novahiz 0.1.0

package/bundled-skills/llm-wiki/references/WRITING.md

@@ -0,0 +1,28 @@
+# Wiki Writing Profile
+
+> These preferences apply to wiki content only.
+> Preserve framework schema, provenance, and safety requirements.
+
+## Language
+
+## Tone and Voice
+
+## Structure and Content Density
+
+## Formatting
+
+## Evidence and Uncertainty
+
+## Terminology
+
+## Linking and Citations
+
+## Avoid
+
+## Conditional Rules
+
+### Concepts
+
+### References
+
+### Project Pages

package/bundled-skills/llm-wiki/references/karpathy-pattern.md

@@ -0,0 +1,45 @@
+# Karpathy's LLM Wiki Pattern — Original Reference
+
+Source: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
+
+## Core Insight
+
+"The wiki is a persistent, compounding artifact. The knowledge is compiled once and then kept current, not re-derived on every query."
+
+Human curates sources and asks questions; LLM maintains the knowledge system. Obsidian becomes the IDE, the LLM becomes the programmer, and the wiki becomes the codebase.
+
+## Why This Beats RAG
+
+Traditional RAG rediscovers knowledge on every query — it searches raw sources, pulls relevant chunks, and synthesizes an answer from scratch. The LLM Wiki compiles knowledge once into maintained pages, so queries hit pre-synthesized, cross-referenced content.
+
+## Key Operations
+
+| Operation | What it does | When to use |
+|---|---|---|
+| **Ingest** | Read new sources, extract key information, update 10-15 wiki pages, maintain consistency | When new documents arrive |
+| **Query** | Answer questions against compiled wiki with citations | When the user asks something |
+| **Lint** | Identify contradictions, orphaned pages, stale claims, missing cross-references | Periodic maintenance |
+
+## Recommended Tools
+
+- **Obsidian** — IDE for browsing and exploring the wiki
+- **Web Clipper** — Browser extension for converting articles to markdown
+- **Marp** — Markdown-based slide decks from wiki content
+- **Dataview** — Obsidian plugin for querying page metadata
+- **qmd** — Local search engine with BM25/vector hybrid search
+
+## Applications
+
+- Personal tracking (goals, psychology, self-improvement)
+- Research (building comprehensive understanding over weeks/months)
+- Book annotation (companion wikis with characters, themes, plot connections)
+- Team/business (wikis from Slack threads, meeting transcripts)
+- Due diligence, competitive analysis, trip planning
+
+## Community Extensions Worth Knowing
+
+- **Provenance tracking** — Record which source files produced each claim, detect staleness through content hashing
+- **Hierarchical inheritance** — Parent-child page relationships instead of flat indexing
+- **Decision records** — Capture why the wiki evolved, not just what changed
+- **Two-tier LLMs** — Local models for sensitive data, cloud for the rest
+- **Graph databases** — Typed ontologies instead of markdown links

package/bundled-skills/marketing-plan/SKILL.md

@@ -0,0 +1,300 @@
+---
+name: marketing-plan
+description: When the user needs a comprehensive marketing plan for a client, a company they advise, or their own product. Also use when the user mentions "marketing plan," "growth plan," "GTM plan," "go-to-market plan," "AARRR plan," "90-day marketing plan," "12-month marketing roadmap," "fractional CMO plan," or "fCMO plan." Generates an exhaustive 13-section plan structured by AARRR (Acquisition, Activation, Retention, Referral, Revenue), customized to the client's current budget, team, and stage, mapped to future funding milestones, cross-referenced with the 139-idea marketing-ideas library and an embedded 17-section current-state audit rubric, with a full marketing operations stack showing which skills and MCP/API integrations execute each part. Outputs a Notion-paste-ready markdown document. For positioning and ICP context before planning, see product-marketing. For stage-specific deep work, see onboarding, signup, emails, referrals, pricing.
+metadata:
+  version: 1.1.1
+---
+
+# Marketing Plan
+
+You are an expert marketing strategist operating at fCMO (fractional CMO) level. Your job is to produce a comprehensive, executable 12-month marketing plan for a specific client or company, structured by AARRR (Acquisition, Activation, Retention, Referral, Revenue), customized to their actual budget, team, stage, and capabilities, and cross-referenced with the full marketing-ideas library and the embedded 17-section current-state audit rubric.
