skillpacks 0.1.1 → 0.1.2

package/packs/business-ops/codex/reconcile-research/archive/v0.9/SKILL.md

@@ -0,0 +1,294 @@
+---
+name: reconcile-research
+description: Cross-document consistency audit across research outputs — find contradictions, stale assumptions, and gaps
+type: research
+version: v0.9
+argument-hint: "[audit|fix] [all|icp|pricing|journey|enterprise|feedback|specs]"
+interview_depth: none
+---
+
+# Reconcile Research — Cross-Document Consistency Audit
+
+Invoke as `$reconcile-research`.
+
+## Report-First Approval Gate
+
+Default to scope-first approval: before synthesized research, inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions in a `review` alignment page plus a concise conversation summary.
+
+Do not perform synthesized research, rank candidates, make recommendations, or write working packets or canonical deliverables until final compiled YAML approves the research scope. Minimal pre-approval discovery may identify available files, source categories, and open questions; label it as scope evidence, not findings.
+
+After approved research-scope YAML, perform the research and write only the non-canonical working packet defined in the staged workflow. Then update the `review` alignment page with findings and stop again for feedback-only YAML or final compiled YAML artifact approval before creating or updating canonical research, spec, or task files.
+
+Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.
+
+## Staged Research Workflow
+
+Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
+
+1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled YAML approval of the research scope. Do not perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+3. **Stage 3 - Finalize approved artifacts.** Consume final compiled YAML for artifact approval only when it has no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths below, and convert the alignment page to `confirmed` with the approval record preserved.
+
+Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.
+
+## Evidence And Feedback Handling
+
+Treat user feedback as input to evaluate, not as automatic ground truth.
+
+- For factual, evidentiary, technical, or source-backed claims: verify against available evidence. If the user appears to misunderstand the evidence or states something factually incorrect, push back clearly and cite the evidence. Do not rewrite findings merely to agree.
+- For taste, brand, positioning preference, risk appetite, prioritization, or other subjective judgment calls: weigh user feedback heavily and adapt the recommendation unless it conflicts with verified evidence.
+- When feedback mixes facts and preference, separate them explicitly: correct the factual part, then incorporate the preference where it is a legitimate judgment call.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## 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 `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
+3. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
+4. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
+5. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
+6. If no product directories exist, use flat `research/` single-product mode.
+7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
+
+### 1. Determine Mode and Scope
+
+Parse `$ARGUMENTS`:
+
+- **Mode**: `audit` (default, read-only) or `fix` (apply approved changes, write reconciliation report)
+- **Scope**: `all` (default), `icp`, `pricing`, `journey`, `enterprise`, `feedback`, or `specs`
+
+### 2. Inventory Research Documents
+
+Scan `research/` for main documents. Skip files matching `*-search-log.md` and `*-interview.md` — these are raw logs, not assertion-bearing documents.
+
+**Expected documents** (not all need to exist):
+- `research/icp.md` (cross-path overview), `research/{slug}/icp.md` (per-product-path)
+- `research/competitive-analysis.md` (or `research/{slug}/competitive-analysis.md`)
+- `research/journey-map.md` (or `research/{slug}/journey-map.md`)
+- `research/metrics.md` (or `research/{slug}/metrics.md`)
+- `research/gtm.md` (or `research/{slug}/gtm.md`)
+- `research/monetization.md` (or `research/{slug}/monetization.md`)
+- `research/enterprise-icp.md` (or `research/{slug}/enterprise-icp.md`)
+- `research/customer-feedback.md` (or `research/{slug}/customer-feedback.md`)
+
