skillpacks 0.1.1 → 0.1.2

package/packs/business-research/claude/lean-canvas/archive/v0.9/SKILL.md

@@ -0,0 +1,344 @@
+---
+name: lean-canvas
+description: One-page Lean Canvas business model synthesis (Ash Maurya)
+type: research
+version: v0.9
+argument-hint: "[optional: focus area e.g. \"revenue model\", \"channels\"]"
+interview_depth: light
+visual_tier: visual
+---
+
+## Pack Availability Guard
+
+Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `/pack install <pack>` inside Claude Code, or `npx skillpacks install <pack>` from the project shell, instead of the target skill. 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.
+
+# Lean Canvas — One-Page Business Model Synthesis
+
+## 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
+
+- **Hard**: `research/icp.md` (or `research/{slug}/icp.md`) must exist. If not, tell the user to run `/customer-discovery` first and stop.
+- **Soft**: Read these if they exist:
+  - `research/competitive-analysis.md` — competitor landscape, channel insights, business model patterns
+  - `research/journey-map.md` — lifecycle moments where value, conversion, and retention occur
+  - `research/positioning.md` — unique value proposition, market category, competitive alternatives
+  - `research/value-prop.md` — value propositions mapped to customer segments
+  - `research/idea-brief.md` — product concept, solution approach, feature set
+
+## 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
+
+- Read `research/icp.md` — ICP segments, pain points, jobs to be done, trigger events
+- Read `research/competitive-analysis.md` if it exists — competitor landscape, channel strategies, business model patterns
+- Read `research/positioning.md` if it exists — unique attributes, value mapping, market category, competitive alternatives
+- Read `research/value-prop.md` if it exists — value propositions per segment
+- Read `research/idea-brief.md` if it exists — product concept, solution approach, features
+- Read CLAUDE.md, README, and key source files for product context
+
+### 2. Research Lean Canvas Methodology
+
+Use WebSearch with **4-6 targeted queries**:
+
+1. **Domain-specific canvases** — "lean canvas [domain]", "lean canvas examples [category]"
+2. **Methodology** — "Ash Maurya lean canvas best practices", "lean canvas vs business model canvas differences"
+3. **Business models** — "one page business model [industry]", "[category] business model patterns"
+4. **Revenue patterns** — "[category] revenue models", "[domain] pricing strategies"
+5. **Channel strategies** — "[category] customer acquisition channels", "[domain] distribution strategies"
+
+### 3. Synthesize Canvas Sections
+
+Map each Lean Canvas section from upstream research:
+
+- **Problem** — Top 3 problems from ICP pain points. Source: `research/icp.md`
+- **Customer Segments** — Primary and secondary segments from ICP. Source: `research/icp.md`
+- **Unique Value Proposition** — From positioning UVP statement, or `research/value-prop.md` if positioning doesn't exist. This is the single clear compelling message that states why you are different and worth buying.
+- **Solution** — Top 3 features or capabilities that address the top 3 problems. Source: `research/idea-brief.md` or product codebase.
+- **Channels** — Path to customers. Source: `research/competitive-analysis.md` channel insights, ICP "where they hang out."
+- **Revenue Streams** — **HYPOTHESIS** — mark "to be validated by `/monetization`". Infer from competitive analysis pricing patterns and positioning (premium vs. value).
+- **Cost Structure** — **HYPOTHESIS** — mark "to be validated by `/monetization`". Infer from solution complexity, channel costs, and competitive analysis.
+- **Key Metrics** — From `research/metrics.md` if it exists, otherwise hypothesize key pirate metrics (AARRR) relevant to the business model.
+- **Unfair Advantage** — From positioning unique attributes or competitive moat. Something that cannot be easily copied or bought.
+
+Use AskUserQuestion to present and validate:
+- "Here's the Lean Canvas synthesized from research. Which sections need correction, stronger grounding, or are missing critical context?"
+
+### 4. Validate Hypotheses
+
+For sections marked as hypotheses (Revenue Streams, Cost Structure, and any others with low evidence), note:
+- **Confidence level**: High / Medium / Low
+- **What would validate** each hypothesis
+- **What would invalidate** each hypothesis
+- **Riskiest assumption** within each section
+
+Use AskUserQuestion:
+- "These are the unvalidated hypotheses. Which are highest risk and should be tested first?"
+
+### 5. Populate Next Steps
+
+Include 3-5 applicable items with "Pick one:" framing:
+
+- ALWAYS: `/user-flow-map [business-model-informed product direction]` — Return to the default AFPS prototype path by mapping screen flow before UI requirements and layout variants
+- IF Revenue/Cost hypotheses need validation: `/monetization` — Validate revenue model and cost structure hypotheses
+- IF riskiest hypothesis identified: `/experiment [riskiest hypothesis]` — Test the riskiest assumption with a structured experiment
+- IF no `research/positioning.md`: `/positioning` — Establish strategic positioning to strengthen UVP and Unfair Advantage sections
+- IF no `research/journey-map.md`: `/journey-map` — Map the customer journey before continuing UX, growth, or spec work
+- IF codebase exists: `/mvp-gap` — Check if the product delivers on the canvas promises
+
+### 6. Write Output
+
+Only after the user confirms, write the output files.
+
+### 7. Downstream Impact Check
+
+After writing, check for downstream research documents that may be affected.
+
+**Downstream documents to check** (use `{slug}/` prefix when product-path scope is active):
+- `research/journey-map.md`
+- `research/monetization.md`
+
+For each existing downstream document:
+1. Read it — focus on sections that reference business model, revenue, channels, or customer segments
+2. Identify conflicts where the downstream document's assumptions don't align with the canvas
