skillpacks 0.1.1 → 0.1.2

package/packs/business-research/claude/customer-discovery/frameworks/jtbd-needs/ALIGNMENT-PAGE.md

@@ -57,7 +57,13 @@ 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-jtbd-needs-research.md`; product-path mode uses `research/{slug}/_working/preliminary-jtbd-needs-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-jtbd-needs-research.md`; product-path mode uses `research/{slug}/_working/preliminary-jtbd-needs-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.
+
+**JTBD needs translation.** Research focus: Gather job, circumstance, desired-outcome, current-alternative, pain, and gain evidence for each candidate. Separate observed job language from inferred outcome statements, assumptions, confidence, and decision impact. Review/documentation format: Render job statements and outcome scorecards, candidate-by-need matrices, importance/satisfaction or opportunity ratings when evidence supports them, evidence tables, and source gaps. Suggested user feedback: Ask reviewers to confirm job framing, outcome wording, candidate fit, importance and satisfaction scoring, missing evidence, and which underserved needs should drive parent synthesis. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
+
+**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.
 
 **Glossary Additions gate.** When this research introduces domain-specific terms, acronyms, or concept definitions that a reader outside the project would not know, include a `## Glossary Additions` section in the alignment page. Render a table of proposed terms with columns: Term, Definition, Source (`jtbd-needs`), Category (business/tooling/workflow/technical/domain), and per-term Approve/Edit/Reject/Flag radio controls. Only user-approved terms are appended to the target glossary (`research/glossary.md` or `research/{slug}/glossary.md` for scoped paths) during the confirmed-page write step. When the skill operates in a product-path scope, ask whether each term belongs in the parent or scoped glossary; default to the scoped glossary.
 

package/packs/business-research/claude/customer-discovery/frameworks/jtbd-needs/CHANGELOG.md

@@ -1,5 +1,13 @@
 # jtbd-needs changelog (claude)
 
+## v0.4 - 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.
+
+## v0.3 - 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.
+
 ## v0.2 - 2026-06-10
 
 - Added npm-aware `npx skillpacks install <pack>` wording to the Pack Availability Guard while preserving runner-specific in-agent pack install routes.

package/packs/business-research/claude/customer-discovery/frameworks/jtbd-needs/SKILL.md

@@ -2,14 +2,14 @@
 name: jtbd-needs
 description: Ulwick/Christensen JTBD — identify jobs, map desired outcomes, score importance vs satisfaction, and segment ICP candidates by unmet needs
 type: research
-version: v0.2
+version: v0.4
 invocation: sub-skill
 parent: customer-discovery
 ---
 
 ## 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. 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. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # JTBD Needs — Ulwick/Christensen Outcome-Driven Innovation
 
@@ -28,7 +28,7 @@ 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-research/claude/customer-discovery/frameworks/jtbd-needs/archive/v0.2/SKILL.md