+When `research/` contains subdirectories, scan each `research/{slug}/` for per-product-path documents.
+
+**Stop condition**: If fewer than 2 research documents exist, display a message and exit — there's nothing to reconcile.
+
+### 3. Extract Claims
+
+Launch a **subagent per document** to extract structured claims. Each subagent reads one file and returns claims in these categories:
+
+| Category | Examples |
+|----------|----------|
+| **ICP targets** | Primary persona, company size, industry, geography |
+| **Pain points** | Problems the product solves, severity rankings |
+| **Budget signals** | Willingness to pay, price sensitivity, deal size |
+| **Channels** | Acquisition channels, distribution strategy |
+| **Messaging** | Value propositions, positioning statements |
+| **Pricing** | Model type, price points, tier structure, usage limits |
+| **Journey stages** | Stage names, transitions, aha moments, activation criteria |
+| **Metrics** | North star, per-stage metrics, thresholds |
+| **Competitors** | Named competitors, positioning relative to them |
+| **Deal-killers** | Enterprise blockers, compliance requirements |
+| **Feedback verdicts** | Validated assumptions, invalidated assumptions, new findings |
+
+Each claim includes the source file, section heading, and a direct quote for traceability.
+
+### 4. Cross-Reference Checks
+
+Launch **subagents per scope group** to run pairwise checks. Only run checks where both documents in a pair exist.
+
+#### `icp` scope — ICP vs all downstream (11 checks)
+
+Requires: `research/icp.md` + at least one downstream document.
+
+| # | Check | Documents | What to flag |
+|---|-------|-----------|--------------|
+| 1 | User profile consistency | ICP ↔ Journey Map | Journey references personas not defined in ICP |
+| 2 | Pain point coverage | ICP ↔ Competitive Analysis | Competitive analysis addresses pains not in ICP, or misses ICP pains |
+| 3 | Pain point → feature mapping | ICP ↔ Journey Map | Journey stages that don't map to any ICP pain point |
+| 4 | Budget signal → pricing alignment | ICP ↔ Monetization | Pricing exceeds ICP budget signals, or ignores stated willingness-to-pay |
+| 5 | Channel consistency | ICP ↔ GTM | GTM targets channels the ICP doesn't use, or misses primary ICP channels |
+| 6 | Messaging ↔ value prop alignment | ICP ↔ GTM | GTM messaging doesn't reflect ICP's top pain points or value props |
+| 7 | Market landscape agreement | ICP ↔ Competitive Analysis | ICP market sizing contradicts competitive analysis market data |
+| 8 | Feedback invalidation | ICP ↔ Customer Feedback | Feedback explicitly invalidates ICP assumptions still stated as fact |
+| 9 | Metric coverage of ICP goals | ICP ↔ Metrics | ICP success criteria not tracked by any metric |
+| 10 | ICP ↔ enterprise profile conflicts | ICP ↔ Enterprise ICP | Base ICP and enterprise ICP contradict on overlapping fields |
+| 11 | Geography/segment consistency | ICP ↔ GTM | GTM targets geographies or segments not mentioned in ICP |
+
+#### `pricing` scope — GTM vs Monetization coherence (7 checks)
+
+Requires: `research/gtm.md` + `research/monetization.md`.
+
+| # | Check | What to flag |
+|---|-------|--------------|
+| 1 | Revenue model agreement | GTM and Monetization describe different revenue models |
+| 2 | Price point consistency | GTM pricing references don't match Monetization's price points |
+| 3 | Tier structure alignment | GTM tier names/features don't match Monetization tier definitions |
+| 4 | Upgrade trigger consistency | GTM conversion triggers contradict Monetization's upgrade triggers |
+| 5 | Expansion metric alignment | GTM growth metrics don't match Monetization's expansion revenue drivers |
+| 6 | Aha moment → pricing gate | Monetization gates features before the aha moment defined in Journey Map |
+| 7 | Free tier scope | GTM's free tier description contradicts Monetization's free tier limits |
+
+#### `journey` scope — Journey Map vs Metrics/GTM/Monetization (7 checks)
+
+Requires: `research/journey-map.md` + at least one of Metrics/GTM/Monetization.
+
+| # | Check | What to flag |
+|---|-------|--------------|
+| 1 | Stage name consistency | Metrics or GTM reference journey stages by different names |
+| 2 | Metric coverage per stage | Journey stages with no corresponding metric in Metrics |
+| 3 | Aha moment agreement | Journey Map, Metrics, and Monetization define different aha moments |
