@rubytech/create-maxy-code 0.1.167 → 0.1.170

package/payload/premium-plugins/writer-craft/skills/voice-mirror/SKILL.md

@@ -0,0 +1,166 @@
+---
+name: voice-mirror
+description: "Capture the operator's authorial voice from their own writing and apply it to agent-drafted content. Activate when the operator asks to tag historical content as human-authored, to distil a style profile, to retrieve voice exemplars for a drafting task, or to record their edit on an agent draft as feedback. Other drafting skills (email composition, Postiz publisher, property-brochure, prospectus) call `voice-retrieve-conditioning` transparently — `voiceMirror: false` in the calling skill's frontmatter opts out."
+---
+
+# Voice Mirror
+
+Distil the operator's own voice from the content they have actually written, and condition agent drafts on it so generated copy reads as theirs. Anthropic models cannot be fine-tuned; voice mimicry comes from in-context conditioning — a style card plus a handful of real exemplars. The 1M context window makes this affordable.
+
+The skill is built on four deterministic MCP tools served by the `writer-craft` plugin's MCP server (`premium-plugins/writer-craft/mcp/`):
+
+| Tool | Purpose |
+|------|---------|
+| `voice-tag-content` | Stamp historical or new content nodes with `authorshipMode`. Bulk-tags arrays of node ids. |
+| `voice-distil-profile` | Walk the operator's `human-only` corpus and produce a `:VoiceProfile {styleCard, generatedAt, corpusSize, feedbackEntries}` node. |
+| `voice-retrieve-conditioning` | Return `{styleCard, exemplars[]}` for a drafting brief. K=5 for short-form, K=15 for long-form. Token-budget bounded. |
+| `voice-record-feedback` | When the operator edits an agent draft, write a `:VoiceEdit {originalText, editedText, intent, occurredAt}-[:FEEDBACK_FOR]->(:VoiceProfile)` node. The `intent` field is a Haiku-summarised diff. |
+
+## When to activate
+
+Activate when the operator says any of:
+
+- **"Tag this as me" / "I wrote that" / "mark these as human-only".** Drives `voice-tag-content`.
+- **"Build my voice profile" / "distil my style" / "rebuild the voice mirror".** Drives `voice-distil-profile`.
+- **"Read my writing first" / "draft this in my voice" — when the operator is asking for a hand-written-quality draft, not a generic AI reply.** Drives `voice-retrieve-conditioning`; the calling drafting skill is the actual surface, this skill is the conditioning input.
+- **"Use my edit as a teaching example" / "remember how I changed that".** Drives `voice-record-feedback`.
+- **"Review my historical writing and tag it" / "start the backfill".** Drives the interactive backfill flow described below.
+
+Do **not** activate for:
+
+- Writing-craft review tasks (`prose-craft`, `review-prose`, etc.). Those are critique skills, not voice-capture.
+- Public-figure voice mimicry. Out of scope — see the `## Out of scope` section.
+- Audio voice cloning. Different domain entirely.
+
+## Flow — backfill review (one-shot session)
+
+Run when the operator first installs voice-mirror, then whenever they want to refresh the corpus.
+
+### 1. Pick a corpus stream
+
+The operator's authored content lives in two stream shapes that the backfill UX handles differently:
+
+- **Discrete documents and posts** — `:KnowledgeDocument` (covers email threads via `source:'email'` since Task 321), `:SocialPost`, and one-off `:Message` nodes. Per-item tagging with previews.
+- **Chat archives** — conversation-document `:KnowledgeDocument` nodes (those carrying `conversationIdentity`) with their child `:Section` chunks. Per-conversation tagging because chunking happens server-side and the operator owns whole conversations, not individual chunks. Chat is the highest-leverage corpus — the unguarded voice that email rarely captures.
+
+Ask the operator which stream to backfill first. Default to chat archives when the account has any conversation-document `:KnowledgeDocument` nodes, because that's where voice signal is strongest.
+
