from `research/monetization.md` if available
+
+**Checkpoint 1 — Present core health assessment to the user.** Use the AskUserQuestion tool to show:
+- A brief health summary: is the core product ready to support expansion, or are there risks?
+- Key infrastructure that could be shared vs. what needs decoupling
+- Any red flags (e.g., poor retention means the core product needs fixing first)
+
+Ask:
+- "Does this assessment match your sense of where the core product is?"
+- "Are there resource constraints I should factor in? (team size, runway, technical debt)"
+
+Incorporate feedback before proceeding.
+
+### 2. Map Expansion Vectors
+
+Use WebSearch with **8-12 diverse queries** to research expansion opportunities. Log every search query and key findings to the research log.
+
+Query strategies (adapt to the specific domain):
+1. **Adjacent market searches** — "[category] adjacent markets", "[category] expansion opportunities"
+2. **Vertical depth searches** — "[category] enterprise features", "[category] advanced use cases", "[ICP role] additional tools needed"
+3. **Horizontal breadth searches** — "[category] related categories", "tools used alongside [product category]"
+4. **Platform precedent searches** — "[category] companies that became platforms", "[competitor] product line"
+5. **User workflow searches** — "what do [ICP] use before/after [category]", "[ICP] tool stack"
+6. **Ecosystem searches** — "[category] marketplace", "[category] integrations ecosystem"
+7. **Acquisition pattern searches** — "[category] acquisitions", "[competitor] acquired companies"
+8. **Market trend searches** — "[category] trends 2025 2026", "future of [domain]"
+9. **Adjacent pain searches** — "[ICP] other frustrations", "[ICP] biggest challenges besides [core problem]"
+10. **Bundling precedent searches** — "[category] suite vs point solution", "[category] all-in-one"
+
+Also analyse the codebase and existing research for internal signals:
+- Features users request that are adjacent to the core product (from `research/customer-feedback.md`)
+- Competitor product lines (from `research/competitive-analysis.md`)
+- Journey map drop-off points where a new product could re-engage users
+- Data or infrastructure that could power additional products
+
+### 3. Identify Expansion Candidates — Present & Validate
+
+From the research, cluster findings into **4-8 expansion candidates** across two axes:
+
+**Vertical (deeper into same customer base):**
+- Advanced tiers, enterprise features, professional services
+- Deeper workflow coverage (upstream/downstream of current product)
+- Industry-specific variants of the core product
+- Data products built on what the core product already collects
+
+**Horizontal (adjacent products for new or overlapping customer bases):**
+- Complementary tools the ICP uses alongside the core product
+- Products for adjacent personas in the same organisation
+- The same core technology applied to a different problem/audience
+- Marketplace or platform plays that enable third-party value creation
+
+For each candidate, note:
+- Problem it solves and for whom
+- Relationship to core product (shared data, shared users, shared infra, or independent)
+- Initial market signal (from web research)
+- Whether it's vertical or 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 to the user.** Use the AskUserQuestion tool to show all candidates grouped by vertical/horizontal, with a brief rationale and research evidence for each. Then ask:
+- "Are there expansion directions I missed?"
+- "Any of these clearly wrong for your situation or that you've already ruled out?"
+- "Are there internal signals (user requests, sales conversations) that point toward any of these?"
+
+Incorporate feedback before proceeding.
+
+### 4. Score Expansion Candidates
+
+For each validated candidate, score across five dimensions:
+
+#### Synergy Score (how much the core product amplifies this)
+- Shared users — do existing users want this?
+- Shared data — does the core product generate data this product needs?
+- Shared infrastructure — auth, billing, deployment, APIs reusable?
+- Cross-sell potential — can you sell this through the same channel?
+
+#### Market Opportunity (how big and accessible is this)
+- Market size signals (from web research)
+- Competitive density — is it crowded or open?
+- Willingness to pay signals
+- Growth trajectory of the adjacent market
+
+#### Effort & Risk
+- Build complexity — new app vs. feature vs. integration
+- Time to first revenue signal
+- Technical risk — new technology needed or existing stack sufficient?
+- Cannibalization risk — could this undermine the core product?
+
+#### Strategic Value
+- Defensibility — does this create a moat (network effects, data, switching costs)?
+- Brand coherence — does this make sense under the same brand?
+- Sequencing value — does this unlock future expansion vectors?
+
+#### Validation Cost
+- How cheaply can we test demand before building?
+- Existing channels to reach potential users
+- Minimum viable experiment complexity
+
+**Build a scoring matrix** with 1-5 ratings per dimension and a weighted total.
+
+### 5. Design Validation Experiments for Top Candidates
+
+For the **top 2-3 scored candidates**, design lightweight validation experiments:
+
+- What's the cheapest way to test demand? (landing page, fake-door, survey, pre-sale, concierge)
+- Who to test with? (existing users, adjacent audience, or both)
+- What signal would confirm or kill this direction?
+- How long would the experiment take?
+- What's the decision rule? (proceed / pivot / kill thresholds)
+
+Keep experiments to 1-4 weeks and minimal budget. Reference `/experiment` for full experiment design if the user wants to go deeper.
