skillpacks 0.1.1 → 0.1.2

package/packs/business-ops/codex/retro/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-retro-research.md`; product-path mode uses `research/{slug}/_working/preliminary-retro-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-retro-research.md`; product-path mode uses `research/{slug}/_working/preliminary-retro-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.
 
 **Risk-validation gates.** Render assumption/risk evidence coverage, confidence, candidate verdicts or mitigations, output-location/change-scope decisions, coverage checkpoint, and post-approval route as gates. Durable tracker outputs remain canonical markdown artifacts and must also be fully rendered in the alignment page. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
 

package/packs/business-ops/codex/retro/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v0.5 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.4 - 2026-06-10
 
 - Added npm-aware install-route guidance for business-ops cross-pack recommendations, preserving `$pack install <pack>` inside Codex while offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-ops/codex/retro/SKILL.md

@@ -2,14 +2,14 @@
 name: retro
 description: Strategic decision retrospective — review research decisions against actual outcomes, update confidence levels
 type: analysis
-version: v0.4
+version: v0.5
 argument-hint: "[optional: focus area e.g. \"ICP\", \"pricing\", \"channels\"]"
-interview_depth: light
+context_intake: scoped
 ---
 
 ## Pack Availability Guard
 
-When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # Retro — Strategic Decision Retrospective
 

