opencode-skills-collection 3.1.11 → 3.1.13

package/bundled-skills/marketing-plan/references/measurement-framework.md

@@ -0,0 +1,213 @@
+# Measurement Framework — KPIs, North Stars, Cadence
+
+Every plan needs a measurement section that tells the team how to know if the plan is working. This doc is the source for Section 13's measurement subsection.
+
+**Related docs:**
+- `growth-patterns.md` — the 3-3-2-2-2 VC growth path (3× in years 1–2, 2× in years 3–7 from $1M ARR) and which phase of SaaS growth the company is in ($0–10K / $10K–100K / $100K–1M+)
+- `budget-planning.md` — CAC calculation (blended, not paid-only) and the forecasting reality check (forecasts under $100M ARR are educated guesses, not precise predictions)
+
+## The north-star principle
+
+A north star is one metric that captures the business-model thesis at the highest level. It should:
+- Be derivable from the funnel + revenue model
+- Move slowly enough to be a strategic compass (not whipsawed by weekly noise)
+- Trade off correctly against other metrics — improving the north star should generally improve the business
+
+Don't default to "ARR" or "MRR" alone. Those are outcomes, not norths. Pick something that captures the business model.
+
+## North-star patterns by business model
+
+### B2B SaaS (subscription)
+- **Net Revenue Retention (NRR)** — keeps existing customers + expansion in focus
+- Alternative: "Logo retention × expansion ARR"
+- Why: ARR alone hides churn / lets gross-add growth mask product fit problems
+
+### D2C consumer app (subscription)
+- **Blended LTV / blended CAC** — keeps unit economics honest as paid layer scales
+- Alternative: "Day-35 paid users from cohort × LTV"
+- Why: monthly subscription metrics are volatile; cohort × LTV smooths it
+
+### Hybrid hardware + software (e.g., Quietude)
+- **Blended LTV / blended CAC across hardware + software** — captures the wedge thesis
+- Alternative: "Hardware-buyers-to-subscriber conversion × blended margin"
+- Why: hardware revenue isn't free (cost to make); subscription revenue isn't expensive to acquire if hardware funds it
+
+### Marketplace (two-sided)
+- **Liquidity ratio × take-rate** — captures both sides + monetization
+- Alternative: "Monthly transacting users × take-rate × repeat frequency"
+- Why: GMV alone doesn't capture whether the marketplace is becoming a habit
+
+### Developer tool / open source
+- **Weekly active developers × paid-conversion** — captures both adoption and monetization
+- Alternative: "Weekly active orgs × seats per org × ARPU"
+
+### Content / media business
+- **Daily active readers / listeners × ad revenue per session** — captures both reach and monetization
+- Alternative: "Subscriber count × retention × ARPU"
+
+### Commerce (DTC, non-subscription)
+- **Repeat purchase rate × AOV × frequency** — captures monetization layered on quality of customer
+- Alternative: "Customer LTV / CAC × payback period"
+
+## Leading indicators by AARRR stage
+
+After the north star, every plan needs leading indicators per AARRR stage. These move faster than the north star and trigger investigations.