+
+### 6. Sequence the Portfolio — Present & Validate
+
+Based on scores, experiments, and strategic value, recommend a portfolio sequence:
+
+- **Now** (next quarter): The highest-confidence, highest-synergy candidate — usually vertical
+- **Next** (quarter after): The second candidate, ideally building on learnings from the first
+- **Later** (6-12 months): Candidates that require more infrastructure or validation
+- **Watch** (12+ months): Candidates that are interesting but premature
+
+For each phase:
+- What shared infrastructure needs to exist first
+- Key dependency on the previous phase
+- Revenue expectation (directional, not precise)
+- Kill criteria — when to abandon this direction
+
+**Checkpoint 3 — Present the full portfolio plan to the user.** Use the AskUserQuestion tool to show:
+1. Scoring matrix with all candidates
+2. Top 2-3 validation experiment designs
+3. Recommended portfolio sequence with rationale
+4. Shared platform considerations
+
+Ask:
+- "Does this sequencing match your priorities and constraints?"
+- "Any experiments you'd want to run first that differ from what I suggested?"
+- "Are there dependencies or constraints I'm not seeing?"
+
+Continue the conversation until all non-trivial details are nailed down. If the user raises points that require additional research, go back and search before finalising.
+
+### 7. Populate Next Steps
+
+Before writing, check which files exist to populate the `## Next Steps` section contextually. Include 3-5 applicable items with "Pick one:" framing:
+
+- ALWAYS first: `/experiment [top candidate hypothesis]` — Validate the top expansion candidate
+- IF no `research/assumption-tracker.md`: `/assumption-tracker` — Extract and rank assumptions behind the expansion plan
+- IF `research/competitive-analysis.md` is stale or doesn't cover adjacent markets: `/competitive-analysis [adjacent category]` — Research competitors in the expansion space
+- IF top candidate targets a new audience: `/customer-discovery [new audience]` — run customer discovery for the new product audience
+- IF top candidate is vertical (enterprise): `/enterprise-icp` — Map enterprise stakeholders for the deeper play
+- IF specs exist for core but not expansion: `/ux-variations [top candidate]` — Explore solution directions for the expansion product
+- ALWAYS: `/roadmap` — Integrate expansion phases into the project roadmap
+
+**Impact-aware adjustments:**
+- IF downstream impact is **Major**: prepend `/reconcile-research — [N] conflicts found in downstream docs` as the first item
+- IF downstream impact is **Minor**: annotate relevant skill suggestions with "(stale — [brief description])"
+- If downstream impact has not been classified yet, run the downstream impact check against the proposed output before selecting the final recommendation. Do not emit a Minor/Major impact recommendation speculatively.
+
+### 8. Write Output
+
+Only after the user has validated the findings, write the output files.
+
+### 9. Downstream Impact Check
+
+After writing, check for downstream research documents that may be affected by what was just decided. Only check documents that exist on disk.
+
+**Downstream documents to check** (use `{slug}/` prefix when product-path scope is active):
+- `research/roadmap.md`
+- `research/monetization.md`
+- `research/gtm.md`
+- `research/positioning.md`
+- `research/metrics.md`
+
+For each existing downstream document:
+1. Read it — focus on `> Based on:` header, `## Summary`, and sections that reference concepts this skill just defined or changed
+2. Identify **specific conflicts**: claims, assumptions, or references that contradict what was just decided. Examples:
+   - Roadmap phases that don't account for expansion products
+   - Monetization strategy built around a single product
+   - GTM messaging that doesn't address multi-product positioning
+   - Positioning anchored to a single-product category
+   - Metrics frameworks that don't cover cross-product health
+3. Note each conflict: downstream file, section, the stale claim (quote it), and what it should now say
+
+**Classify the impact**:
+- **None**: No downstream documents exist, or no conflicts found. Skip display entirely.
+- **Minor** (1-2 small conflicts): Display conflicts to user inline.
+- **Major** (3+ conflicts OR a foundational assumption changed — e.g., positioning shifted from point solution to platform, revenue model needs restructuring): Display conflicts and strongly recommend `/reconcile-research`.
+
+Display to the user after showing the written file confirmation. This should be quick — one read per downstream doc, scan for conflicts against key decisions. Not a deep reconciliation.
+
+## Output
+
+### `research/platform-strategy.md` (or `research/{slug}/platform-strategy.md`)
+
+```markdown
+# Platform Strategy
+
+> Product: [product name and one-line description]
+> Current ICP: [primary ICP from research/icp.md]
+> Date: [current date]
+> Candidates evaluated: [number]
+
+## Summary
+[3-5 sentences: core health assessment, top expansion direction, portfolio thesis, and the single most important next move]
+
+## Core Product Health
+
+### Product-Market Fit Signals
+[Retention, activation, satisfaction — is the foundation solid?]
+
+### Technical Extensibility
+[What infrastructure is shareable vs. tightly coupled — auth, billing, data, APIs]
+
+### Expansion Readiness
+[Overall assessment: ready / ready with caveats / not yet — with reasoning]
+
+## Expansion Vector Map
+
+### Vertical Candidates (Deeper Into Same Customer Base)
+
+For each:
+- **[Candidate Name]** — [one-line description]
+  - Problem: [what it solves]