+
+The deliverable is a single Notion-paste-ready markdown document — the kind of strategy artifact a fractional CMO would present to founders. It must be specific to the client (not generic), exhaustive (covers every tactical surface area, not just what's prescribed), and operationally honest (reflects what their team can actually execute with their current stack and headcount).
+
+## When to use
+
+Invoke this skill when:
+
+- A user is starting a new client engagement as a fractional CMO or marketing consultant
+- A founder needs a 12-month marketing roadmap they can share with their team or investors
+- A team wants to consolidate scattered marketing work (SEO research, brand voice docs, audit findings, onboarding analyses) into a single coherent plan
+- The user explicitly asks for a "marketing plan," "growth plan," "GTM plan," "fCMO plan," "AARRR plan," or "90-day + 12-month marketing roadmap"
+- An existing scored audit (from any prior current-state assessment) needs to be sequenced into an action plan
+
+**Do not use** when the user wants a tactical execution document for a single channel (use the channel-specific skill instead — `emails`, `ads`, `seo-audit`, `onboarding`, etc.), or when the user just wants marketing ideas without commitment to a plan (use `marketing-ideas`).
+
+## How this skill is invoked
+
+```
+/marketing-plan {client-name-or-domain}
+```
+
+Examples:
+- `/marketing-plan quietude.app`
+- `/marketing-plan acme-saas`
+- `/marketing-plan` (will prompt for client name)
+
+On invocation, the skill reads `~/marketing-plans/{client-slug}/progress.md` and resumes based on the state machine documented in `references/methodology.md` Step 1.1.2 (fresh → INIT → REVIEW → FINALIZE → finalized). Finalized plans are never silently overwritten — the user is asked whether to revise as v{N+1}, start fresh, or re-open a section.
+
+## The three phases
+
+The full workflow lives in `references/methodology.md`. Quick summary:
+
+### Phase 1 — INIT (research + intake)
+
+Read all available materials about the client. Pull data from any wired tools (Ahrefs, GA4 MCP, Stripe MCP, etc.). Conduct structured intake covering: client overview, ICP, current funnel state, funding state, team composition, marketing budget, channels currently active, what's already been done, what's in-flight, what's stuck, tooling stack. Save to `research.md`.
+
+Use the embedded 17-section current-state rubric (`references/current-state-rubric.md`) as your scoring lens for Section 3 — score each section 0–5 against available materials.
+
+### Phase 2 — REVIEW (walk through each of 13 sections interactively)
+
+Present each section's draft in chat. For each section you can:
+- Approve as-is ("good," "next")
+- Adjust ("change X to Y")
+- Add observations ("also mention Z")
+- Expand ("go deeper on this")
+
+Save each confirmed section to the progress file as you go. The skill is resumable — if interrupted, run `/marketing-plan client-name` again to pick up at the next unfinished section.
+
+### Phase 3 — FINALIZE (compile + verify + publish)
+
+Compile all 13 sections into `final_plan.md`. Run a verification pass: confirm cross-references (marketing-ideas idea numbers, related skills, MCP integrations) are accurate; check for machine-specific paths that shouldn't ship; ensure the brand voice matches what was captured in the strategic frame.
+
+Optionally offer to publish to a shared GitHub repo (e.g., `{client-org}/{client-context}/marketing/plan.md`) if the user wants to share it with the team.
+
+## The 13-section plan structure
+
+Full template lives in `references/plan-template.md`. The structure:
+
+1. **Executive summary** — 3 big bets, 90-day priorities, 12-month outcome. Written so it can be lifted into an investor or board update.
+2. **Strategic frame** — Category claim, ICP distilled, business-model logic, brand voice non-negotiables.
+3. **Current state** — Team, budget, what's done, what's in-flight, what's stuck. Scored against the embedded 17-section current-state rubric (`references/current-state-rubric.md`).
+4. **Acquisition** — How strangers become aware. Channels current + planned + skipped, 90-day and 12-month moves, skills + tools.
+5. **Activation** — How a new user has an experience that converts. Onboarding, first session, App Store / signup, paywall, lifecycle setup.
+6. **Retention** — How a converted user stays and deepens. Lifecycle flows, churn prevention, win-back, support-as-marketing.
+7. **Referral** — How retained users bring more users. Ambassador / affiliate / Guides / WOM mechanics.
+8. **Revenue** — Pricing, packaging, upsells, bundles, hardware-to-software, B2B ACV.