@@ -0,0 +1,234 @@
+---
+name: jtbd-needs
+description: Ulwick/Christensen JTBD — identify jobs, map desired outcomes, score importance vs satisfaction, and segment ICP candidates by unmet needs
+type: research
+version: v0.2
+invocation: sub-skill
+parent: customer-discovery
+---
+
+## 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. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# JTBD Needs — Ulwick/Christensen Outcome-Driven Innovation
+
+## 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. Push back clearly and cite the evidence when the user appears to misunderstand.
+- For taste, prioritization, or subjective judgment calls: weigh user feedback heavily and adapt unless it conflicts with verified evidence.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## Prerequisites
+
+- **Hard**: ICP candidates from orchestrator working packet (`research/_working/preliminary-customer-discovery-research.md`) or `research/icp.md` (or `research/{slug}/icp.md`) must exist. If neither exists, tell the user to run `/customer-discovery` first and stop.
+- **Soft**: `research/competitive-analysis.md`, `research/customer-feedback.md`, idea brief, specs, and codebase context when available.
+
+## 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.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`.
+
+### 1. Load Context
+
+- Read ICP candidates from orchestrator working packet (`research/_working/preliminary-customer-discovery-research.md`) or `research/icp.md`
+- Read idea brief (`research/idea-scope-brief.md`) if it exists
+- Read `research/competitive-analysis.md` if it exists
+- Read `research/customer-feedback.md` if it exists
+- Read CLAUDE.md, README for product context
+- Scan codebase and existing research for additional signal
+
+### 2. Identify Jobs-to-be-Done
+
+For each ICP candidate, identify the full job landscape:
+
+**Functional jobs** — tasks and outcomes they need accomplished:
+- Core tasks they hire a solution to perform
+- Desired outcomes for each task (measurable results)
+- Related tasks that precede, follow, or co-occur with the core job
+- Frequency and context of job execution
+
+**Social jobs** — how they want to be perceived:
+- Professional reputation goals
+- Peer perception and status signals
+- Team/org perception of their decisions
+- Industry credibility and thought leadership
+
+**Emotional jobs** — how they want to feel:
+- Confidence and control over outcomes
+- Reduced anxiety about risks or unknowns
+- Satisfaction and sense of progress
+- Freedom from tedious or frustrating work
+
+**Related jobs** — adjacent jobs that create context:
+- Jobs performed immediately before and after
+- Jobs that share the same workflow or trigger
+- Jobs delegated to other roles that affect this one
+- Jobs that compete for the same time/attention
+
+**Consumption chain jobs** — jobs around acquiring, using, maintaining the solution:
+- Evaluate and select solutions
+- Onboard and learn the solution
+- Integrate with existing workflow
+- Maintain, update, and extend over time
+- Migrate away when the job changes
+
+### 3. Map Desired Outcomes
+
+For each job, write Ulwick outcome statements following the canonical format:
+
+`[Direction of improvement] + [performance metric] + [object of control] + [contextual clarifier]`
+
+Direction of improvement: Minimize, Maximize, Increase, Reduce, Eliminate, Optimize
+
+Examples:
+- "Minimize the time it takes to identify qualified leads in a new market segment"
+- "Reduce the likelihood of misallocating budget to underperforming channels"
+- "Maximize the percentage of outreach messages that receive a response"
+- "Minimize the number of tools required to complete end-to-end campaign analysis"
+
+Write 8-15 outcome statements per core functional job, 3-5 per social/emotional job.
+
+### 4. Score Importance & Satisfaction
+
+For each outcome statement, score based on available evidence (research, feedback, competitive analysis, codebase signals):
+
+- **Importance** (1-10): How important is achieving this outcome to the ICP candidate?
+- **Current Satisfaction** (1-10): How well do existing solutions satisfy this outcome?
+
+Calculate **Opportunity Score**: `Importance + max(Importance - Satisfaction, 0)`
+
+Classify each outcome:
+- **Underserved** (opportunity score ≥ 12): high importance, low satisfaction — prime innovation targets
+- **Appropriately served** (opportunity score 8-11): adequate current solutions exist
+- **Overserved** (opportunity score < 8): low importance or high satisfaction — potential to simplify/reduce
+
+### 5. Segment by Unmet Needs
+
+Cluster ICP candidates by shared patterns of underserved outcomes:
+
+- Identify candidates with similar underserved outcome clusters
+- Define natural segments based on shared unmet needs (not demographics)
+- Map cross-segment patterns: outcomes underserved across all candidates
+- Identify segment-specific opportunity areas unique to each cluster
+- Rank segments by total addressable opportunity (sum of opportunity scores for underserved outcomes)
+- Note which segments align with or diverge from demographic/firmographic ICP boundaries
+
+### 6. Validate with User
+
+Present jobs, outcomes, opportunity scores, and segment recommendations. Ask for corrections on:
+- Job completeness: missing jobs or mischaracterized job importance
+- Outcome accuracy: whether statements reflect real user language and priorities
+- Scoring calibration: whether importance/satisfaction estimates match known reality
+- Segment validity: whether proposed clusters reflect real behavioral differences
+
+## Output
+
+### `research/customer-discovery-jtbd-needs.md` (or `research/{slug}/customer-discovery-jtbd-needs.md`)
+
+```markdown
+# JTBD Needs Analysis
+
+> Based on: [sources]
+> Date: [current date]
+> Methodology: Ulwick/Christensen Outcome-Driven Innovation
+
+## ICP Candidate: [Name]
+
+### Functional Jobs
+| Job | Context | Frequency |
+|-----|---------|-----------|
+| [core task] | [when/where this job arises] | [how often] |
+
+### Social & Emotional Jobs
+| Type | Job | Evidence |
+|------|-----|----------|
+| Social | [how they want to be perceived] | [source] |
+| Emotional | [how they want to feel] | [source] |
+
+### Desired Outcomes & Opportunity Scores
+| Outcome Statement | Job | Importance | Satisfaction | Opportunity Score | Classification |
+|-------------------|-----|------------|--------------|-------------------|----------------|
+| [direction] + [metric] + [object] + [context] | [parent job] | 1-10 | 1-10 | calculated | Underserved/Served/Overserved |
+
+### Top Underserved Outcomes
+1. [outcome] — Opportunity Score: [score]
+2. [outcome] — Opportunity Score: [score]
+3. [outcome] — Opportunity Score: [score]
+
+## ICP Candidate: [Name 2]
+...
+
+## Opportunity Landscape
+| Outcome | Candidate(s) | Importance | Satisfaction | Opportunity Score |
+|---------|-------------|------------|--------------|-------------------|
+| [outcome] | [who shares it] | [avg] | [avg] | [score] |
+
+## Needs-Based Segments
+### Segment: [Name]
+- **Shared underserved outcomes**: [list]
+- **ICP candidates in segment**: [list]
+- **Total addressable opportunity**: [sum of opportunity scores]
+- **Distinguishing characteristic**: [what unites them beyond demographics]
+
+## Cross-Candidate Comparison
+| Candidate | Top Underserved Outcome | Segment | Total Opportunity |
+|-----------|------------------------|---------|-------------------|
+| [name] | [highest-scoring outcome] | [segment] | [sum] |
+
+## Evidence Matrix
+| Claim | Evidence Source | Evidence Type | Confidence |
+|-------|---------------|---------------|------------|
+| [claim] | [source] | Observed/Inferred/Hypothesized | High/Medium/Low |
+```
+
+## Constraints
+
+- Ground every job, outcome, and score in evidence from ICP candidates, research, specs, feedback, or codebase.
+- Use Ulwick's canonical outcome statement format — do not shortcut to vague needs language.
+- Prioritize underserved outcomes as innovation targets; do not optimize for overserved outcomes.
+- Do not prescribe UI or architecture — describe the customer need, not the solution.
+- Present findings before writing.
+- Do not overwrite existing output without asking the user first.
+- This is a sub-skill — do not emit next-step routing.
+
+## 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/jtbd-needs-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-research/claude/customer-discovery/frameworks/jtbd-needs/archive/v0.3/SKILL.md