package/packs/business-ops/codex/retro/archive/v0.4/SKILL.md

@@ -0,0 +1,246 @@
+---
+name: retro
+description: Strategic decision retrospective — review research decisions against actual outcomes, update confidence levels
+type: analysis
+version: v0.4
+argument-hint: "[optional: focus area e.g. \"ICP\", \"pricing\", \"channels\"]"
+interview_depth: light
+---
+
+## Pack Availability Guard
+
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Retro — Strategic Decision Retrospective
+
+Invoke as `$retro`.
+
+Reviews decisions made in research docs against actual outcomes. Was the primary ICP right? Did pricing work? Did the launch channel deliver? Captures lessons and updates confidence levels across all research documents.
+
+## Prerequisites
+
+- **Hard**: At least 2 research docs must exist, AND at least one source of outcome data must exist (`research/customer-feedback.md`, `research/cohort-review-*.md`, or `research/runway-model.md`). If no outcome data exists, tell the user there's nothing to retrospect against yet and stop.
+- **Soft**: The more research + outcome data exists, the richer the retro. Reads all of: `research/icp.md`, `research/competitive-analysis.md`, `research/journey-map.md`, `research/metrics.md`, `research/gtm.md`, `research/monetization.md`, `research/positioning.md`, `research/assumption-tracker.md`, `research/customer-feedback.md`, `research/cohort-review-*.md`, `research/runway-model.md`, `research/experiments/*.md`.
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$ARGUMENTS` names a non-archived `research/{slug}/` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product/app name, not the ICP, audience, or segment label.
+2. If `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
+3. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
+4. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
+5. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
+6. If no product directories exist, use flat `research/` single-product mode.
+7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
+
+### 1. Load Everything
+
+Read ALL research documents and outcome data. Build a map of:
+- **Decisions made**: Key choices documented in each research file (primary ICP, pricing model, launch channel, positioning, etc.)
+- **Predictions/targets**: Expected outcomes (metric targets, revenue projections, conversion estimates)
+- **Actual outcomes**: Real data from customer feedback, cohort reviews, runway model, experiment results
+
+### 2. Decision-by-Decision Review
+
+For each major decision found in research docs:
+
+#### A. ICP Decisions (from `research/icp.md`)
+- Was the primary ICP selection correct?
+- Did the pain points rank correctly?
+- Were the trigger events accurate?
+- Did the market sizing hold up?
+
+#### B. Competitive Decisions (from `research/competitive-analysis.md`)
+- Did the competitive landscape change?
+- Were the identified gaps real?
+- Did differentiation hold?
+
+#### C. Journey Decisions (from `research/journey-map.md`)
+- Did users follow the mapped journey?
+- Was the aha moment correctly identified?
+- Were the churn triggers right?
+
+#### D. Metrics Decisions (from `research/metrics.md`)
+- Were targets realistic?
+- Was the North Star metric the right choice?
+- Which metrics turned out to be leading vs. lagging indicators?
+
+#### E. GTM Decisions (from `research/gtm.md`)
+- Did the primary channel work?
+- Was the messaging effective?
+- Did the launch plan execute as designed?
+
+#### F. Monetization Decisions (from `research/monetization.md`)
+- Was the pricing model correct?
+- Were price points right?
+- Did unit economics match estimates?
+
+#### G. Positioning Decisions (from `research/positioning.md`)
+- Was the market category right?
+- Did the competitive framing resonate?
+- Was the target segment correct?
+
+For each decision, classify:
+- **Correct** — the decision was right, outcomes match
+- **Partially correct** — directionally right but details were off
+- **Wrong** — the decision was incorrect and outcomes show it
+- **Unknown** — insufficient outcome data to judge
+
+### 3. Pattern Analysis
+
+Look across all decisions for patterns:
+- **Systematic biases** — are we consistently too optimistic? Too conservative? Biased toward certain segments?
+- **Research gaps** — which decisions had the least evidence and turned out wrong?
+- **Compounding errors** — where did one wrong decision cascade into others?
+- **Surprising successes** — what worked that we didn't expect?
+- **Timing issues** — were decisions right but timing wrong?
+
+### 4. Present & Validate
+
+Present findings to the user. If the session is already in Plan mode and there are 2-3 concrete choices, prefer `request_user_input`; otherwise ask in plain text:
+- Summary of decisions reviewed and their correctness
+- Key patterns identified
+- Recommendations for which research docs to re-run
+
+Ask:
+- "Does this assessment feel accurate? Any decisions I'm judging too harshly or too generously?"