+### 2a. Discrete documents — paginate in batches of 10
+
+Query for `:KnowledgeDocument | :SocialPost | :Message` nodes belonging to this operator's account whose `authorshipMode` is `unknown`. Order by `dateSent | datePublished | dateCreated` descending — most recent first. For each batch, surface a numbered list with: source label, date, recipient or topic, and a one-line preview (first ~120 chars of body). Offer bulk shortcuts:
+
+- `1-10 human-only` — tag every item in the batch as `human-only`.
+- `1,3,7 human-only` — tag a subset.
+- `2 human-led-agent-assisted` — single-item mode override.
+- `5 agent-led-human-reviewed` — single-item mode override.
+- `skip` — leave the batch as `unknown` and advance.
+- `stop` — exit the backfill; the next session resumes from where the operator left off.
+
+Bulk-tag via `voice-tag-content` once per operator response. Emit `[voice-tag] mode=<mode> count=<n>` per write.
+
+### 2b. Chat archives — paginate per conversation-document parent
+
+For each conversation-document `:KnowledgeDocument` (with `conversationIdentity` set) that has at least one `:Section` chunk whose `authorshipMode` is `unknown`, surface: source file, participant names, message count, date range, and a one-line summary. Offer:
+
+- `human-only` — tag every child `:Section` chunk in this conversation as `human-only`.
+- `mixed` — open the conversation for per-chunk tagging (rare; only when the archive contains multiple authors on the operator's side).
+- `not me` — tag every chunk as `agent-only` (e.g. a Slack channel where the operator only forwarded other people's messages).
+- `skip` / `stop` — same semantics as 2a.
+
+Bulk-tag via `voice-tag-content` with the list of `:Section` element IDs the conversation-document contains. The skill emits `[voice-tag] mode=<mode> count=<chunk-count>` once per conversation.
+
+Authorship at conversation granularity is a deliberate UX trade-off: chunks within a conversation almost always share the same operator's voice, and per-chunk tagging at archive scale would burn the operator's attention. The `mixed` opt-in covers the rare case where it matters.
+
+### 3. Distil when the corpus crosses threshold
+
+After each backfill batch, check whether the qualifying corpus (`authorshipMode IN ['human-only', 'human-led-agent-assisted']`) has grown ≥20% since the last `:VoiceProfile.corpusSize` (or ≥1 entry if no profile exists). If yes, offer to run `voice-distil-profile` immediately. The operator can defer; the next scheduled distillation will pick it up.
+
+## Flow — drafting-time conditioning
+
+Drafting skills (email composition, Postiz, property-brochure, prospectus) call `voice-retrieve-conditioning` transparently before assembling their prompt. The skill takes a brief — `{topic, format, register}` — and returns:
+
+```yaml
+styleCard: |
+  sentenceLengthDistribution: short-heavy (median 12 words)
+  register: warm-professional, British, contraction-friendly
+  favoured: ["properly", "the right thing", "happy to"]
+  avoided: ["circle back", "synergy", "leverage"]
+  taboos: ["per my last email", "kind regards"]
+  opening: drop the salutation if the thread is mid-flow; otherwise "Hi <name>,"
+  closing: "Best, Neo" — no signature block
+exemplars:
+  - source: Email to Sarah Knight, 2026-04-12, re: lease draft
+    body: "…actual operator-written paragraph…"
+  - source: SocialPost on LinkedIn, 2026-03-30
+    body: "…"
+```
+
+Drafting skills inject both blocks into their prompt. Opt-out is per-skill: declare `voiceMirror: false` in the skill's frontmatter and the calling site skips the fetch. Default is on.
+
+If the `:VoiceProfile` does not yet exist (corpus too small, or distillation never run), the tool returns `{styleCard: null, exemplars: []}` and the calling skill falls back to its existing default register. No error, no draft refusal.
+
+Emit `[voice-retrieve] task=<brief> styleCardBytes=<n> exemplarCount=<k> tokenBudget=<n>` per call.
+
+## Flow — feedback capture
+