+
+### Acquisition leading indicators
+- Organic visits/month, total + per pillar (SEO health)
+- App Store / Play Store visit-to-install rate (ASO health)
+- Founder-led social channel growth → email subscriber conversion (LinkedIn / X / Substack funnels)
+- Event-to-app conversion rate (event ROI)
+- Ambassador-attributed visits (referral funnel)
+- Paid CAC by channel (when paid is firing)
+
+### Activation leading indicators
+- Day 1 / Day 7 / Day 35 → paid conversion rate
+- Onboarding session-completion rate
+- First key-action completion (post-signup activation event)
+- App Store conversion rate (install → trial → paid)
+- Trial → paid conversion rate
+
+### Retention leading indicators
+- Day 30 / Day 60 / Day 90 retention
+- Monthly churn rate (gross + net)
+- Lifecycle email engagement (open / click / unsubscribe by flow)
+- Hardware → app activation rate (for hybrid businesses)
+- Win-back / reactivation rate
+
+### Referral leading indicators
+- Ambassador-attributed new subs (via Dub or similar)
+- Share-after-value moment rate (% of users sharing)
+- Two-sided referral completion rate
+- Guides program referrals (when live)
+- NPS score (if surveyed)
+
+### Revenue leading indicators
+- ARPU by cohort
+- Annual plan adoption %
+- Cohort LTV by source
+- Plan mix shifts
+- Eye-mask / hardware attach rate (for hybrid)
+- Expansion revenue (B2B)
+
+## Review cadence
+
+The plan should specify three rhythms:
+
+### Weekly (operational sync)
+- **Who:** fCMO ↔ founder (CEO usually)
+- **Duration:** 30 min
+- **Format:** AARRR scoreboard (current vs. last week numbers across the leading indicators) + this week's ships + blockers
+- **Output:** Action items, decisions made
+
+### Monthly (metrics review)
+- **Who:** fCMO + founder + extended team (CXO, product lead, designer if applicable)
+- **Duration:** 60–90 min
+- **Format:** Full metrics review + comparison against quarterly KPI targets + qualitative learnings + idea bank reprioritization
+- **Output:** Possible plan adjustments, hire decisions
+
+### Quarterly (plan recalibration)
+- **Who:** fCMO + founders + key advisors
+- **Duration:** 2–3 hours
+- **Format:** Full plan review against 90-day and 12-month outcomes, channel-level analysis, funding-stage transition check, recalibration of next 90 days
+- **Output:** Updated plan (could be v2 / v3 document iteration)
+
+## KPI target setting
+
+For each quarter in Section 10, the plan must include 3–5 specific KPI targets. These should be:
+- **Specific** — not "improve retention," but "Day 30 retention from 22% → 30%"
+- **Measurable** — pull from a wired data source
+- **Stretch but plausible** — based on funnel state + historical patterns
+- **Decision-triggering** — if missed, what does that mean? (Adjust strategy, kill a channel, etc.)
+
+### KPI target patterns by quarter
+
+**Q1 (foundation quarter):**
+- Mostly *bedrock* metrics — fixing leaks. "Headphones-gate conversion drop reverses." "Day 1 → paid +25–50%."
+- Some *foundation* metrics — laying tracks. "4 SEO pillars staked." "App Store rewrite shipped."
+- Avoid bold growth targets — the foundations aren't in yet
+
+**Q2 (validation quarter):**
+- Mostly *validation* metrics — does what we built work? "Paid CAC < $X blended." "Organic traffic 1,500–3,500/mo."
+- Some *cohort* metrics — do new cohorts behave better? "Day 7 retention for Q2 cohort vs. Q1."
+
+**Q3 (scaling quarter):**
+- Mostly *scaling* metrics — how far does it go? "Paid scaling to $20–30K/mo with CAC steady." "First B2B install reference case live."
+- Some *capability* metrics — what new things are live? "First Guides pilot launched."
+
+**Q4 (compound quarter):**
+- Mostly *compound* metrics — is the flywheel turning? "50%+ of new subs from non-paid channels." "Ambassador-driven 15–25% of new subs."
+- Some *narrative* metrics — does the Series A story write itself? "Blended LTV/CAC > 3."
+
+## Anchoring against the VC growth path
+
+For VC-backed clients past $1M ARR, anchor 12-month and multi-year targets against the **3-3-2-2-2 rule** (3× in years 1 and 2, then 2× in years 3 through 7). Hitting it is rare; most companies don't. Anchoring against it forces the plan to either match it and show how, or explicitly defend choosing a slower trajectory. Full table and context in `growth-patterns.md`.
+
+For non-VC-backed companies (bootstrapped, founder-funded, profit-focused), the 3-3-2-2-2 doesn't apply. Use linear-pattern targets ("$X MRR added per month") or step-function targets ("$Y revenue jump after the enterprise tier launches") instead.
+
+## Forecasting reality check
+
+A plan derives a budget and an annual goal. It does not produce a 12-month month-by-month forecast that's reliably accurate to the dollar.