+  - Audience: [who benefits — same ICP or subset]
+  - Synergy: [shared data, users, infra]
+  - Market signal: [evidence from research]
+  - Effort: [new app / feature / integration — rough complexity]
+
+### Horizontal Candidates (Adjacent Products for New/Overlapping Audiences)
+
+For each:
+- **[Candidate Name]** — [one-line description]
+  - Problem: [what it solves]
+  - Audience: [who benefits — new or adjacent ICP]
+  - Synergy: [shared data, users, infra]
+  - Market signal: [evidence from research]
+  - Effort: [new app / feature / integration — rough complexity]
+
+## Scoring Matrix
+
+| Candidate | Synergy | Market Opportunity | Effort & Risk | Strategic Value | Validation Cost | Weighted Total |
+|-----------|---------|-------------------|---------------|-----------------|-----------------|----------------|
+| ... | /5 | /5 | /5 | /5 | /5 | /25 |
+
+### Scoring Rationale
+[Brief justification for scores that aren't obvious — especially where candidates are close]
+
+## Validation Experiments
+
+### [Top Candidate 1]
+
+**Hypothesis**: [structured hypothesis]
+**Method**: [experiment type — landing page / fake-door / survey / pre-sale / concierge]
+**Audience**: [who to test with and how to reach them]
+**Timeline**: [duration]
+**Success criteria**: [specific measurable threshold]
+**Decision rule**: If validated → [action]. If invalidated → [pivot].
+
+### [Top Candidate 2]
+[Same structure]
+
+### [Top Candidate 3]
+[Same structure]
+
+## Portfolio Sequence
+
+### Now (Next Quarter)
+- **[Candidate]**: [what to do and why this is first]
+- Shared infra needed: [what to build/decouple]
+- Validation: [experiment to run]
+- Kill criteria: [when to abandon]
+
+### Next (Quarter +1)
+- **[Candidate]**: [what to do and why this follows]
+- Depends on: [what must be true from previous phase]
+- Kill criteria: [when to abandon]
+
+### Later (6-12 Months)
+- **[Candidate]**: [why it's deferred — what needs to change for it to move up]
+
+### Watch (12+ Months)
+- **[Candidate]**: [why it's interesting but premature]
+
+## Shared Platform Considerations
+
+### Infrastructure to Share
+[Auth, billing, data layer, deployment, APIs — what should be centralised]
+
+### What to Keep Independent
+[Where new products should have their own stack to avoid coupling]
+
+### Brand Architecture
+[Single brand with sub-products, separate brands, or brand + "for [segment]" variants]
+
+### Cross-Product Metrics
+[Portfolio-level health metrics: cross-sell rate, multi-product retention, platform LTV vs. single-product LTV]
+
+### Cannibalization Risks
+[Where new products might undermine the core — and how to mitigate]
+
+<!-- Include this section only when downstream impact is Minor or Major. Omit entirely for None. -->
+## Downstream Impact
+
+> Checked: [list of downstream docs checked]
+> Impact: Minor | Major
+
+### Conflicts Found
+
+1. **research/[file].md** — [Section Name]
+   - **Stale**: "[exact quote from downstream doc]"
+   - **Now**: [what this skill's output says instead]
+
+[For Major only:]
+> **Recommended action**: Run `/reconcile-research` to audit and fix all affected downstream documents.
+
+## Next Steps
+
+Pick one:
+- [conditional items from step 7 — only include items whose conditions are met]
+```
+
+### `research/platform-strategy-search-log.md` (or `research/{slug}/platform-strategy-search-log.md`)
+
+Raw research log containing:
+- Every WebSearch query executed and why
+- Key findings from each search (with source attribution)
+- Evidence for and against each expansion candidate
+- Competitor product-line analysis
+- Market size signals for adjacent markets
+
+### `research/.progress.yaml`
+
+Product-path manifest updated with 4-8 expansion candidates. This does not require every candidate to become a full research track.
+- Any data gaps or areas where research was inconclusive
+
+Create the `research/` (or `research/{slug}/`) 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
+
+- **Use web search extensively.** This skill's value comes from real market data about adjacent opportunities — not assumptions. Every market signal must trace to research evidence.
+- **Cite sources.** When stating market signals, competitor product lines, or trend data, note where the information came from.
+- **Be honest about uncertainty.** If market size or demand can't be verified, say so. Don't fabricate metrics.
+- **Stay in strategy mode.** Do not propose architecture, features, or technical solutions — that's for `/ux-variations`. Do not design full experiments — that's for `/experiment`. Provide enough to decide direction, not enough to build.
+- **Core health is gating.** If the core product shows clear PMF problems (poor retention, no activation), say so directly. Expanding from a weak foundation is a common startup mistake — flag it.
+- **Score honestly.** Low-synergy, high-effort candidates should score low even if the market is exciting. The whole point is to find expansion that leverages the existing product.
+- **Present before writing.** Never write output files until findings have been presented to the user and validated through the checkpoint questions. The user must see and approve the analysis before anything is written to disk.
+- **Do not overwrite existing `research/platform-strategy.md`** (or `research/{slug}/platform-strategy.md`) without asking the user first.
+- **Keep validation experiments lightweight.** Full experiment design belongs in `/experiment`. Here, provide just enough to estimate validation cost and timeline.
+
+## 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/platform-strategy-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/claude/product-line/ALIGNMENT-PAGE.md