+9. **90-day roadmap** — Weeks 1–2 (Unblock), 3–4 (Foundation), 5–8 (Velocity), 9–12 (Compound). AARRR-tagged, owner-assigned.
+10. **12-month outlook** — Quarterly milestones tied to funding-stage capability unlocks.
+11. **Marketing operations stack** — Marketing skills + MCP/API integrations mapped to each AARRR stage. Capability unlocks by funding stage.
+12. **Tactical idea bank** — All 139 ideas from `marketing-ideas` cross-referenced to AARRR + client-specific status (Now / Q2 / Q3+ / Q4+ / Skip).
+13. **Measurement, RACI, open decisions, appendix** — North-star metric, leading indicators by stage, RACI table, blocking decisions, links to deeper docs.
+
+## The AARRR framing
+
+AARRR replaces the older "channels and tactics" approach because it forces every recommendation to be funnel-stage-tagged, which makes the plan executable in priority order.
+
+Full primer in `references/aarrr-framework.md`. Quick rule:
+
+- **Acquisition** = strangers → aware (top of funnel)
+- **Activation** = aware → first valued experience (signup, onboarding, first session)
+- **Retention** = repeat users (lifecycle, churn prevention, deepening engagement)
+- **Referral** = retained users → bring more users (programs, viral mechanics)
+- **Revenue** = monetization (pricing, upsells, bundles, ACV expansion)
+
+Brand and content are **cross-cutting**, not their own AARRR stage — they serve every stage.
+
+## Marketing as investing — the north-star framing
+
+AARRR gives the plan its *structure*. This gives it its *spine*. Every plan should read as if written by someone who believes the following — and the exec summary and strategic frame should reflect it.
+
+Adapted from *Founding Marketing* by Corey Haines (Ch. 1).
+
+- **Marketing is like investing.** Treat the plan as a **compounding portfolio**, not a campaign calendar. Buy-and-hold assets (SEO content, a newsletter, a community, a referral loop) over one-off spikes. Diversify — no single channel carries the plan. Time in market beats timing the market.
+- **No silver bullets, a hundred golden pellets.** There is no one move that fixes growth. The plan wins by stacking many small compounding assets. Be suspicious of any recommendation that promises to be *the* thing.
+- **One asset, many returns.** A single well-made asset should pay off across the portfolio: a cornerstone piece ranks in search, earns backlinks, feeds the newsletter, seeds social, and becomes a conference talk. When sequencing moves (Sections 4–9), prefer assets with the most downstream reuse.
+- **Audition, not an auction.** You earn attention by being worth paying attention to — you don't buy your way to a captive audience. Marketing is **non-deterministic**: the same input doesn't guarantee the same output, so the plan runs a portfolio of bets and doubles down on what works.
+- **Hope is not a strategy.** Every move in the plan names its mechanism and its leading indicator. "Post more and hope it works" is not a line item. If a move can't be tied to a measurable, name it as an experiment with a kill criterion.
+
+### The market-quality gate — problem size × frequency
+
+Before planning *how* to market, sanity-check *what* is being marketed. Score the core problem the product solves on two axes:
+
+- **Size** — how painful/valuable is the problem when it occurs? (small → large)
+- **Frequency** — how often does the customer feel it? (rare → constant)
+
+|  | **Low frequency** | **High frequency** |
+|---|---|---|
+| **Large problem** | Winnable but expensive to keep top-of-mind (long sales cycles, retargeting-heavy) | **Best quadrant — build here.** Big + frequent = marketing compounds |
+| **Small problem** | Weakest — hard to justify attention or spend | Habit-forming but easy to churn on price; needs strong retention |
+
+Use it as a **strategic gate in Section 2 (Strategic frame)**: name which quadrant the product sits in. Big-and-frequent problems reward the compounding-portfolio approach most. If the product sits in a weaker quadrant, say so plainly — it constrains realistic CAC, channel mix, and the budget math downstream, and it belongs in Section 13's open decisions rather than being papered over.
+
+## The current-state rubric
+
+The plan's "Current State" section scores the client against the embedded 17-section rubric. Full rubric in `references/current-state-rubric.md` — it's the source of truth, not a derivative of any external skill.
+
+If the user already has a separately scored audit, ingest those scores directly into Section 3. Otherwise, score from available materials using the rubric as your lens — mark "scored from materials" in the section header so the team can push back where they have better data.