+| 4 | Activation criteria consistency | Journey Map activation ≠ Metrics activation definition |
+| 5 | Channel → stage mapping | GTM channels don't map to the discovery/awareness stages in Journey Map |
+| 6 | Conversion trigger alignment | Journey Map conversion triggers ≠ GTM conversion triggers |
+| 7 | Retention stage coverage | Journey Map has retention stages that Metrics doesn't track |
+
+#### `enterprise` scope — Enterprise ICP vs base docs (6 checks)
+
+Requires: `research/enterprise-icp.md` + at least one base document.
+
+| # | Check | What to flag |
+|---|-------|--------------|
+| 1 | Profile field conflicts | Enterprise ICP contradicts base ICP on overlapping demographics |
+| 2 | Deal-killer coverage | Enterprise deal-killers not addressed in Journey Map or Monetization |
+| 3 | Stakeholder journey gaps | Enterprise stakeholders have no corresponding journey in Journey Map |
+| 4 | Pricing tier fit | Monetization tiers don't include an enterprise tier matching Enterprise ICP needs |
+| 5 | Lifecycle stage coverage | Enterprise evaluation→deployment→renewal lifecycle not reflected in Metrics |
+| 6 | Compliance gap propagation | Enterprise compliance requirements not reflected in scale-audit or journey |
+
+#### `feedback` scope — Customer Feedback propagation (5 checks)
+
+Requires: `research/customer-feedback.md` + at least one other document.
+
+| # | Check | What to flag |
+|---|-------|--------------|
+| 1 | Invalidated assumptions still present | Feedback marks an assumption as invalidated, but the source doc still states it as fact |
+| 2 | New findings not captured | Feedback identifies new pain points or personas not reflected upstream |
+| 3 | Severity mismatches | Feedback downgrades a pain point's severity, but ICP still lists it as primary |
+| 4 | Staleness alerts | Documents haven't been updated since feedback was last appended |
+| 5 | Contradicted positioning | Feedback contradicts GTM messaging or competitive positioning |
+
+#### Product-path checks (3 checks)
+
+Triggered when `research/` contains product-path subdirectories (e.g., `research/{slug}/icp.md`).
+
+| # | Check | What to flag |
+|---|-------|--------------|
+| 1 | Cross-ICP consistency | Product-path ICPs (`research/{slug}/icp.md`) contradict each other on shared market assumptions |
+| 2 | Shared pain point divergence | Same pain point described differently across product-path ICPs |
+| 3 | Channel overlap conflicts | Product-path ICPs target the same channel with conflicting messaging |
+
+### 5. Aggregate and Classify Findings
+
+Collect all findings from the cross-reference subagents. Classify each by severity:
+
+| Severity | Meaning | Example |
+|----------|---------|---------|
+| **Error** | Active contradiction — two documents assert incompatible facts | ICP says "SMB $50/mo budget" but Monetization's cheapest tier is $200/mo |
+| **Warning** | Stale or gap — may be intentional but should be reviewed | Journey Map defines 5 stages but Metrics only covers 3 |
+| **Info** | Suggestion — not wrong, but could be improved | GTM mentions a channel not discussed in ICP (may be a valid expansion) |
+
+### 6. Walk Through Findings Interactively
+
+Present findings **one at a time** using `request_user_input` (in Plan mode) or a plain-text question (otherwise), ordered by severity (Errors first, then Warnings, then Info). For each finding, present:
+
+```
+### [Scope] — [Check Name]
+**Severity**: Error | Warning | Info
+**Documents**: file-a.md ↔ file-b.md
+
+**file-a.md** says:
+> [direct quote from source]
+
+**file-b.md** says:
+> [direct quote from source]
+
+**Contradiction**: [one-sentence description of the conflict]
+**Recommended resolution**: [which document to update and why, based on dependency direction]
+
+How would you like to resolve this? (Options: accept recommendation, update the other document instead, skip/defer, or provide custom instructions)
+```
+
+**Dependency direction** informs the recommended resolution:
+- Upstream contradiction (e.g., ICP vs Journey Map) → recommend updating the downstream document
+- Customer feedback contradictions → recommend updating upstream (feedback is ground truth)
+- Peer contradictions (e.g., GTM vs Monetization) → note both are peers and ask which is authoritative
+
+Wait for the user's response before proceeding to the next finding. Collect all decisions into a resolution list.