+
+**Unless the company is publicly traded, all forecasts are educated guesses.** No startup under $100M ARR consistently hits month-by-month forecasts. Quarterly review is when the plan adjusts — not when variance is treated as failure.
+
+What the plan commits to honestly:
+- The annual goal is a defensible direction-of-travel
+- The budget is the resource commitment that makes the goal plausible
+- The 90-day roadmap (Section 9) is what's actionable now
+- Month-to-month projection is illustrative, not promised
+
+Founders who over-engineer the forecast end up explaining variance every month instead of executing. The plan should resist this — name the annual target, the quarterly KPIs, and the kill criteria. Don't promise the month.
+
+Full context in `budget-planning.md`.
+
+## Kill criteria
+
+For every channel or initiative, the plan should specify when to stop. Often missing from plans, kill criteria force discipline.
+
+Examples:
+- "If a paid channel has CAC > 2× target after 30 days at meaningful spend, pause."
+- "If onboarding Variant 3 doesn't show statistically meaningful lift (or directional lift + congruent qualitative signal) after 4 weeks, move to Variant 1."
+- "If lifecycle Flow 4 has open rate < 12% after 6 weeks, redo subject lines + audience segmentation."
+
+## Guardrail metrics
+
+Some metrics get a hard guardrail (cannot drop below threshold). Useful for protecting brand or unit economics during aggressive growth.
+
+Examples:
+- "Brand voice complaint rate > 1% of customer feedback triggers content review."
+- "Paid CAC > $X for two consecutive months pauses paid scaling pending audit."
+- "App Store rating drops below 4.5 triggers product review."
+
+## Data sources mapping
+
+The plan should name where each metric comes from. This makes it auditable.
+
+| Metric | Source |
+|---|---|
+| Organic traffic | GA4 / Ahrefs |
+| App Store conversion | App Store Connect |
+| Funnel conversion (Day N → paid) | Internal analytics (Mixpanel / Amplitude) or App Store Connect cohort export |
+| Retention | Customer.io segments + product analytics |
+| MRR / ARR | Stripe (via MCP if wired) |
+| Plan mix | Stripe |
+| Lifecycle email metrics | Customer.io |
+| Ambassador attribution | Dub.co |
+| Hardware → app activation | Shopify + App Store + internal join |
+| NPS | Survey tool (Customer.io / Typeform / SurveyMonkey) |
+
+## When data isn't wired
+
+If a metric can't currently be measured, flag it in Section 13's open decisions. Example:
+
+> "Hardware → app activation rate not currently visible in the App Store dashboard. Requires Shopify ↔ App Store Connect join. Q1 work item."
+
+A plan with un-measurable goals is a plan that can't be validated. Surface the instrumentation work explicitly.
+
+## Reporting cadence + automation
+
+Where possible, auto-generate the metrics review rather than building it manually each time. Stripe MCP + GA4 MCP + Customer.io MCP can pull most of what's needed.
+
+For Tier 1 clients, a simple weekly metrics email to the team (Markdown table, generated via skills + MCPs) costs nothing and creates discipline.
+
+For Tier 2+ clients, consider a real dashboard (Hex, Metabase, Looker, or internal tool).

package/bundled-skills/marketing-plan/references/methodology.md

@@ -0,0 +1,363 @@
+# Methodology — How a Marketing Plan Gets Made
+
+The three-phase workflow that produces a comprehensive marketing plan. SKILL.md is the orchestration layer; this is the operational detail.
+
+## Phase 1 — INIT (research + intake)
+
+**Goal:** Walk into Phase 2 with enough context to draft every section without guessing.
+
+### Step 1.1 — Set up the plan folder
+
+Canonical file layout for every plan:
+
+```
+~/marketing-plans/{client-slug}/
+├── materials/         # Client-provided files (decks, audit output, brand-voice doc, etc.)
+├── research.md        # Written in Phase 1 (INIT)
+├── progress.md        # State machine — see Step 1.1.1 for schema
+├── sections/
+│   ├── 01.md          # Executive summary (written last, ordered first)
+│   ├── 02.md          # Strategic frame
+│   ├── ...