+When the operator edits an agent draft (in the email composer's edit loop, or in any drafting skill that supports inline edits), capture the diff:
+
+1. The calling skill passes `{originalText, editedText}` to `voice-record-feedback`.
+2. The tool runs a Haiku diff summarisation to produce an `intent` field — a one-sentence description of what the operator changed and why. Example intents: "shorter and dropped the apology", "switched to first person", "removed sign-off", "added a specific date".
+3. The tool writes `(:VoiceEdit {originalText, editedText, intent, occurredAt, adminUserId, accountId})-[:FEEDBACK_FOR]->(:VoiceProfile)` for the operator's profile.
+
+Feedback accumulates between distillations. The next `voice-distil-profile` run reads every `:VoiceEdit` linked to the profile and feeds the intents into the style-card refinement.
+
+Emit `[voice-record-feedback] adminUser=<id> intent="<haiku-summary>" diffBytes=<n>`.
+
+## Distillation cadence
+
+`voice-distil-profile` re-runs when **either**:
+
+- the `human-only` corpus has grown ≥20% since the last `:VoiceProfile.corpusSize`, OR
+- 30 days have passed since `:VoiceProfile.generatedAt`.
+
+A re-run within the 30-day window with <20% growth is a no-op — the tool returns the existing profile unchanged and emits `[voice-distil] skip reason=below-threshold`.
+
+The triggering surface is the skill, not a scheduled job. Distillation runs on demand: at the end of a backfill batch, when the email composer notices stale-profile narration, or when the operator says "rebuild my voice profile".
+
+## Per-operator scope
+
+One `:VoiceProfile` per `:AdminUser`. Multi-author accounts (an agency with several operators) get one profile per person. Identity is the `(accountId, adminUserId)` pair, enforced by the schema constraint.
+
+## Observability
+
+| Tag | When |
+|-----|------|
+| `[voice-tag] mode=<mode> nodeId=<id> count=<n>` | Every tag write. |
+| `[voice-distil] adminUser=<id> corpusSize=<n> generatedAt=<iso> feedbackEntries=<n>` | Each distillation. |
+| `[voice-distil] skip reason=<below-threshold\|recent>` | When the cadence guard fires. |
+| `[voice-retrieve] task=<topic\|format> styleCardBytes=<n> exemplarCount=<k> tokenBudget=<n>` | Each retrieval. |
+| `[voice-record-feedback] adminUser=<id> intent="<haiku-summary>" diffBytes=<n>` | Each feedback write. |
+
+**Confirms working:** `[voice-retrieve] exemplarCount≥1` precedes every drafting-skill prompt assembly when the calling skill has not opted out. `[voice-distil]` appears at least once per 30-day window per active `:AdminUser`.
+
+**Indicates failure:** `[voice-retrieve] exemplarCount=0` with non-empty corpus → similarity index broken; `[voice-distil] error …` → corpus walk or LLM call failed; absence of `[voice-record-feedback]` after an operator-edit-then-send flow → feedback loop is dead.
+
+**Diagnostic path:**
+
+```
+journalctl -u maxy-code | grep -E '\[voice-(tag|distil|retrieve|record-feedback)\]'
+```
+
+Filter by `adminUser=<id>` for per-operator drill-down.
+
+## Out of scope
+
+- Voice blending across multiple authors (no "Joel + Neo combined voice").
+- Style transfer from public-figure corpora — voice-mirror only learns from the operator's own writing.
+- Audio voice cloning / speech synthesis — different domain.
+- Auto-tagging legacy content via heuristics — backfill is operator-driven only; the agent never guesses authorship.
+- Register-segmented profiles (one profile per author, not one per formality level).
+- Admin-UI editing of the `styleCard` — operator edits via `database-operator` for now. Surfacing this in a dedicated UI is a follow-up task.
+
+## Dependencies
+
+- **Memory plugin's graph-write gate** is the single write boundary; new tools route through it, never bypass.
+- **Haiku LLM call path** (already used by `memory-classify`) is reused for diff-intent summarisation.
+- **`:AdminUser` must exist** for the operator before distillation runs. Personal-mode operators with `Person {role: "admin-personal"}` need to be promoted to an `:AdminUser` first — out of scope here.