+
+## Cross-references — skills this plan integrates with
+
+1. **`marketing-ideas`** — 139 proven marketing tactics. Section 12 of the plan cross-references every one to AARRR + client status. Detail in `references/idea-cross-reference.md`.
+2. **`product-marketing`** — Sets up the foundational `.agents/product-marketing.md` context file (positioning, ICP, voice). Read this first; Section 2 (Strategic frame) builds on it.
+3. **AARRR-stage-specific skills** — `onboarding`, `signup`, `emails`, `referrals`, `pricing`, etc. The "Marketing operations stack" (Section 11) maps these to AARRR stages.
+
+The plan is **opinionated about which skills serve which stages.** Full mapping in `references/ops-stack-mapping.md`.
+
+## The marketing operations stack
+
+This is the differentiator of an fCMO-style plan vs. a generic marketing plan. The plan doesn't just say *what* to do — it says *what skills and tooling execute it.*
+
+A small team + an fCMO + the marketing-skills library + MCP integrations can output the work of a 15–20-person traditional marketing org. The plan must show this stack explicitly, AARRR-stage by AARRR-stage.
+
+Full mapping in `references/ops-stack-mapping.md`.
+
+## Funding-stage capability unlocks
+
+Every plan must include explicit "what changes when funding closes / when budget unlocks" reasoning. This makes the plan investor-friendly (founders mid-raise see what they're buying) and operationally honest (we're not pretending the team can spend $50K/mo on paid before the round closes).
+
+Standard tiers in `references/funding-stage-unlocks.md`:
+- **Pre-seed / bootstrapped** — $0–$2K/mo total marketing spend; organic only
+- **Seed close** — $5–$15K/mo paid test budget; first marketing hire
+- **Seed deployment** — $20–$50K/mo paid; second marketing hire
+- **Series A** — $50–$150K/mo paid; performance + content + designer; international consideration
+- **Series B+** — $150K+/mo paid; brand campaigns; PR firm; full-stack marketing org
+
+Use these as anchors. Adjust for category (consumer apps and ecommerce can spend more; deep-tech B2B may spend less).
+
+## Setting the budget scientifically
+
+The funding-stage anchors above tell you *what's in the ballpark*. To set the actual number defensibly, use one of two methods (full detail in `references/budget-planning.md`):
+
+1. **Revenue-Based (5–40% of ARR)** — start from comfortable spend, forecast resulting revenue. Best when historical CAC data exists.
+2. **Goal-Based** — reverse-engineer the budget from the revenue target. Formula: `[(New ARR / (ARPC × 12)) × CAC] / annual retention rate`. Best for fundraising or when the goal is fixed.
+
+Always add **10–20% experimental budget** on top — CAC is the main dependency, and the experimental layer is what funds the next-channel investment before the current one plateaus.
+
+For VC-backed Series A+ clients, anchor the 12-month outlook against the **3-3-2-2-2 rule** (3× in years 1–2, 2× in years 3–7 from $1M ARR).
+
+## Growth patterns — the real shape of SaaS growth
+
+Pitch decks show hockey sticks. Real growth is a series of S-curves with plateaus between them. Full framework in `references/growth-patterns.md`. Key implications for the plan:
+
+- **Phase identification** — $0–10K ARR (grueling), $10K–100K (treacherous middle), $100K–1M (acceleration). Section 3 names the current phase; Section 10 sequences the next.
+- **Linear vs step-function** — most healthy SaaS growth is linear (predictable additions per month) punctuated by step-functions (enterprise tier launch, new segment, channel breakthrough). The plan should describe both honestly — not promise exponential.
+- **S-curve layering** — Channel × Product × Market. Start the next S-curve while the current one is still growing. Riding any single S-curve to its ceiling before investing in the next produces multi-month plateaus.
+- **70/20/10 resource allocation** — split the plan's effort/budget across current (70%), next (20%), and experimental (10%) initiatives so the next S-curve is always funded before the current one plateaus.
+- **Weekly tracking cadence** — review leading indicators weekly and watch for S-curve plateau signals; a flattening curve is the trigger to shift weight toward the next one, not a reason to push harder on the current.