+│   └── 13.md          # Measurement, RACI, open decisions, appendix
+└── final_plan.md      # Compiled deliverable (Phase 3 output)
+```
+
+### Step 1.1.1 — `progress.md` state schema
+
+Every plan tracks a single `progress.md` file at the plan root. It's the source of truth for resumption. Schema:
+
+```markdown
+# {Client} — Marketing Plan Progress
+
+phase: init | review | finalize | finalized
+current_section: <number, only meaningful during review phase>
+plan_version: v1
+last_updated: YYYY-MM-DD HH:MM
+
+## Sections completed
+- [ ] 2. Strategic frame
+- [ ] 3. Current state
+- [ ] 4. Acquisition
+- [ ] 5. Activation
+- [ ] 6. Retention
+- [ ] 7. Referral
+- [ ] 8. Revenue
+- [ ] 9. 90-day roadmap
+- [ ] 10. 12-month outlook
+- [ ] 11. Marketing operations stack
+- [ ] 12. Tactical idea bank
+- [ ] 13. Measurement, RACI, open decisions, appendix
+- [ ] 1. Executive summary (synthesized last)
+
+## Approved artifacts
+sections/02.md, sections/03.md, ... (list as they're written)
+
+## Notes
+<any open decisions, blockers, or out-of-band context that aren't in research.md>
+```
+
+### Step 1.1.2 — Resumption decision tree
+
+On every invocation, check state in this order:
+
+1. **No `{client-slug}/` folder** → fresh plan. Create folder + `materials/` + empty `sections/`. Start INIT (Step 1.2).
+2. **Folder exists, no `research.md`** → INIT was interrupted. Resume from Step 1.2.
+3. **`research.md` exists, no `progress.md`** → INIT done, REVIEW not started. Create `progress.md`, start REVIEW from Section 2.
+4. **`progress.md` exists, `phase: review`** → REVIEW in progress. Resume from `current_section` (or first unchecked box).
+5. **`progress.md` exists, `phase: finalize`** → FINALIZE was interrupted. Re-run Phase 3.
+6. **`progress.md` exists, `phase: finalized`** → plan is done. **Do not silently overwrite.** Ask the user: *"This plan is finalized (v{N}). Want to (a) revise it as v{N+1}, (b) start a fresh plan in a new folder, or (c) re-open a specific section?"*
+
+Update `phase` and `last_updated` whenever state changes.
+
+### Step 1.2 — Read existing materials
+
+If `materials/` has files, read all of them. Common drops:
+- Pitch deck / investor deck
+- Positioning doc / brand voice doc
+- Customer research / ICP doc
+- App Store metrics / analytics snapshot
+- Lifecycle email inventory
+- Prior audit output (any scored current-state assessment the team has run)
+- SEO research (`seo/plan.md`, `seo/keyword-shortlist.md`)
+- Kickoff call transcript
+- Founder Slack / async notes
+
+Read everything. Capture key facts to `research.md` as you go.
+
+### Step 1.3 — Pull live data where wired
+
+If MCPs/APIs are wired for this client, pull:
+
+- **Ahrefs** → domain rating, organic keywords, backlinks, top pages, ref domains (per `/seo-audit` skill)
+- **GA4 MCP** → traffic by channel, conversion events, retention curves
+- **Stripe MCP** → MRR, ARR, churn, plan mix, blended LTV by cohort
+- **App Store Connect** (manual or `dev-browser`) → install → trial → paid funnel; cohort retention
+- **Customer.io MCP** → flow inventory, send / open / click / unsubscribe rates
+- **Shopify** → product page conversion, AOV, repeat rate
+- **GitHub MCP** → repos inventory, last commit dates, what's stale
+- **Notion** → internal knowledge directory if exposed
+
+Don't ask the user to copy/paste data that can be pulled directly.
+
+### Step 1.4 — Conduct structured intake
+
+For every gap in the materials, ask the user. The minimum intake covers ten topics:
+
+#### Intake 1 — Client overview
+- What does the company do, in one sentence (founder's words)?