package/payload/server/{chunk-3TRIXQSJ.js → chunk-L2YK2VK3.js}

@@ -3818,7 +3818,6 @@ import {
   readdirSync as readdirSync2,
   existsSync as existsSync5,
   statSync as statSync2,
-  cpSync,
   rmSync
 } from "fs";
 import { createHash as createHash2 } from "crypto";
@@ -3903,59 +3902,48 @@ function walkPremiumBundlesOnDisk() {
 function reapDuplicateFlatPremiumSubs(bundles, stagingRoot, pluginsDir) {
   const TAG = "[premium-auto-deliver]";
   for (const { bundle, subs } of bundles) {
+    const isBundle = existsSync5(join3(stagingRoot, bundle, "BUNDLE.md"));
     for (const sub of subs) {
-      const premiumManifest = resolve4(stagingRoot, bundle, "plugins", sub, "PLUGIN.md");
+      const premiumManifest = isBundle ? resolve4(stagingRoot, bundle, "plugins", sub, "PLUGIN.md") : resolve4(stagingRoot, bundle, "PLUGIN.md");
       const flatDir = resolve4(pluginsDir, sub);
       const flatManifest = resolve4(flatDir, "PLUGIN.md");
       if (!existsSync5(premiumManifest) || !existsSync5(flatManifest)) continue;
       const premiumSha = createHash2("sha256").update(readFileSync5(premiumManifest)).digest("hex");
       const flatSha = createHash2("sha256").update(readFileSync5(flatManifest)).digest("hex");
-      if (premiumSha === flatSha) {
+      if (isBundle) {
+        if (premiumSha === flatSha) {
+          try {
+            rmSync(flatDir, { recursive: true });
+            console.log(`${TAG} reaped sub=${sub} reason=duplicate-of-premium-tree`);
+          } catch (err) {
+            console.log(`${TAG} reap-failed sub=${sub} err=${err instanceof Error ? err.message : String(err)}`);
+          }
+        } else {
+          console.log(`${TAG} flat-copy-divergent sub=${sub} action=skip-keep`);
+        }
+      } else {
         try {
           rmSync(flatDir, { recursive: true });
-          console.log(`${TAG} reaped sub=${sub} reason=duplicate-of-premium-tree`);
+          console.log(`${TAG} reaped standalone=${sub} matches-source=${flatSha === premiumSha}`);
         } catch (err) {
-          console.log(`${TAG} reap-failed sub=${sub} err=${err instanceof Error ? err.message : String(err)}`);
+          console.log(`${TAG} reap-failed standalone=${sub} err=${err instanceof Error ? err.message : String(err)}`);
         }
-      } else {
-        console.log(`${TAG} flat-copy-divergent sub=${sub} action=skip-keep`);
       }
     }
   }
 }
 function autoDeliverPremiumPlugins() {
-  const TAG = "[premium-auto-deliver]";
   const bundles = walkPremiumBundles();
   if (bundles.length === 0) return;
   const stagingRoot = resolve4(PLATFORM_ROOT2, "../premium-plugins");
   const pluginsDir = resolve4(PLATFORM_ROOT2, "plugins");
   reapDuplicateFlatPremiumSubs(bundles, stagingRoot, pluginsDir);
-  for (const { bundle, subs: _subs } of bundles) {
-    const stagingDir = resolve4(stagingRoot, bundle);
-    const bundlePath = join3(stagingDir, "BUNDLE.md");
-    const isBundle = existsSync5(bundlePath);
-    if (isBundle) {
-      continue;
-    }
-    const target = resolve4(pluginsDir, bundle);
-    if (existsSync5(resolve4(target, "PLUGIN.md"))) {
-      console.log(`${TAG} ${bundle}: already present, skipping`);
-    } else {
-      try {
-        cpSync(stagingDir, target, { recursive: true });
-        console.log(`${TAG} ${bundle} (standalone): delivered`);
-      } catch (err) {
-        console.log(`${TAG} ${bundle}: copy failed: ${err instanceof Error ? err.message : String(err)}`);
-      }
-    }
-  }
 }
 function reconcileEnabledPlugins(accountDir, config, accountId) {
   const TAG = "[premium-auto-deliver]";
   if (!accountDir || !config) return;
   const bundles = walkPremiumBundles();
   const stagingRoot = resolve4(PLATFORM_ROOT2, "../premium-plugins");
-  const pluginsDir = resolve4(PLATFORM_ROOT2, "plugins");
   const bundleNames = [];
   const allSubs = [];
   for (const { bundle, subs } of bundles) {
@@ -3963,7 +3951,7 @@ function reconcileEnabledPlugins(accountDir, config, accountId) {
     const bundlePath = join3(stagingRoot, bundle, "BUNDLE.md");
     const isBundle = existsSync5(bundlePath);
     for (const sub of subs) {
-      const subManifest = isBundle ? resolve4(stagingRoot, bundle, "plugins", sub, "PLUGIN.md") : resolve4(pluginsDir, sub, "PLUGIN.md");
+      const subManifest = isBundle ? resolve4(stagingRoot, bundle, "plugins", sub, "PLUGIN.md") : resolve4(stagingRoot, bundle, "PLUGIN.md");
       if (!existsSync5(subManifest)) continue;
       allSubs.push(sub);
     }

package/payload/server/maxy-edge.js

@@ -14,7 +14,7 @@ import {
   sanitizeClientCorrId,
   vncLog,
   websockifyLog
-} from "./chunk-3TRIXQSJ.js";
+} from "./chunk-L2YK2VK3.js";
 import "./chunk-PFF6I7KP.js";
 
 // server/edge.ts

package/payload/server/server.js

@@ -84,7 +84,7 @@ import {
   vncLog,
   walkPremiumBundles,
   writeAdminUserAndPerson
-} from "./chunk-3TRIXQSJ.js";
+} from "./chunk-L2YK2VK3.js";
 import {
   __commonJS,
   __toESM

package/payload/platform/plugins/venture-studio/.claude-plugin/plugin.json

@@ -1,8 +0,0 @@
-{
-  "name": "venture-studio",
-  "description": "Founding-a-business agent. Drives an operator from raw idea to fundraise-ready deliverables: validated wedge, branded identity, prototyped product, structured data room, business plan, prospectus + term sheet, deck. Every artefact slots into a tracked Project + Task graph so nothing gets forgotten.",
-  "version": "0.1.0",
-  "author": {
-    "name": "Rubytech LLC"
-  }
-}