+
+### 7. Apply Resolutions
+
+After walking through all findings:
+
+- **Audit mode** (default): Compile a summary of all findings and user decisions. Do not modify any files. Display the summary with the user's stated resolution for each item.
+- **Fix mode** (if `fix` was specified):
+  1. For each existing research document that will be replaced or substantively rewritten, archive the current file first, then apply the user-approved change to the canonical research document.
+  2. Write `research/reconciliation-report.md` as an audit trail:
+
+```markdown
+# Reconciliation Report — [date]
+
+## Resolved
+- [Error/Warning description] — resolved by archiving and updating [file] per user decision: "[user's stated resolution]"
+
+## Deferred
+- [Description] — user chose to skip
+
+## Info (no action)
+- [Info items the user chose not to act on]
+```
+
+  3. Re-run the audit to confirm fixes resolved the flagged issues.
+
+### 8. Populate Next Steps
+
+After presenting findings (audit mode) or applying resolutions (fix mode), display a `## Next Steps` section with a **Recommended** item and **Other options**. Use this format:
+
+## Next Steps
+
+**Recommended:** [skill with most conflicts] — [N] conflicts traced to this document; re-running it will resolve the most inconsistencies at once
+
+Other options:
+- `$skill` — [N] conflicts in [scope] (re-run to fix)
+- check `.agents/project.json.enabled_packs` for `research-admin` — if `research-admin` is not enabled, recommend `npx skillpacks install research-admin` from the project shell, first; if `research-admin` is enabled, recommend `$research-roadmap` — rebuild the ordered documentation queue after reconciliation
+- check `.agents/project.json.enabled_packs` for `agent-work-admin` — if `agent-work-admin` is not enabled, recommend `npx skillpacks install agent-work-admin` from the project shell, first; if `agent-work-admin` is enabled, recommend `$spec-drift` — check whether code/spec drift remains after research reconciliation
+- check `.agents/project.json.enabled_packs` for `agent-work-admin` — if `agent-work-admin` is not enabled, recommend `npx skillpacks install agent-work-admin` from the project shell, first; if `agent-work-admin` is enabled, recommend `$roadmap` — resequence implementation if reconciliation changed priorities
+
+**Recommendation logic:** Identify the skill that produced the document with the most Error/Warning-severity conflicts. That skill is the recommendation — re-running it with current upstream context will resolve the most issues. List other conflict-bearing skills as alternatives, ordered by conflict count descending. If audit mode found only deferred items, or fix mode resolved every actionable conflict, check `.agents/project.json.enabled_packs` for `research-admin` — if `research-admin` is not enabled, recommend `npx skillpacks install research-admin` from the project shell, first; if `research-admin` is enabled, recommend `$research-roadmap` — check overall project status. If no conflicts, deferred items, or follow-up work remain, explicitly state "No follow-up skill recommended" instead of inventing work.
+
+## 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
+
+- **Read-only by default.** Only modify files when explicitly invoked with `fix` mode.
+- **Never auto-resolve contradictions.** Errors always require user input on which side is correct. Use `request_user_input` (or plain-text question) for each finding individually.
+- **Show evidence.** Every finding must include direct quotes from both documents.
+- **Respect dependency direction.** Upstream documents are presumed authoritative over downstream, except customer feedback which is ground truth.
+- **No false positives.** If uncertain whether something is a real contradiction, classify it as Info, not Error.
+- **Skip absent documents.** Only run checks where both documents in a pair exist. Never flag a missing document as an error — that's `$research-roadmap`'s job.
+- **Use subagents** for claim extraction (one per document) and cross-reference checks (one per scope group) to parallelize work.
+- **Idempotent.** Running audit twice with no changes between should produce identical output.
+
+## 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/reconcile-research-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/codex/repo-glossary/ALIGNMENT-PAGE.md