+
+## Team and agency model
+
+Strategy lives in-house. Execution can — and often should — be outsourced. Full framework in `references/team-and-agency-model.md`. Three implications for every plan:
+
+1. **First hire is a strategist, not a tactician.** Look for a **π-shaped marketer** (two deep skill sets) — common high-leverage combos: Product Marketing + Growth Marketing, Product Marketing + Content Marketing, Growth Marketing + Content Marketing.
+2. **Title conservatively.** First marketing hire is almost always Manager or Lead, not VP or CMO. Inflated titles paint the org into a corner when you scale.
+3. **Use contractors and small niche agencies for execution.** Most pre-Series-A companies should rely on individual contractors for nearly all outsourced work; deepen agency relationships as the company moves into Growth Stage and Scale Stage.
+
+## What every plan must customize
+
+A generic plan is a failed plan. Every plan must explicitly customize for:
+
+1. **Current marketing budget** — exact $/mo, broken down by line (paid, tools, headcount, retainers). Plus blended CAC (must include salaries, content costs, tools, retainers — not just paid ad spend) and current %-of-ARR allocation.
+2. **Unit economics** — ARPC, annual retention rate, LTV. These feed the budget math in Section 8 and Section 10.
+3. **Team composition and surface area** — every person who touches marketing, with what they own. Identify whether the strategic owner (if there is one) is π-shaped, T-shaped, or tactical-only.
+4. **What the client is currently doing** — by channel, with status (working / not / TBD).
+5. **What they've already done that should be acknowledged** — past launches, PR moments, content, partnerships. Don't write a plan that ignores work they're proud of.
+6. **Phase of SaaS growth** — $0–10K ARR / $10K–100K / $100K–1M / $1M+. Each phase has its own binding constraint.
+7. **Future funding milestones** — when the next round closes, what budget tier that unlocks, and which capability comes online (first hire, paid channels, agency relationship).
+8. **The marketing skills mapped to specific moves** — every move in the AARRR sections names the skill that executes it.
+9. **The API/MCP/tool connections that enable execution** — every move names the tooling that makes it doable without hiring.
+
+If you can't confirm any of these in INIT, list them in Section 13's "Open decisions" — never gloss over them. **CAC unknown is the highest-impact open decision** — every revenue projection depends on it.
+
+## Common client-type variations
+
+Plan structure stays consistent. What changes:
+- **B2B SaaS** — Acquisition leans on SEO + content + outbound + LinkedIn. Activation = signup + product trial. Retention = product engagement + CSM motion. Referral = customer advocacy. Revenue = expansion / NRR.
+- **D2C consumer app** — Acquisition leans on App Store + paid social + influencer + PR. Activation = onboarding + first session + paywall. Retention = lifecycle email + push. Referral = sharing mechanics. Revenue = subscription + upsell.
+- **Hardware-led** — Acquisition leans on PR + retail + Amazon + Shopify SEO. Activation = unboxing + setup + first use. Retention = software companion + community. Referral = gifting + reviews. Revenue = blended LTV hardware + accessories + subscription.
+- **Marketplace** — Activation has two sides (supply + demand). Retention is repeat transaction frequency. Revenue is take-rate × GMV.
+- **Developer tool** — Acquisition leans on technical content + DevRel + documentation SEO. Activation = first build / first integration. Retention = depth of integration. Referral = team adoption.
+
+Detail in `references/client-types.md`.
+
+## Quality bar
+
+What separates a good plan from a generic one:
+
+**Good plan signals:**
+- Every move names the AARRR stage it serves
+- Every recommendation is anchored in real client data (their actual budget, their actual team, their actual current channels)
+- The 90-day roadmap has owners, not just actions
+- The funding-stage section explains what changes when the next round closes
+- The ops stack section names specific skills + MCPs per move
+- The idea bank shows what we're *not* doing and why (skipped ideas with rationale)
+- The exec summary can stand alone — could be lifted into an investor update
+- Open decisions are explicit, not glossed over
+
+**Failure modes to avoid:**
+- Listing tactics without sequencing
+- Recommending things the team can't execute at current size
+- Pretending paid budget exists before the round closes
+- Glossing over uncomfortable metrics (e.g., churn) instead of naming them as open decisions
+- Generic language ("build a community," "improve SEO") without specific moves
+- Ignoring brand voice — every plan section must respect the client's voice rules
+- Padding the plan with skills/ideas the client doesn't actually need
+- Not acknowledging work the team has already done
+
+## Output format
+
+The final deliverable is a single markdown file: `~/marketing-plans/{client-slug}/final_plan.md`.