+- What's the primary product?
+- What other products / SKUs / tiers exist?
+- Is the product live, beta, or pre-launch?
+- If beta: throttling? GA timeline?
+
+#### Intake 2 — ICP
+- Who are you for, in one sentence?
+- What do they say they want?
+- What do they actually want?
+- What's their stated problem? Their real problem?
+- Demographics / firmographics: who fits the ICP exactly?
+
+#### Intake 3 — Funnel state today
+- What are the current funnel numbers? (signups, activations, paid, retention)
+- What's the funnel *shape* — is it bottle-necked at top, middle, or bottom?
+- What's the biggest leak?
+
+#### Intake 4 — Funding state
+- Current round (pre-seed / seed / Series A / etc.)?
+- Total raised to date?
+- Current burn / runway?
+- Active raise? Closing when?
+- Investors of note?
+- Permission to mention fCMO engagement in pitches?
+
+#### Intake 5 — Team
+- Founders and what each owns (product, marketing, sales, etc.)?
+- Other roles on the team and their marketing surface area?
+- Advisors who touch marketing?
+- Agencies / contractors / fractionals?
+- Where are the obvious gaps?
+- For the team's current marketing owner (if there is one): is the shape π-shaped (two deep skill sets), T-shaped (one deep, broad), or tactical-only? See `team-and-agency-model.md` for the framework that informs Section 11 RACI and the first-hire recommendation in Section 9.
+
+#### Intake 6 — Budget
+- Current monthly marketing spend, broken down: paid acquisition, tools, retainers, headcount?
+- Budget tier this maps to (see `funding-stage-unlocks.md`)?
+- What budget unlocks when the next round closes?
+- Blended CAC if known (including salaries, content costs, tools, retainers — not just paid ad spend). If unknown, flag as the top Section 13 open decision — every revenue projection depends on it.
+- ARPC, annual retention rate (or churn rate), so the budget math in `budget-planning.md` can be applied to Section 8 (Revenue) and Section 10 (12-month outlook).
+
+#### Intake 7 — Channels currently active
+- Acquisition: organic SEO, paid search, paid social, content, social, partnerships, events, PR, ambassadors, etc. — for each, status (live / paused / never tried)
+- Activation: onboarding state, signup flow, paywall, first-session experience, app store listing
+- Retention: lifecycle email state, in-app upsells, churn cohort
+- Referral: program existence, attribution, inbound interest
+- Revenue: pricing structure, plan mix, recent experiments
+
+#### Intake 8 — Already done
+What past work should this plan acknowledge?
+- Major launches and dates
+- PR moments and who covered
+- Content pillars / hubs / cornerstone pieces
+- Partnerships
+- Awards / certifications
+- Notable customers / users (if consumer-named users)
+- Past advisors / fractionals
+
+#### Intake 9 — In-flight and stuck
+- What's drafted but not shipped? Why?
+- What's been "almost ready" for months?
+- What's blocking each?
+- What's broken or actively harmful?
+
+#### Intake 10 — Strategic posture
+- The most important thing to fix this quarter (founder's read)
+- The most important thing to ignore this quarter (founder's read)
+- What investors / board are asking about most
+- Any constraints not visible elsewhere (legal, partnership-related, brand-related)
+
+### Step 1.5 — Score current state against the rubric
+
+Use the 17-section rubric in `references/current-state-rubric.md` as your scoring lens. Two modes:
+
+- **From rich materials.** When the team has shared decks, prior content audits, an existing brand voice doc, recent positioning work, or a kickoff call transcript — score from those. Mark "scored from materials" in the section heading.
+- **From a separately scored audit.** If the team already has a scored current-state assessment (in any format), ingest those numbers directly. Don't redo the work.
+
+Either way, the output is the scored 17-row table that becomes Section 3 of the plan, followed by a 2–4 sentence "shape interpretation" calling out where strengths and gaps cluster.