+- "Any context I'm missing about why certain decisions were made?"
+- "What surprised you most in practice vs. what the research predicted?"
+
+Incorporate feedback before proceeding.
+
+### 5. Populate Next Steps
+
+Include 3–5 applicable items with "Pick one:" framing:
+
+- IF ICP decisions were wrong: `$customer-discovery` — Re-run customer discovery with what you now know
+- IF pricing was wrong: `$monetization` — Revisit pricing with real revenue data
+- IF channels underperformed: `$gtm` — Update GTM with actual channel performance
+- IF assumptions tracker exists: `$assumption-tracker` — Bulk-update validation status from retro findings
+- IF metrics targets were off: `$metrics` — Recalibrate targets based on baseline reality
+- IF multiple docs need updating: `$reconcile-research` — Audit all research for consistency after retro findings
+- ALWAYS: `$research-roadmap` — Check overall project status
+
+### 6. Write Output
+
+Present final retro to user. Ask:
+- "Ready to write this? Anything to adjust?"
+
+Only after confirmation, write the output file.
+
+## Output
+
+### `research/retro-[YYYY-MM-DD].md` (or `research/{slug}/retro-[YYYY-MM-DD].md`)
+
+```markdown
+# Strategic Retro: [Date]
+
+> Date: [current date]
+> Period reviewed: [timeframe — e.g., "launch through Q1 2026"]
+> Research docs reviewed: [count]
+> Outcome data sources: [list]
+
+## Summary
+
+[3-5 sentences: the headline findings — what was right, what was wrong, and the biggest lesson]
+
+## Decision Scorecard
+
+| Area | Decision | Status | Evidence | Impact |
+|------|----------|--------|----------|--------|
+| ICP | [decision] | Correct/Partial/Wrong/Unknown | [data source] | [what it affected] |
+| Competitive | [decision] | ... | ... | ... |
+| Journey | [decision] | ... | ... | ... |
+| Metrics | [decision] | ... | ... | ... |
+| GTM | [decision] | ... | ... | ... |
+| Monetization | [decision] | ... | ... | ... |
+| Positioning | [decision] | ... | ... | ... |
+
+**Score**: [X/Y correct] — [percentage]
+
+## Detailed Analysis
+
+### What We Got Right
+[Decisions that were correct and why — what made the research good here]
+
+1. **[Decision]** — [evidence it was right] — [lesson: what to keep doing]
+2. ...
+
+### What We Got Wrong
+[Decisions that were wrong and why — what the research missed]
+
+1. **[Decision]** — [evidence it was wrong] — [lesson: what to change]
+2. ...
+
+### What We Got Partially Right
+[Decisions that were directionally correct but details were off]
+
+1. **[Decision]** — [what was right, what was off] — [lesson]
+2. ...
+
+## Patterns
+
+### Systematic Biases
+[Recurring patterns in how decisions were made — e.g., consistently overestimating market size, underestimating competition]
+
+### Research Gaps
+[Where lack of evidence led to wrong decisions — what should have been researched more]
+
+### Compounding Errors
+[Where one wrong decision led to others — the chain of consequences]
+
+## Confidence Updates
+
+Research docs that should be re-run based on retro findings:
+
+| Document | Current Confidence | Recommended Action | Why |
+|----------|-------------------|-------------------|-----|
+| research/icp.md | [High/Med/Low] | [Re-run / Update section / Keep] | [reason] |
+| research/gtm.md | [High/Med/Low] | [Re-run / Update section / Keep] | [reason] |
+| ... | | | |
+
+## Lessons Learned
+
+1. **[Lesson title]** — [description — specific, actionable, grounded in evidence from this retro]
+2. ...
+
+## Next Steps
+
+Pick one:
+- [conditional items from step 5]
+```
+
+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
+
+- **Evidence-based judgments.** Every "correct" or "wrong" assessment must cite specific outcome data. Don't judge decisions without evidence.
+- **No hindsight bias.** Judge decisions based on what was knowable at the time, not what we know now. A decision can be "right process, wrong outcome" — note when this is the case.
+- **Present before writing.** Never write output files until findings have been presented and validated.
+- **Separate dated files.** Each retro is a new file. Don't modify previous retros.
+- **Be constructive.** The goal is learning, not blame. Frame "wrong" decisions as lessons, not failures.
+- **Recommend actions.** Every finding should connect to a concrete next step for improving the research.
+- **Quarterly or milestone-based.** Designed for periodic use, not continuous. Note the recommended next retro date.
+
+## 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/retro-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/codex/risk-register/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-risk-register-research.md`; product-path mode uses `research/{slug}/_working/preliminary-risk-register-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-risk-register-research.md`; product-path mode uses `research/{slug}/_working/preliminary-risk-register-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.
 