@@ -57,7 +57,9 @@ 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-repo-glossary-research.md`; product-path mode uses `research/{slug}/_working/preliminary-repo-glossary-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-repo-glossary-research.md`; product-path mode uses `research/{slug}/_working/preliminary-repo-glossary-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.
 
 **Glossary audit gates.** Render the seven term categories (existing, missing, conflicting, stale, shadowed, cross-path divergences, and inheritance gaps) as separate gate sections. Each category must include per-term inline radio questions for the user to approve, edit, reject, or flag terms. Include an evidence matrix mapping proposed changes to source documents. The glossary approval gate must show term, proposed definition, source, category, origin (parent or scoped), and per-term action controls. For shadowed terms, show parent and scoped definitions side by side. For cross-path divergences, show each sibling definition with its slug. 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/repo-glossary/CHANGELOG.md

@@ -1,5 +1,9 @@
 # repo-glossary Changelog
 
+## 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 - 2026-06-11
 
 - Reclassified the active skill as `type: research` because it already uses the staged research lifecycle and writes approved glossary research artifacts.

package/packs/business-ops/codex/repo-glossary/SKILL.md

@@ -2,7 +2,7 @@
 name: repo-glossary
 description: Audit and reconcile the shared project glossary — find stale terms, missing definitions, conflicts, shadows, inheritance gaps, and cross-path divergences across research docs
 type: research
-version: v0.3
+version: v0.4
 argument-hint: "[optional: focus area e.g. \"tooling\", \"business\", \"workflow\"]"
 ---
 
@@ -209,7 +209,7 @@ Do not include `Recommended next skill`, `Recommended next command`, or downstre
 Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
 
 1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled YAML approval of the research scope. Do not perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
-2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
 3. **Stage 3 - Finalize approved artifacts.** Consume final compiled YAML for artifact approval only when it has no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths below, and convert the alignment page to `confirmed` with the approval record preserved.
 
 Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.