+
+### Step 1.6 — Write research.md
+
+Compile everything into `research.md` with this structure:
+
+```markdown
+# {Client} — Marketing Plan Research Record
+
+**Date:** YYYY-MM-DD
+**Author:** (fCMO / planner name)
+
+## Company snapshot
+- One-sentence description
+- Stage (pre-seed / seed / Series A / etc.)
+- Product status (beta / GA)
+
+## ICP
+- Primary ICP
+- Stated vs. actual problem
+- Demographics / firmographics
+
+## Funnel state today
+- Current numbers
+- Funnel shape
+- Biggest leak
+
+## Funding
+- Total raised
+- Current round status
+- Runway
+
+## Team
+- Founders and ownership
+- Marketing surface area by person
+- Gaps
+
+## Current marketing budget
+- $/mo total
+- Breakdown
+- Tier mapping
+
+## Channels currently active
+[By AARRR stage]
+
+## Already done (acknowledge in plan)
+[List]
+
+## In-flight and stuck
+[List with blockers]
+
+## Strategic posture
+- Founder's top priority
+- Founder's top de-prioritization
+- Investor pressure points
+- Constraints
+
+## Current-state rubric scores
+[17 section scores using `references/current-state-rubric.md`. If a prior scored audit exists, paste those scores. Otherwise mark "scored from materials."]
+
+## Materials read
+[List of files in materials/ + when read]
+```
+
+Save. Move to Phase 2.
+
+---
+
+## Phase 2 — REVIEW (section-by-section drafting)
+
+**Goal:** Walk through all 13 sections of the plan template (`references/plan-template.md`), drafting each, getting user confirmation, saving as you go.
+
+### Step 2.1 — Initialize progress.md
+
+Use the schema defined in Step 1.1.1 above. Set `phase: review`, `current_section: 2`, `plan_version: v1`, and stamp `last_updated`.
+
+### Step 2.2 — Walk each section in this order: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, then 1
+
+Section 1 (Executive Summary) is drafted **last** because it depends on every other section's conclusions. Walk Sections 2 → 13 in numeric order, then synthesize Section 1 from the others. The final compiled `final_plan.md` is always presented in canonical order 1 → 13.
+
+For each section, use the template at `references/plan-template.md` to draft. Then in chat:
+
+1. Present the draft (or key bullets — short sections inline, long sections as bullet outline first)
+2. Ask: *"Approve, adjust, or expand?"*
+3. Iterate until user confirms
+4. Save the confirmed text to `sections/01.md` ... `sections/13.md` (one file per section, zero-padded for sort order). This is the canonical persisted artifact — recovery depends on it.
+5. Check the box in `progress.md`
+6. Move to next section
+
+### Step 2.3 — Section-specific guidance
+
+**Section 1 (Executive summary)** is synthesized from Sections 2–13 after they're all approved. Draft it last; present it first in the output document.
+
+**Section 3 (Current state)** uses the embedded 17-section rubric in `references/current-state-rubric.md`. If a prior scored audit exists, paste those scores in. If not, score from available materials.
+
+**Sections 4–8 (AARRR)** each follow the same internal structure: current state, the plan (numbered moves), 90-day moves, 12-month outlook, skills + tools. Don't skip the skills + tools sub-section — it's what makes the plan operationally honest.
+
+**Section 11 (Marketing operations stack)** is auto-generatable from `references/ops-stack-mapping.md` plus the specific moves named in Sections 4–8.
+
+**Section 12 (Idea bank)** is auto-generatable from `references/idea-cross-reference.md` plus client-specific filters (skip ideas that conflict with brand voice; status moves based on funding-stage timing).
+
+**Section 13** lives at the end. Open decisions should be ranked by impact. Appendix should reference only files the team can access (warn about machine-local paths).
+
+### Step 2.4 — Brand voice consistency
+
+If the client has documented brand voice rules (captured in research.md / Section 2), every section must respect them. Common voice constraints:
+- Vocabulary rules (YES / NO lists)
+- CTA rules (e.g., "never pressure")
+- Initiatory vs. explanatory framing
+- Tone (e.g., authoritative-yet-accessible, intimate-yet-professional)
+
+If a section's draft violates the brand voice, redo it before showing it to the user.