@@ -0,0 +1,234 @@
+---
+name: jtbd-needs
+description: Ulwick/Christensen JTBD — identify jobs, map desired outcomes, score importance vs satisfaction, and segment ICP candidates by unmet needs
+type: research
+version: v0.3
+invocation: sub-skill
+parent: customer-discovery
+---
+
+## 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 `npx skillpacks install <pack>` from the project shell, instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# JTBD Needs — Ulwick/Christensen Outcome-Driven Innovation
+
+## 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. Push back clearly and cite the evidence when the user appears to misunderstand.
+- For taste, prioritization, or subjective judgment calls: weigh user feedback heavily and adapt unless it conflicts with verified evidence.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## Prerequisites
+
+- **Hard**: ICP candidates from orchestrator working packet (`research/_working/preliminary-customer-discovery-research.md`) or `research/icp.md` (or `research/{slug}/icp.md`) must exist. If neither exists, tell the user to run `/customer-discovery` first and stop.
+- **Soft**: `research/competitive-analysis.md`, `research/customer-feedback.md`, idea brief, specs, and codebase context when available.
+
+## 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.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`.
+
+### 1. Load Context
+
+- Read ICP candidates from orchestrator working packet (`research/_working/preliminary-customer-discovery-research.md`) or `research/icp.md`
+- Read idea brief (`research/idea-scope-brief.md`) if it exists
+- Read `research/competitive-analysis.md` if it exists
+- Read `research/customer-feedback.md` if it exists
+- Read CLAUDE.md, README for product context
+- Scan codebase and existing research for additional signal
+
+### 2. Identify Jobs-to-be-Done
+
+For each ICP candidate, identify the full job landscape:
+
+**Functional jobs** — tasks and outcomes they need accomplished:
+- Core tasks they hire a solution to perform
+- Desired outcomes for each task (measurable results)
+- Related tasks that precede, follow, or co-occur with the core job
+- Frequency and context of job execution
+
+**Social jobs** — how they want to be perceived:
+- Professional reputation goals
+- Peer perception and status signals
+- Team/org perception of their decisions
+- Industry credibility and thought leadership
+
+**Emotional jobs** — how they want to feel:
+- Confidence and control over outcomes
+- Reduced anxiety about risks or unknowns
+- Satisfaction and sense of progress
+- Freedom from tedious or frustrating work
+
+**Related jobs** — adjacent jobs that create context:
+- Jobs performed immediately before and after
+- Jobs that share the same workflow or trigger
+- Jobs delegated to other roles that affect this one
+- Jobs that compete for the same time/attention
+
+**Consumption chain jobs** — jobs around acquiring, using, maintaining the solution:
+- Evaluate and select solutions
+- Onboard and learn the solution
+- Integrate with existing workflow
+- Maintain, update, and extend over time
+- Migrate away when the job changes
+
+### 3. Map Desired Outcomes
+
+For each job, write Ulwick outcome statements following the canonical format:
+
+`[Direction of improvement] + [performance metric] + [object of control] + [contextual clarifier]`
+
+Direction of improvement: Minimize, Maximize, Increase, Reduce, Eliminate, Optimize
+
+Examples:
+- "Minimize the time it takes to identify qualified leads in a new market segment"
+- "Reduce the likelihood of misallocating budget to underperforming channels"
+- "Maximize the percentage of outreach messages that receive a response"
+- "Minimize the number of tools required to complete end-to-end campaign analysis"
+
+Write 8-15 outcome statements per core functional job, 3-5 per social/emotional job.
+
+### 4. Score Importance & Satisfaction
+
+For each outcome statement, score based on available evidence (research, feedback, competitive analysis, codebase signals):
+
+- **Importance** (1-10): How important is achieving this outcome to the ICP candidate?
+- **Current Satisfaction** (1-10): How well do existing solutions satisfy this outcome?
+
+Calculate **Opportunity Score**: `Importance + max(Importance - Satisfaction, 0)`