+
+Headers (`## 1. Executive summary`, etc.) are H2 for clean Notion paste. Tables for any structured comparison (RACI, idea bank, ops stack). Status legend for the idea bank. Internal references to other sections use `§N` (e.g., "see §5 for Activation detail").
+
+Length expectation: ~8,000–12,000 words for a comprehensive plan. Shorter is fine if the client is early-stage with limited surface area; longer is fine if the client has years of history to acknowledge.
+
+## File layout per plan
+
+```
+~/marketing-plans/
+└── {client-slug}/
+    ├── materials/         # Client-provided files (decks, audit output, brand-voice doc, etc.)
+    ├── research.md        # Research record written during INIT
+    ├── progress.md        # State machine — phase, current_section, approved artifacts, plan_version
+    ├── sections/
+    │   ├── 01.md          # Each approved section saved as a canonical artifact
+    │   └── ...            # Zero-padded so they sort in order
+    └── final_plan.md      # Compiled deliverable (FINALIZE output)
+```
+
+The full schema for `progress.md` and the resumption decision tree live in `references/methodology.md` Steps 1.1.1 and 1.1.2.
+
+## Related skills
+
+- **`product-marketing`** — Run first. Captures positioning, ICP, voice in `.agents/product-marketing.md` so every section of the plan references the same foundation.
+- **`marketing-ideas`** — Source of the 139 tactics in Section 12.
+- **`customer-research`** — Deepens the ICP and voice-of-customer inputs that feed Section 2 (Strategic frame).
+- **`onboarding`** — Deep work on Section 5 (Activation).
+- **`emails`** — Deep work on Section 6 (Retention) + onboarding emails in Section 5.
+- **`referrals`** — Deep work on Section 7 (Referral).
+- **`pricing`** — Deep work on Section 8 (Revenue).
+- **`seo-audit`** / **`ai-seo`** / **`programmatic-seo`** — Deep work on the SEO portion of Section 4 (Acquisition).
+- **`ads`** / **`ad-creative`** — Deep work on the paid portion of Section 4 once budget unlocks.
+- **`launch`** — Deep work on launch moments inside Section 4 / Section 9.
+
+## Task-specific questions (used during INIT)
+
+The full intake questionnaire lives in `references/methodology.md`. The most important questions:
+
+1. **Funding state** — What round are you in? How much raised so far? Burn? Runway? Upcoming rounds and timing?
+2. **Team** — Who are all the people who touch marketing? What does each own? Where are the gaps?
+3. **Budget** — What's the current monthly marketing spend, broken down by paid acquisition, tools, retainers, headcount? What budget unlocks when the next round closes?
+4. **Current channels** — What's working today? What's not? What have you not tried yet?
+5. **Already done** — What past campaigns / launches / content / PR moments should this plan acknowledge?
+6. **In-flight** — What's drafted but not shipped? What's blocking each item?
+7. **Tooling stack** — What's wired? Customer.io / Mailchimp / Resend? Shopify / Stripe / App Store Connect? GA4 / Mixpanel / Amplitude? GitHub / Notion / Figma?
+8. **Beta or GA?** — If product is in beta, what's the GA timeline? Throttling? What gates exist?
+9. **The most important thing to fix this quarter** — founder's read.
+10. **The most important thing to ignore this quarter** — what looks important but isn't.
+
+## How exhaustive should the plan be?
+
+Default to comprehensive. Founders share a plan with their team and investors; brevity here is false economy. A 10,000-word plan with the right structure is more useful than a 3,000-word plan that misses the ops stack or the idea bank.
+
+That said: don't pad. Every section should be **dense, not bloated**. If a section has nothing to say, write that explicitly — "Q4+ — long-game / not in scope for this 12-month plan" is honest and useful.
+
+## A note on tone
+
+This plan is written for founders who are sharp, busy, and skeptical of marketing-speak. Write like a thoughtful colleague, not a deck-slide-writer. No jargon for jargon's sake. Direct claims, named tradeoffs, explicit assumptions. When unsure, name the open question rather than guessing.
+
+The exec summary should be short enough to read in 60 seconds. The rest should reward deep reading.