 **Risk-validation gates.** Render assumption/risk evidence coverage, confidence, candidate verdicts or mitigations, output-location/change-scope decisions, coverage checkpoint, and post-approval route as gates. Durable tracker outputs remain canonical markdown artifacts and must also be fully rendered in the alignment page. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
 

package/packs/business-ops/codex/risk-register/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v0.4 - 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.
+
 ## v0.3 - 2026-06-10
 
 - Added npm-aware install-route guidance for business-ops cross-pack recommendations, preserving `$pack install <pack>` inside Codex while offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-ops/codex/risk-register/SKILL.md

@@ -2,15 +2,15 @@
 name: risk-register
 description: Broad risk assessment — key-person, technical, regulatory, competitive, financial, and execution risks beyond product/market
 type: analysis
-version: v0.3
+version: v0.4
 argument-hint: "[optional: focus area e.g. \"technical\", \"regulatory\", \"financial\"]"
-interview_depth: light
+context_intake: scoped
 visual_tier: visual
 ---
 
 ## Pack Availability Guard
 
-When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # Risk Register — Systematic Risk Assessment
 

package/packs/business-ops/codex/risk-register/archive/v0.3/SKILL.md

@@ -0,0 +1,220 @@
+---
+name: risk-register
+description: Broad risk assessment — key-person, technical, regulatory, competitive, financial, and execution risks beyond product/market
+type: analysis
+version: v0.3
+argument-hint: "[optional: focus area e.g. \"technical\", \"regulatory\", \"financial\"]"
+interview_depth: light
+visual_tier: visual
+---
+
+## Pack Availability Guard
+
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Risk Register — Systematic Risk Assessment
+
+Invoke as `$risk-register`.
+
+Identifies and tracks risks beyond product/market: key-person, technical, regulatory, competitive, financial, and execution risks. Complements `$assumption-tracker` (which focuses on product/market assumptions) with broader organizational and environmental risks.
+
+## Soft Prerequisites
+
+- Read all that exist: `research/icp.md`, `research/competitive-analysis.md`, `research/gtm.md`, `research/monetization.md`, `research/runway-model.md`, `research/assumption-tracker.md`, CLAUDE.md, README
+- The more context exists, the more thorough the risk identification.
+
+## 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 all available research docs and codebase files. Extract signals relevant to risk:
+- **Financial**: runway, burn rate, revenue concentration
+- **Technical**: tech debt, single points of failure, scaling concerns
+- **Market**: competitive threats, market shifts, regulatory changes
+- **Team**: key-person dependencies, skill gaps, hiring needs
+- **Execution**: timeline risks, scope creep, dependency chains
+
+### 2. Identify Risks
+
+Use WebSearch with **3-5 targeted queries** for domain-specific risks:
+1. "[industry/category] startup risks"
+2. "[category] regulatory requirements"
+3. "[technology stack] scaling risks"
+4. "[category] common failure modes"
+
+Systematically identify risks in each category:
+
+#### A. Key-Person Risk
+- Single points of failure in the team
+- Critical knowledge held by one person
+- Founder dependency
+
+#### B. Technical Risk
+- Architecture limitations, scaling bottlenecks
+- Security vulnerabilities, data privacy
+- Dependency on third-party services
+- Technical debt accumulation
+
+#### C. Regulatory & Legal Risk
+- Compliance requirements (GDPR, SOC2, industry-specific)
+- IP risks, patent exposure
+- Terms of service dependencies on platforms
+
+#### D. Competitive Risk
+- Well-funded competitor entering the space
+- Platform risk (building on someone else's platform)
+- Open-source alternatives emerging
+
+#### E. Financial Risk
+- Revenue concentration (one big customer)
+- Runway constraints
+- Pricing pressure from competitors
+- Cost structure changes (API pricing, infrastructure)
+
+#### F. Execution Risk
+- Scope creep, feature bloat
+- Hiring challenges
+- Timeline slippage
+- Integration complexity
+
+### 3. Score Each Risk
+
+| Dimension | Scale |
+|-----------|-------|
+| **Likelihood** | 1 (unlikely) → 5 (near certain) |
+| **Impact** | 1 (minor setback) → 5 (existential threat) |
+| **Priority** | Likelihood × Impact (max 25) |
+
+### 4. Define Mitigations
+
+For each high-priority risk (score ≥ 12):
+- **Accept**: Acknowledge and monitor