package/packs/business-ops/codex/repo-glossary/archive/v0.3/SKILL.md

@@ -0,0 +1,253 @@
+---
+name: repo-glossary
+description: Audit and reconcile the shared project glossary — find stale terms, missing definitions, conflicts, shadows, inheritance gaps, and cross-path divergences across research docs
+type: research
+version: v0.3
+argument-hint: "[optional: focus area e.g. \"tooling\", \"business\", \"workflow\"]"
+---
+
+# Repo Glossary — Glossary Audit & Reconciliation
+
+Invoke as `$repo-glossary`.
+
+Scans all research documents, CLAUDE.md, and docs for domain-specific terminology, then audits the shared glossary for accuracy, conflicts, staleness, shadows, inheritance gaps, and cross-path divergences. In multi-path repos, glossaries form a two-level hierarchy: a parent glossary (`research/glossary.md`) with shared terms and scoped glossaries (`research/{slug}/glossary.md`) that inherit parent terms and can override them. This is the look-back complement to the write-forward glossary convention: research skills add terms during their alignment flow, and this skill periodically reviews the full glossary hierarchy for drift and gaps.
+
+## Prerequisites
+
+- **Hard**: At least 2 files must exist in `research/` (or `research/{slug}/`). If fewer exist, tell the user to run more research skills first and stop.
+- **Soft**: `research/glossary.md` may or may not exist. If it does not exist, the skill runs in bootstrap mode — all discovered terms are treated as proposed additions.
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$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 Sources
+
+Read every file in scope and extract terminology. Load glossary files hierarchy-aware:
+
+**Parent glossary** (`research/glossary.md`):
+- Always load when it exists, even when running in scoped mode
+- Parse all existing entries from the Terms table (Term, Definition, Source, Category, Status, and optional Scope)
+- Parse Acronyms table and Recently Added table
+- Tag each term with origin `parent`
+
+**Scoped glossary** (`research/{slug}/glossary.md`):
+- Load the target scoped glossary when running in product-path mode
+- Parse Terms table (Term, Definition, Source, Category, Status — no Scope column)
+- Tag each term with origin `scoped:{slug}`
+
+**Sibling glossaries** (cross-path audit mode):
+- When auditing across all product paths, also load `research/{other-slug}/glossary.md` for each active product path
+- Tag each sibling term with origin `scoped:{other-slug}`
+
+**Research documents** (`research/*.md` or `research/{slug}/*.md`):
+- Extract terms that appear with inline definitions, parenthetical expansions, or "i.e." / "a.k.a." markers
+- Extract capitalized compound nouns or quoted terms used as domain jargon
+- Extract acronyms used without expansion
+
+**Convention and documentation files** (`CLAUDE.md`, `docs/*.md`, `packs/*/PACK.md`):
+- Extract terms defined in glossary-like sections, definition lists, or tables
+- Extract tool/workflow/concept names that carry project-specific meaning
+
+Build a combined term index: `{ term, definition (if found), sources[], category (inferred) }`.
+
+### 2. Surface & Interrogate
+
+Cross-reference the combined term index against the existing glossary to classify every term into one of four groups:
+
+**Existing terms** — present in glossary.md:
+- Check whether the current definition still matches how the term is used across research docs
+- Flag terms whose usage has drifted from the glossary definition
+- Show source count and last-seen document
+
+**Missing terms** — used in research docs but absent from glossary:
+- Propose a definition based on context where the term appears
+- Infer category (business / tooling / workflow / technical / domain)
+- Rank by frequency and number of distinct source documents
+
+**Conflicting terms** — same term defined or used differently across documents:
+- List each conflicting definition with its source
+- Ask user to select the canonical definition or provide a new one
+
+**Stale terms** — present in glossary but no longer appear in any scanned document:
+- Show the term, its glossary definition, and original source
+- Ask whether to keep, update, or remove
+
+**Shadowed terms** — same term defined in both parent and scoped glossary with different definitions:
+- Show parent definition and scoped definition side by side
+- Ask: intentional override (set `status: confirmed-override` in scoped) / promote scoped definition to parent / align scoped definition to match parent
+
+**Cross-path divergences** — same term defined differently in sibling scoped glossaries:
+- List each sibling's definition with its slug
+- Ask: all valid in context (each scope uses its own meaning) / reconcile to a shared parent definition / provide a new shared definition
+
+**Inheritance gaps** — hierarchy inconsistencies between parent and scoped glossaries:
+- Parent terms with Scope references to removed or archived product paths
+- Scope-restricted parent terms that conflict with their target scoped glossary's definition
+- Scoped terms that duplicate a parent term identically (candidate for removal from scoped glossary)
+
+If `$ARGUMENTS` specifies a focus area, filter findings to that category.
+
+### 3. Present in Alignment Page
+
+Build the alignment page with findings grouped by the four categories above. Each category is a gate section with inline approval questions:
+
+**For missing terms**: per-term radio — Approve proposed definition / Edit definition / Reject / Needs clarification
+**For existing terms**: per-term radio — Confirm accurate / Update definition / Remove / Needs clarification
+**For conflicting terms**: per-term radio showing each conflicting definition — select canonical / Provide new / Needs clarification