@@ -1,6 +1,6 @@
 # Alignment Page — product-line
 
-When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page at `alignment/product-line-{topic}.html`. Use a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
+Alignment pages are optional for this operational skill. By default, report the outcome inline and write only the skill's normal durable artifacts (`tasks/*.md`, reports, queues, benchmark notes, status docs, or other skill-specific files). Build `alignment/product-line-{topic}.html` only when the user explicitly requests an alignment page or when the agent explicitly identifies a concrete clarification/review need that cannot be resolved cleanly in conversation or the normal artifacts. When an alignment page is created, use the full contract below and a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
 
 **Visual rendering tier.** Each alignment page declares a rendering tier:
 - `document` (default) — text, tables, approval gates. No charts or interactive elements.
@@ -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: artifact_only` (Artifact-driven). Work from concrete artifacts, data, logs, or existing instructions by default; ask concise clarification questions only when the available artifacts are missing, contradictory, or unsafe to interpret.
+
 **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-product-line-research.md`; product-path mode uses `research/{slug}/_working/preliminary-product-line-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-product-line-research.md`; product-path mode uses `research/{slug}/_working/preliminary-product-line-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.
 
 **Visual tier rendering.** This skill's alignment page uses the `visual` tier. Inline charts and diagrams are rendered via self-contained Canvas/SVG within the HTML file. Use the alignment chart snippet library (`scripts/alignment-chart-snippets.js`) as reference — copy needed chart functions directly into the page's `<script>` block. Charts must read CSS variables (`--chart-1` through `--chart-8`) for the data visualization palette. Every chart must include a `<table>` fallback, `aria-label` on canvas/SVG, and a "View as table" toggle. Data is embedded as inline JSON — no external fetches.
 

package/packs/business-ops/claude/product-line/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## v0.6 - 2026-06-12
+
+- Made alignment pages optional by default: report inline and write the skill's normal durable artifacts unless the user requests an alignment page or the agent identifies a concrete clarification/review need.
+
+## v0.5 - 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.
+
 ## v0.4 - 2026-06-10
 
 - Added npm-aware install-route guidance for business-ops cross-pack recommendations, preserving `/pack install <pack>` inside Claude Code while offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-ops/claude/product-line/SKILL.md

@@ -2,15 +2,15 @@
 name: product-line
 description: Manage the portfolio of product paths — review, activate, archive, restore, promote, fork, and check revisit triggers across the product-path manifest
 type: ops
-version: v0.4
+version: v0.6
 argument-hint: "review | activate <path-id> | archive <path-id> | restore <path-id> | promote <path-id> | fork <label> [--from <skill>] | triggers"
-interview_depth: none
+context_intake: artifact_only
 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 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.
+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 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.
 
 # Product Line — Product Path Portfolio Management
 
@@ -186,7 +186,7 @@ When this skill produces follow-up work, file it by execution semantics:
 
 ## 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/product-line-{topic}.html`.
+By default, this skill reports results inline and writes only its normal durable artifacts (for example `tasks/*.md`, reports, queues, benchmark notes, status docs, or other skill-specific files). Do not build an alignment page automatically. Create `alignment/product-line-{topic}.html` only when the user explicitly requests an alignment page or when you explicitly identify a concrete clarification/review need that cannot be handled cleanly inline; when you create one, follow `ALIGNMENT-PAGE.md` in this skill's directory.
 
 ## Default Shipping Contract