+
+---
+
+## Phase 3 — FINALIZE (compile + verify + publish)
+
+**Goal:** Produce `final_plan.md` and optionally publish to a shared repo.
+
+### Step 3.1 — Compile
+
+Set `phase: finalize` in `progress.md` before starting. Concatenate `sections/01.md` through `sections/13.md` into `final_plan.md` (canonical order 1 → 13, regardless of drafting order). Add:
+- Title header with date and "v1" version marker
+- "Prepared by / For / Date / Status" frontmatter
+- Section anchors that work in Notion paste
+
+### Step 3.2 — Verification pass
+
+Before printing:
+
+- **Cross-reference check** — every marketing-ideas number (e.g., "idea #17") matches the actual idea in `references/idea-cross-reference.md`. Every related-skill mention either exists in the `marketingskills` repo or is documented as an external dependency (see ops-stack-mapping note on cross-marketplace skills).
+- **MCP/API check** — every tool mentioned in Section 11 actually exists in the user's stack (per research.md intake) OR is flagged as "future / not yet wired."
+- **Path check** — no machine-specific paths (`/Users/...`, `/home/...`) in the output. Replace with descriptive references.
+- **Voice check** — final read against brand voice rules. Flag and fix violations.
+- **Open-decisions check** — every "TBD" or unanswered question from intake is listed in Section 13's open decisions, not hidden in the body.
+- **Acknowledge check** — every item from "already done" in research.md is acknowledged somewhere in the plan.
+
+### Step 3.3 — Print
+
+Output `final_plan.md` to the plan folder. Print a summary to chat:
+
+> *"Marketing Plan v1 saved to `~/marketing-plans/{client-slug}/final_plan.md`. ~X,XXX words across 13 sections. Ready to paste into Notion or share with the team."*
+
+### Step 3.4 — Publish (optional)
+
+Ask the user:
+> *"Want me to publish this to a shared GitHub repo so the team can access it? If yes, what's the target repo and path (e.g., `{client-org}/{client-context}/marketing/plan.md`)?"*
+
+If yes:
+- Clone (or assume cloned) target repo
+- Check out a feature branch or push direct to main per user's preference
+- Copy `final_plan.md` to the target path
+- Adjust the appendix to use repo-relative paths (not machine paths)
+- Commit + push
+- Confirm with commit URL
+
+If no: leave it local. Done.
+
+### Step 3.5 — Mark finalized
+
+Set `phase: finalized` in `progress.md` and stamp `last_updated`. This is the terminal state and prevents future `/marketing-plan` invocations from silently overwriting the plan (see Step 1.1.2 case 6).
+
+---
+
+## Resuming a plan
+
+Resumption is governed entirely by the decision tree in Step 1.1.2 above — always check state in that order on every invocation.
+
+If the user says *"start over"* → ask whether they want to delete the existing folder or move it to `archive/` first; don't silently overwrite.
+If the user says *"redo Section X"* → uncheck that box in `progress.md`, delete `sections/0X.md`, and re-draft.
+
+## Failure modes to watch for
+
+- **Skipping intake.** A plan written without proper intake is generic and won't survive contact with the founder. Always do the full ten-topic intake unless the user explicitly waives it.
+- **Pretending data exists.** If you can't confirm a number (current MRR, retention rate, etc.), don't guess. Mark it `[TBD — to confirm with team]` in the plan and add to open decisions.
+- **Ignoring the brand voice.** If the client has a strong voice (most do), every section must respect it. Read the voice rules before drafting any copy-adjacent text.
+- **Padding the idea bank.** Section 12 is comprehensive only if it includes the skip list with reasons. Don't pad with ideas that clearly don't fit just to hit the 139.
+- **Glossing over uncomfortable metrics.** If churn is high or activation is low, name it in Current State. Founders read past sugar-coating.
+- **Forgetting funding-stage logic.** If the client is mid-raise, the plan must explain what changes when the round closes. Skipping this turns a plan into a wish-list.