+3. Note each conflict: file, section, stale claim, what it should now say
+
+**Classify the impact**:
+- **None**: No downstream docs exist, or no conflicts. Skip display.
+- **Minor** (1-2 small conflicts): Display inline.
+- **Major** (3+ conflicts OR customer segments changed, revenue model shifted, channel strategy changed): Display and recommend `/reconcile-research`.
+
+## Output
+
+### `research/lean-canvas.md` (or `research/{slug}/lean-canvas.md`)
+
+```markdown
+# Lean Canvas
+
+> Based on: research/icp.md[, research/competitive-analysis.md, research/positioning.md, research/value-prop.md, research/idea-brief.md]
+> Date: [current date]
+> Methodology: Lean Canvas (Ash Maurya)
+
+## Summary
+
+[2-3 sentence business model thesis — who the customer is, what problem you solve, how you make money, and what makes this defensible]
+
+## Lean Canvas
+
+### Problem
+
+Top 3 problems:
+1. [problem 1] — _Source: [reference]_
+2. [problem 2] — _Source: [reference]_
+3. [problem 3] — _Source: [reference]_
+
+**Existing alternatives**: [how customers solve these problems today]
+
+### Customer Segments
+
+**Primary segment**: [segment description]
+**Early adopters**: [most acute subset — who you target first]
+
+_Source: research/icp.md_
+_Confidence: [High/Medium/Low]_
+
+### Unique Value Proposition
+
+**Single clear compelling message**:
+> [UVP statement]
+
+**High-level concept**: [X for Y analogy, if applicable]
+
+_Source: [research/positioning.md or research/value-prop.md]_
+_Confidence: [High/Medium/Low]_
+
+### Solution
+
+Top 3 features addressing top 3 problems:
+1. [feature 1] → solves [problem 1]
+2. [feature 2] → solves [problem 2]
+3. [feature 3] → solves [problem 3]
+
+_Source: [research/idea-brief.md or product codebase]_
+_Confidence: [High/Medium/Low]_
+
+### Channels
+
+**Path to customers**:
+- [channel 1] — [rationale]
+- [channel 2] — [rationale]
+- [channel 3] — [rationale]
+
+_Source: [research/competitive-analysis.md, research/icp.md]_
+_Confidence: [High/Medium/Low]_
+
+### Revenue Streams
+
+> **HYPOTHESIS** — to be validated by `/monetization`
+
+- [revenue stream 1] — [pricing model]
+- [revenue stream 2] — [pricing model]
+
+**Price anchoring**: [what customers pay for alternatives today]
+
+_Source: [inferred from competitive analysis and positioning]_
+_Confidence: [High/Medium/Low]_
+
+### Cost Structure
+
+> **HYPOTHESIS** — to be validated by `/monetization`
+
+**Fixed costs**:
+- [cost 1]
+- [cost 2]
+
+**Variable costs**:
+- [cost 1]
+- [cost 2]
+
+_Source: [inferred from solution complexity and channel costs]_
+_Confidence: [High/Medium/Low]_
+
+### Key Metrics
+
+- [metric 1] — [what it measures and why it matters]
+- [metric 2] — [what it measures and why it matters]
+- [metric 3] — [what it measures and why it matters]
+
+_Source: [research/metrics.md or hypothesized]_
+_Confidence: [High/Medium/Low]_
+
+### Unfair Advantage
+
+[Something that cannot be easily copied or bought]
+
+- [advantage 1] — [why it's defensible]
+- [advantage 2] — [why it's defensible]
+
+_Source: [research/positioning.md unique attributes or competitive moat]_
+_Confidence: [High/Medium/Low]_
+
+## Hypothesis Register
+
+| Hypothesis | Section | Confidence | Validation Method | Status |
+|-----------|---------|------------|-------------------|--------|
+| [hypothesis 1] | Revenue Streams | [H/M/L] | [how to test] | Unvalidated |
+| [hypothesis 2] | Cost Structure | [H/M/L] | [how to test] | Unvalidated |
+| [hypothesis 3] | [section] | [H/M/L] | [how to test] | Unvalidated |
+
+**Riskiest hypothesis**: [which hypothesis, if wrong, would most undermine the business model]
+
+## Strategic Implications
+
+### Business Model Type
+[What type of business model this canvas describes — marketplace, SaaS, transactional, etc.]
+
+### Key Dependencies
+[What must be true for this business model to work]
+
+### Biggest Risks
+[Top 2-3 risks to the business model thesis]
+
+<!-- Only include when downstream impact is Minor or Major -->
+## Downstream Impact
+
+> Checked: [list of downstream docs checked]
+> Impact: Minor | Major
+
+### Conflicts Found
+
+1. **research/[file].md** — [Section Name]
+   - **Stale**: "[exact quote]"
+   - **Now**: [what the canvas 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 5]
+```
+
+### `research/lean-canvas-search-log.md` (or `research/{slug}/lean-canvas-search-log.md`)
+
+Raw research log — queries, findings, evidence for each canvas section decision.
+
+Create the `research/` 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
+
+- **Requires ICP.** A business model without customer understanding is fiction.
+- **Synthesis-first.** Every canvas section should trace to upstream research, not invented from scratch. If a section cannot be grounded in existing research, mark it as a hypothesis with Low confidence.
+- **Mark hypotheses honestly.** Revenue Streams and Cost Structure are hypotheses until `/monetization` validates them. Any other section without strong evidence should also be flagged.
+- **Present before writing.** Never write output files until the canvas has been presented and validated by the user.
+- **Do not overwrite existing `research/lean-canvas.md`** without asking the user first.
+- **Lean Canvas ≠ full business plan.** This is a one-page hypothesis document. Do not expand it into a detailed business plan — that's a different deliverable.
+- **One canvas per product.** Don't try to capture multiple business models in a single canvas. If the product has multiple revenue models, pick the primary one and note alternatives.
+
+## 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/lean-canvas-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-research/claude/positioning/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-positioning-research.md`; product-path mode uses `research/{slug}/_working/preliminary-positioning-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-positioning-research.md`; product-path mode uses `research/{slug}/_working/preliminary-positioning-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.
 