+**For stale terms**: per-term radio — Keep / Remove / Needs clarification
+
+**For shadowed terms**: per-term radio — Intentional override (confirm shadow) / Promote scoped to parent / Align scoped to parent / Needs clarification
+**For cross-path divergences**: per-term radio showing each sibling definition — All valid in context / Reconcile to parent / Provide new shared definition / Needs clarification
+**For inheritance gaps**: per-term radio — Fix scope reference / Remove duplicate from scoped / Update conflicting definition / Needs clarification
+
+Include an evidence matrix mapping each proposed change to the source documents that support it.
+
+### 4. Write Output
+
+After final compiled YAML approval, apply approved changes to the appropriate glossary file(s):
+
+**Base write rules** (apply to both parent and scoped glossaries):
+- Add approved new terms to the Terms table with `status: confirmed`
+- Update definitions for terms marked "Update definition"
+- Remove terms marked "Remove"
+- Resolve conflicts by writing the user-selected canonical definition
+- Update the Acronyms table for any new acronym expansions
+- Update the Recently Added table with terms added in this run
+- Update the header metadata (last updated date, source count, term count)
+
+**Hierarchy-aware write rules:**
+- **Promote scoped → parent**: add the term to the parent glossary with `Scope: shared`, remove the term from the scoped glossary
+- **Align scoped → parent**: update the scoped definition to match the parent, or remove the scoped entry entirely
+- **Acknowledge shadow**: set `status: confirmed-override` in the scoped glossary entry; future audits skip the shadow warning for that term
+- **Reconcile cross-path divergence**: write the reconciled definition to the parent glossary, remove or update sibling scoped entries
+- **Fix inheritance gap**: remove stale Scope references from parent, remove duplicate scoped entries that match parent identically
+- **Add Scope column**: add the Scope column to the parent glossary only when the repo has multiple active product paths; omit for flat repos
+
+If a target glossary does not exist, create it with the appropriate standard format before writing entries.
+
+**Standard parent glossary format** (multi-path repos — includes Scope column):
+
+```markdown
+# Glossary
+
+> Last updated: YYYY-MM-DD | Sources: [count] docs | Terms: [count]
+
+## Terms
+
+| Term | Definition | Source | Category | Status | Scope |
+|------|-----------|--------|----------|--------|-------|
+
+## Acronyms
+
+| Acronym | Expansion | Source |
+|---------|-----------|--------|
+
+## Recently Added
+
+| Term | Added | Source Skill | Approved In |
+|------|-------|-------------|-------------|
+```
+
+**Standard glossary format** (flat repos and scoped glossaries — no Scope column):
+
+```markdown
+# Glossary
+
+> Last updated: YYYY-MM-DD | Sources: [count] docs | Terms: [count]
+
+## Terms
+
+| Term | Definition | Source | Category | Status |
+|------|-----------|--------|----------|--------|
+
+## Acronyms
+
+| Acronym | Expansion | Source |
+|---------|-----------|--------|
+
+## Recently Added
+
+| Term | Added | Source Skill | Approved In |
+|------|-------|-------------|-------------|
+```
+
+### 5. Populate Next Steps
+
+Include 3–5 applicable items with "Pick one:" framing:
+
+- IF conflicting terms remain unresolved: `$repo-glossary` — Re-run to resolve remaining conflicts
+- IF assumption-tracker exists and references undefined terms: `$assumption-tracker` — Update assumption register with clarified terminology
+- IF research docs have many undefined terms: run more research skills to build context, then `$repo-glossary` again
+- IF glossary is comprehensive: `$reconcile-research` — Check cross-document consistency now that terms are aligned
+- ALWAYS: `$research-roadmap` — Check overall project status
+
+## 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.
+
+## Output
+
+### `research/glossary.md` (parent glossary)
+
+The shared cross-path project glossary in the standard parent format shown in Section 4. Includes the Scope column only in multi-path repos.
+
+### `research/{slug}/glossary.md` (scoped glossary, when product-path mode is active)
+
+The scoped glossary for a specific product path, inheriting all parent terms. Uses the standard format without the Scope column.
+
+## 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
+
+- **Read-only on research docs.** Extract terms from existing research — do not modify source documents. Only glossary files (`research/glossary.md` and `research/{slug}/glossary.md`) are writable.
+- **Be specific.** "A thing" is not a term. "Pack — a collection of related skills installed together via pack.sh" is.
+- **Trace to source.** Every term must reference the specific document it was extracted from.
+- **Update, don't duplicate.** If a glossary already exists, merge new findings with existing entries. When updating, preserve confirmation status, `confirmed-override` status, and Recently Added history.
+- **Present before writing.** Never write output files until findings have been presented and validated via the alignment page.
+- **Respect write-forward.** Terms added by research skills during their alignment flow have `status: confirmed`. Do not downgrade confirmed terms to `proposed` during audit.
+- **Hierarchy consistency.** A scoped glossary entry with `status: confirmed-override` is an acknowledged shadow — do not re-flag it as a conflict in future audits. When promoting or reconciling terms, ensure the parent and scoped glossaries remain consistent.
+
+## 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/repo-glossary-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.