+- **Mitigate**: Actions to reduce likelihood or impact
+- **Transfer**: Insurance, contracts, or partnerships
+- **Avoid**: Change plans to eliminate the risk
+
+### 5. Present & Validate
+
+Present the top risks to the user. If the session is already in Plan mode and there are 2-3 concrete choices, prefer `request_user_input`; otherwise ask in plain text:
+- "Here are the highest-priority risks I've identified. Any I'm missing or scoring wrong?"
+- "Are there any risks you're already mitigating that I should note?"
+
+Incorporate feedback before proceeding.
+
+### 6. Write Output
+
+Only after confirmation, write the output file.
+
+## Output
+
+### `research/risk-register.md` (or `research/{slug}/risk-register.md`)
+
+```markdown
+# Risk Register
+
+> Last updated: [current date]
+> Sources: [research docs reviewed]
+> Total risks: [count] | High priority: [count]
+
+## Summary
+[2-3 sentences: the top risks and overall risk posture]
+
+## Top Risks
+
+| # | Risk | Category | Likelihood | Impact | Priority | Mitigation |
+|---|------|----------|-----------|--------|----------|------------|
+| 1 | [risk] | [category] | [1-5] | [1-5] | [L×I] | [strategy] |
+| ... | | | | | | |
+
+## Key-Person Risks
+| Risk | Likelihood | Impact | Priority | Mitigation |
+|------|-----------|--------|----------|------------|
+| [risk] | [1-5] | [1-5] | [L×I] | [action] |
+
+## Technical Risks
+[Same table format]
+
+## Regulatory & Legal Risks
+[Same table format]
+
+## Competitive Risks
+[Same table format]
+
+## Financial Risks
+[Same table format]
+
+## Execution Risks
+[Same table format]
+
+## Mitigation Plan
+
+### Immediate Actions (This Month)
+1. [Action] — mitigates [risk #]
+2. ...
+
+### Ongoing Monitoring
+| Risk | Trigger Signal | Check Frequency |
+|------|---------------|-----------------|
+| [risk] | [what to watch for] | [weekly/monthly/quarterly] |
+
+## Next Steps
+
+**Recommended:** [recommended skill] — [one-line reason grounded in the highest-priority risk]
+
+Other options:
+- `$assumption-tracker` — Cross-reference product/market assumptions with these broader risks
+- `$experiment [top risk assumption]` — Test the riskiest uncertainty when it can be validated cheaply
+- `$reconcile-research` — Update downstream research if risk findings contradict existing assumptions
+- `$research-roadmap` — Check overall project status
+```
+
+Create the `research/` directory if it doesn't exist.
+
+### 7. Populate Next Steps
+
+Before writing, choose one recommended next step using the first applicable rule:
+
+1. IF a high-priority risk is a product/market assumption: recommend `$assumption-tracker`.
+2. IF the top risk can be cheaply validated: recommend `$experiment [top risk assumption]`.
+3. IF the findings contradict existing research: recommend `$reconcile-research`.
+4. Otherwise recommend `$research-roadmap`.
+
+## 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
+
+- **Complement, don't duplicate.** Product/market assumptions belong in `$assumption-tracker`. Cover organizational, technical, regulatory, competitive, financial, and execution risks.
+- **Be specific.** "Competition" is not a risk. "Well-funded competitor X launching a free tier in Q3" is.
+- **Present before writing.** Never write until the user validates the assessment.
+- **Score honestly.** Don't inflate risks to seem thorough. Low-probability risks should be scored low.
+- **Update, don't duplicate.** If `research/risk-register.md` exists, ask whether to update or overwrite.
+
+## 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/risk-register-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/codex/runway-model/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-runway-model-research.md`; product-path mode uses `research/{slug}/_working/preliminary-runway-model-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-runway-model-research.md`; product-path mode uses `research/{slug}/_working/preliminary-runway-model-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Visual tier rendering.** This skill's alignment page uses the `visual` tier. Inline charts and diagrams are rendered via self-contained Canvas/SVG within the HTML file. Use the alignment chart snippet library (`scripts/alignment-chart-snippets.js`) as reference — copy needed chart functions directly into the page's `<script>` block. Charts must read CSS variables (`--chart-1` through `--chart-8`) for the data visualization palette. Every chart must include a `<table>` fallback, `aria-label` on canvas/SVG, and a "View as table" toggle. Data is embedded as inline JSON — no external fetches.