+
+Classify each outcome:
+- **Underserved** (opportunity score ≥ 12): high importance, low satisfaction — prime innovation targets
+- **Appropriately served** (opportunity score 8-11): adequate current solutions exist
+- **Overserved** (opportunity score < 8): low importance or high satisfaction — potential to simplify/reduce
+
+### 5. Segment by Unmet Needs
+
+Cluster ICP candidates by shared patterns of underserved outcomes:
+
+- Identify candidates with similar underserved outcome clusters
+- Define natural segments based on shared unmet needs (not demographics)
+- Map cross-segment patterns: outcomes underserved across all candidates
+- Identify segment-specific opportunity areas unique to each cluster
+- Rank segments by total addressable opportunity (sum of opportunity scores for underserved outcomes)
+- Note which segments align with or diverge from demographic/firmographic ICP boundaries
+
+### 6. Validate with User
+
+Present jobs, outcomes, opportunity scores, and segment recommendations. Ask for corrections on:
+- Job completeness: missing jobs or mischaracterized job importance
+- Outcome accuracy: whether statements reflect real user language and priorities
+- Scoring calibration: whether importance/satisfaction estimates match known reality
+- Segment validity: whether proposed clusters reflect real behavioral differences
+
+## Output
+
+### `research/customer-discovery-jtbd-needs.md` (or `research/{slug}/customer-discovery-jtbd-needs.md`)
+
+```markdown
+# JTBD Needs Analysis
+
+> Based on: [sources]
+> Date: [current date]
+> Methodology: Ulwick/Christensen Outcome-Driven Innovation
+
+## ICP Candidate: [Name]
+
+### Functional Jobs
+| Job | Context | Frequency |
+|-----|---------|-----------|
+| [core task] | [when/where this job arises] | [how often] |
+
+### Social & Emotional Jobs
+| Type | Job | Evidence |
+|------|-----|----------|
+| Social | [how they want to be perceived] | [source] |
+| Emotional | [how they want to feel] | [source] |
+
+### Desired Outcomes & Opportunity Scores
+| Outcome Statement | Job | Importance | Satisfaction | Opportunity Score | Classification |
+|-------------------|-----|------------|--------------|-------------------|----------------|
+| [direction] + [metric] + [object] + [context] | [parent job] | 1-10 | 1-10 | calculated | Underserved/Served/Overserved |
+
+### Top Underserved Outcomes
+1. [outcome] — Opportunity Score: [score]
+2. [outcome] — Opportunity Score: [score]
+3. [outcome] — Opportunity Score: [score]
+
+## ICP Candidate: [Name 2]
+...
+
+## Opportunity Landscape
+| Outcome | Candidate(s) | Importance | Satisfaction | Opportunity Score |
+|---------|-------------|------------|--------------|-------------------|
+| [outcome] | [who shares it] | [avg] | [avg] | [score] |
+
+## Needs-Based Segments
+### Segment: [Name]
+- **Shared underserved outcomes**: [list]
+- **ICP candidates in segment**: [list]
+- **Total addressable opportunity**: [sum of opportunity scores]
+- **Distinguishing characteristic**: [what unites them beyond demographics]
+
+## Cross-Candidate Comparison
+| Candidate | Top Underserved Outcome | Segment | Total Opportunity |
+|-----------|------------------------|---------|-------------------|
+| [name] | [highest-scoring outcome] | [segment] | [sum] |
+
+## Evidence Matrix
+| Claim | Evidence Source | Evidence Type | Confidence |
+|-------|---------------|---------------|------------|
+| [claim] | [source] | Observed/Inferred/Hypothesized | High/Medium/Low |
+```
+
+## Constraints
+
+- Ground every job, outcome, and score in evidence from ICP candidates, research, specs, feedback, or codebase.
+- Use Ulwick's canonical outcome statement format — do not shortcut to vague needs language.
+- Prioritize underserved outcomes as innovation targets; do not optimize for overserved outcomes.
+- Do not prescribe UI or architecture — describe the customer need, not the solution.
+- Present findings before writing.
+- Do not overwrite existing output without asking the user first.
+- This is a sub-skill — do not emit next-step routing.
+
+## 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/jtbd-needs-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-research/claude/customer-discovery/frameworks/pmf-engine/ALIGNMENT-PAGE.md