 **Positioning research translation.** Render positioning claims with supporting ICP, competitive, journey, and customer-language evidence. Show alternatives considered, rejected narratives, confidence by claim, and which missing evidence would change the recommended position.
 

package/packs/business-research/claude/positioning/CHANGELOG.md

@@ -1,5 +1,20 @@
+# Changelog
+
+## v0.17 - 2026-06-13
+
+- Removed direct execution-loop command handoffs from non-exec routing; route through approved YAML, task, or roadmap artifacts instead.
+
+
 # positioning changelog (claude)
 
+## v0.16 - 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.
+
+## v0.15 - 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.
+
 ## v0.14 - 2026-06-11
 
 - Added npm-aware install-route guidance so unavailable-pack fallbacks keep `/pack install` while also offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-research/claude/positioning/SKILL.md

@@ -2,16 +2,16 @@
 name: positioning
 description: Orchestrator — detect market vs product mode, recommend positioning frameworks, synthesize outputs into unified positioning
 type: research
-version: v0.14
+version: v0.17
 argument-hint: "[optional: \"product\" | \"--synthesize\" | focus area]"
-interview_depth: light
+context_intake: scoped
 visual_tier: visual
 invocation: orchestrator
 ---
 
 ## Pack Availability Guard
 
-Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `/pack install <pack>` inside Claude Code, or `npx skillpacks install <pack>` from the project shell, instead of the target skill. 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.
+Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `npx skillpacks install <pack>` from the project shell, instead of the target skill. 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.
 
 # Positioning — Orchestrator
 
@@ -32,7 +32,7 @@ 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.
@@ -151,7 +151,7 @@ Write selected frameworks as sequential steps in `tasks/todo.md`:
 
 Only include frameworks the user selected. Always append the synthesis step last.
 
-Stop after writing `tasks/todo.md`. The user runs `/exec` to execute each framework sequentially.
+Stop after writing `tasks/todo.md`. The approved task artifact records the ordered framework execution and synthesis steps.
 
 ### 4. Mode B — Synthesis (`/positioning --synthesize`)
 
@@ -209,14 +209,14 @@ After user approval via final compiled YAML, write this execution plan to `tasks
 - [ ] Synthesize: `/positioning --synthesize` — Write research/positioning.md
 ```
 
-Stop — user runs `/exec`.
+Stop; the approved task artifact is the routing contract.
 
 ### 6. Next Steps (after synthesis only)
 
 Include 3–5 applicable items with "Recommended + Other options" framing:
 
 - IF no `research/journey-map.md`: check for `customer-lifecycle` pack → recommend `/journey-map`
-- DEFAULT: check `.agents/project.json.enabled_packs` for `product-design` — if not enabled, recommend `/pack install product-design` inside Claude Code, or `npx skillpacks install product-design` from the project shell; if enabled, recommend `/user-flow-map [positioning-backed product direction]`
+- DEFAULT: check `.agents/project.json.enabled_packs` for `product-design` — if not enabled, recommend `npx skillpacks install product-design` from the project shell; if enabled, recommend `/user-flow-map [positioning-backed product direction]`
 - IF solution-customer fit is weak/disputed: `/value-prop-canvas`
 - IF revenue/channels/cost/defensibility risks exposed: `/lean-canvas`
 - IF no `research/gtm.md`: check for `business-growth` pack → recommend `/gtm`