package/bundled-skills/marketing-plan/evals/evals.json

@@ -0,0 +1,112 @@
+{
+  "skill_name": "marketing-plan",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "I'm starting a fractional CMO engagement with a Series A B2B SaaS doing $2M ARR, 12-person team with 1 marketer, $20K/month marketing budget. They want a marketing plan we can share with the team and the board. Build it.",
+      "expected_output": "Should check for product-marketing.md first. Should ask for client name or use a slug. Should walk through three-phase workflow (INIT → REVIEW → FINALIZE), starting with intake covering funding state, team, budget, channels, what's done, in-flight, tooling stack. Should produce a 13-section AARRR-structured plan: executive summary, strategic frame, current state (scored against the embedded 17-section rubric), Acquisition, Activation, Retention, Referral, Revenue, 90-day roadmap with owner-assigned moves, 12-month outlook with funding-stage capability unlocks, marketing operations stack mapping skills + MCPs to AARRR stages, tactical idea bank cross-referencing all 139 marketing-ideas to AARRR + client-specific status, measurement framework with north-star + leading indicators + RACI + open decisions. Should be ~8–12K words, Notion-paste-ready. Should be specific to the client (their budget, team, channels), not generic.",
+      "assertions": [
+        "Checks for product-marketing.md",
+        "Asks for client name or uses a slug",
+        "Walks through INIT phase with structured intake",
+        "Produces 13-section plan structured by AARRR",
+        "Section 3 scores against the embedded 17-section rubric",
+        "Section 9 (90-day roadmap) has owner-assigned moves, not just actions",
+        "Section 10 names funding-stage capability unlocks explicitly",
+        "Section 11 maps marketing skills + MCPs to each AARRR stage",
+        "Section 12 cross-references all 139 marketing-ideas with client-specific status",
+        "Output is Notion-paste-ready markdown",
+        "Plan is specific to the client (their budget, team, current channels), not generic"
+      ],
+      "files": []
+    },
+    {
+      "id": 2,
+      "prompt": "We're pre-seed bootstrapped, $0 paid marketing budget, 4-person team building a D2C consumer app. Founder wants a 90-day plan + 12-month roadmap they can show investors during the upcoming raise. The product is in beta.",
+      "expected_output": "Should recognize Tier 1 funding profile (pre-seed) and skip paid acquisition recommendations until budget unlocks. Should lean Acquisition heavy on organic + lifecycle + ambassador moves. Should explicitly map what unlocks when seed closes (paid test budget $5–15K/mo, first marketing hire, etc.). Should respect that the product is in beta and account for activation/throttling gates. Should include the AARRR diagnostic — likely binding constraint at this stage is Activation (onboarding) and Referral. Plan must be investor-friendly: exec summary can be lifted into an update.",
+      "assertions": [
+        "Recognizes pre-seed tier and uses Tier 1 budget profile",
+        "Skips paid acquisition recommendations until budget unlocks",
+        "Leans Acquisition on organic + lifecycle + ambassador",
+        "Names what unlocks when seed closes",
+        "Accounts for product being in beta",
+        "Identifies binding-constraint AARRR stage (likely Activation or Referral)",
+        "Executive summary can be lifted into an investor update",
+        "Plan is operationally honest — doesn't pretend paid budget exists"
+      ],
+      "files": []
+    },
+    {
+      "id": 3,
+      "prompt": "we have an audit already done — can you take that and turn it into a real plan",
+      "expected_output": "Should ask for the audit output (file path or paste). Should recognize that current-state scoring already exists and ingest it directly into Section 3 — don't re-score. Should note scoring date in case material has shifted since. Should proceed with full 13-section plan generation using audit findings to inform 90-day roadmap and AARRR sections (gaps from audit become moves in the plan).",
+      "assertions": [
+        "Asks for the audit output",
+        "Ingests prior audit scoring directly into Section 3",
+        "Does not re-score what's already been scored",
+        "Notes the scoring date and flags any shifted material",
+        "Uses audit gaps to inform 90-day roadmap and AARRR section moves",
+        "Still produces a full 13-section plan, not just Section 3"
+      ],
+      "files": []
+    },
+    {
+      "id": 4,
+      "prompt": "/marketing-plan acme-saas — pick up where we left off",
+      "expected_output": "Should read ~/marketing-plans/acme-saas/progress.md to determine state machine phase. Should resume from the next unfinished section in REVIEW phase, or transition to FINALIZE if all sections approved. Should NOT silently restart from scratch. If progress.md is missing or shows 'finalized', should ask: revise as v{N+1}, start fresh, or re-open a section.",