@@ -57,7 +57,13 @@ 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-pmf-engine-research.md`; product-path mode uses `research/{slug}/_working/preliminary-pmf-engine-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-pmf-engine-research.md`; product-path mode uses `research/{slug}/_working/preliminary-pmf-engine-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.
+
+**PMF Engine translation.** Research focus: Gather real user evidence for Sean Ellis PMF signal, very-disappointed segmentation, retention/usage behavior, alternatives, and High-Expectation Customer synthesis. Separate observed user data from inference, sample assumptions, confidence, and decision impact. Review/documentation format: Render a data-readiness scorecard, PMF signal table, very-disappointed segment analysis, HXC profile, retention/behavior evidence matrix, confidence register, and minimum-evidence gaps. Suggested user feedback: Ask reviewers to confirm evidence completeness, segment cuts, sample-size and bias risks, HXC realism, product-focus implications, missing data, and whether PMF claims are sufficiently supported. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
+
+**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.
 
 **Glossary Additions gate.** When this research introduces domain-specific terms, acronyms, or concept definitions that a reader outside the project would not know, include a `## Glossary Additions` section in the alignment page. Render a table of proposed terms with columns: Term, Definition, Source (`pmf-engine`), Category (business/tooling/workflow/technical/domain), and per-term Approve/Edit/Reject/Flag radio controls. Only user-approved terms are appended to the target glossary (`research/glossary.md` or `research/{slug}/glossary.md` for scoped paths) during the confirmed-page write step. When the skill operates in a product-path scope, ask whether each term belongs in the parent or scoped glossary; default to the scoped glossary.
 

package/packs/business-research/claude/customer-discovery/frameworks/pmf-engine/CHANGELOG.md

@@ -1,5 +1,13 @@
 # pmf-engine changelog (claude)
 
+## v0.4 - 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.
+
+## v0.3 - 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.
+
 ## v0.2 - 2026-06-10
 
 - Added npm-aware `npx skillpacks install <pack>` wording to the Pack Availability Guard while preserving runner-specific in-agent pack install routes.

package/packs/business-research/claude/customer-discovery/frameworks/pmf-engine/SKILL.md

@@ -2,14 +2,14 @@
 name: pmf-engine
 description: Vohra/Supan PMF Engine - evaluate existing user data with Sean Ellis PMF signal, very-disappointed segmentation, retention/usage evidence, and High-Expectation Customer synthesis
 type: research
-version: v0.2
+version: v0.4
 invocation: sub-skill
 parent: customer-discovery
 ---
 
 ## 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. 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. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # PMF Engine - Vohra/Supan Product-Market Fit Analysis
 
@@ -28,7 +28,7 @@ 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.