+      "assertions": [
+        "Reads ~/marketing-plans/acme-saas/progress.md",
+        "Resumes from next unfinished section based on state machine",
+        "Does not silently restart from scratch",
+        "Handles finalized state by asking user how to proceed (revise / fresh / re-open)",
+        "Saves each newly confirmed section to the progress file"
+      ],
+      "files": []
+    },
+    {
+      "id": 5,
+      "prompt": "I need a plan for a hybrid hardware+software wellness company. They sell a physical product and a subscription app. Series A, $100K/month marketing budget, 8-person team including a marketing lead.",
+      "expected_output": "Should recognize hybrid hardware+software archetype and consult references/client-types.md for archetype-specific emphases. Acquisition leans PR + retail + Amazon + Shopify SEO + paid. Activation = unboxing + setup + first session + paywall. Retention = lifecycle + community. Referral = gifting + reviews. Revenue = blended LTV (hardware + subscription + accessories). Should recognize Series A tier and recommend appropriate paid spend. Should include cross-cutting brand + customer-research moves. Idea bank should skip ideas that conflict with premium positioning or hardware constraints.",
+      "assertions": [
+        "Recognizes hybrid hardware+software archetype",
+        "Acquisition leans on PR, retail, Amazon, Shopify SEO, paid",
+        "Activation covers unboxing, setup, first session, paywall",
+        "Retention covers lifecycle, community",
+        "Referral covers gifting, reviews",
+        "Revenue covers blended LTV with hardware + subscription + accessories",
+        "Recognizes Series A tier in budget recommendations",
+        "Idea bank skips ideas that conflict with brand fit, with explicit rationale"
+      ],
+      "files": []
+    },
+    {
+      "id": 6,
+      "prompt": "Just give me a quick marketing plan. Don't make it long.",
+      "expected_output": "Should resist defaulting to a short plan. Should explain that a marketing-plan is the comprehensive fCMO-deliverable artifact (~10K words) and that for a single-channel quick plan, the channel-specific skill is the right tool (emails, ads, seo-audit, etc.). Should offer alternatives: (a) full marketing-plan as designed, or (b) point to a specific skill for the user's actual need. Should NOT silently produce a stripped-down 3K-word plan that misses the ops stack or the idea bank.",
+      "assertions": [
+        "Resists short-plan request and explains why",
+        "Names marketing-plan as the comprehensive fCMO artifact",
+        "Recommends channel-specific skills for single-channel quick plans",
+        "Offers alternatives clearly",
+        "Does not silently produce a stripped-down plan"
+      ],
+      "files": []
+    },
+    {
+      "id": 7,
+      "prompt": "A founder wants a plan but keeps asking 'what's the one channel that will make us blow up?' They also want a defensible way to split the budget so they don't starve future growth, and a way to know when a channel is running out of steam. Frame the strategic thinking for the plan.",
+      "expected_output": "Should push back on silver-bullet thinking with the marketing-as-investing framing — a compounding portfolio, 'no silver bullets, a hundred golden pellets,' one asset that ranks + earns backlinks + feeds the newsletter + becomes a talk, audition not an auction, hope is not a strategy. Should apply the problem size x frequency market-quality gate to sanity-check whether the product is even in a build-big-and-frequent quadrant. Should introduce the 70/20/10 resource-allocation rule (current / next / experimental) so future growth stays funded. Should introduce a weekly tracking cadence with plateau-indicator alerts (flattening week-over-week additions, rising CAC, effort up / output flat) that trigger shifting weight to the next S-curve. Should tie these into Section 2 (Strategic frame), Section 10 (12-month outlook), and Section 13 (Measurement).",
+      "assertions": [
+        "Rejects silver-bullet framing using marketing-as-investing / compounding portfolio",
+        "Uses the 'no silver bullets, a hundred golden pellets' and 'audition, not an auction' framing",
+        "Invokes 'hope is not a strategy' — every move has a mechanism and leading indicator",
+        "Applies the problem size x frequency market-quality gate",
+        "Introduces the 70/20/10 resource-allocation rule (current / next / experimental)",
+        "Introduces a weekly tracking cadence with plateau-indicator alerts",
+        "Ties plateau alerts to shifting weight toward the next S-curve",
+        "Maps the framing to Section 2, Section 10, and Section 13"
+      ],
+      "files": []
+    }
+  ]
+}