package/payload/platform/plugins/venture-studio/PLUGIN.md

@@ -1,119 +0,0 @@
----
-name: venture-studio
-description: "Founding-a-business agent. Drives an operator from raw idea to fundraise-ready deliverables: validated wedge, branded identity, prototyped product, structured data room, business plan, prospectus + term sheet, deck. Every artefact slots into a tracked Project + Task graph so nothing gets forgotten."
-requires:
-  - projects
-  - work
-  - cloudflare
-  - deep-research
-metadata: {"platform":{"always":false,"embed":["admin"],"pluginKey":"venture-studio","optional":true,"recommended":true}}
----
-
-# Venture Studio
-
-You are the founding-a-business agent. The operator has a business they want to start; your job is to take them from idea to a fundraise-ready pack — without losing track of any artefact along the way.
-
-## Operating principle: data-room first
-
-Every business this agent founds produces the same set of artefacts: a discovery design doc, a brand pack, a validated wedge with a landing page and PRD, a structured data room, a business plan, a prospectus, a term sheet, a deck. The operator does not have to remember any of this. The agent's job is to ensure every artefact has a tracked Task before any artefact is produced.
-
-Outcome (binding):
-
-- **Every artefact has a tracked Task** in a `Project` named for this business, before that artefact's skill is invoked.
-- **Section order is preserved.** Artefacts are produced in the data-room's section order (`01-narrative` → `02-corporate-legal` → ... → `10-supporting`), with the `html/<artefact>/` rendered outputs landing as the section's content matures.
-- **Nothing is forgotten.** The Project's Task list IS the operator's view of what is done, what is in flight, what is outstanding.
-
-Constraint (binding): **No downstream venture-studio skill (`brand-pack`, `zero-to-prototype`, `investor-data-room` Stages 3+, etc.) is invoked before the data-room scaffold + Project + per-artefact Tasks exist on disk and in the graph.** If the operator asks you to skip straight to a deliverable ("just write me a business plan"), restate the scaffold-first principle and offer to scaffold the data room first, then jump straight to that artefact's task. The principle is the outcome contract; the scaffold proves it.
-
-### Deterministic pre-flight gate
-
-Before invoking any downstream skill, both checks below must pass. Both are deterministic — exit-code on `ls`, structured output on `project-list`. Neither check depends on LLM judgement.
-
-1. **Directory check:** `[ -d "${PROJECT_ROOT}/.docs/data-room/01-narrative" ]` returns exit 0.
-2. **Graph check:** the `project-list` tool returns a Project whose `name` matches the business's working name.
-
-If either check fails, run the scaffolding script (see below) before the skill fires. If the script fails, surface the literal stderr error to the operator — do not narrate around it (memory: [[feedback_no_stdout_parsing_for_control_flow]]).
-
-### Scaffolding script
-
-`bin/scaffold.sh` is the deterministic enforcement layer. It creates the Project + nine artefact Tasks (via the work plugin's `project-create-cli` bridge) and materialises the ten-section directory tree plus the `prototype/` top-level for hosted surfaces. Graph write first, directories second; idempotent re-run if any partial state lands.
-
-```bash
-ACCOUNT_ID="${ACCOUNT_ID}" \
-  premium-plugins/venture-studio/bin/scaffold.sh \
-  "${PROJECT_ROOT}" \
-  "${BUSINESS_NAME}"
-```
-
-The script is the binding check, not the prose principle above. The prose explains why; the script is what makes it true.
-
-## First-conversation routing
-
-When the operator first invokes this agent, confirm the intent ("Are we founding a new business, or working on an existing one?") and run the scaffolding script — it does steps 1–3 below in a single atomic invocation:
-
-```bash
-ACCOUNT_ID="${ACCOUNT_ID}" \
-  premium-plugins/venture-studio/bin/scaffold.sh \
-  "${PROJECT_ROOT}" \
-  "${BUSINESS_NAME}"
-```
-
-The script's three effects:
-
-1. **Scaffolds the data room.** Materialises the ten-section directory tree under `<project-root>/.docs/data-room/`. Every artefact has a slot to land in before any artefact is produced.
-2. **Creates the `Project` node.** Tier `full` (data-room work is multi-phase). Project name is the business's working name; description references the data-room root path.
-3. **Enumerates the nine artefact Tasks** in section order — one transaction, atomic with the Project. The work-item list the script pre-seeds:
-   - **Stage 1 — Office-hours design doc** → produces `01-narrative/office-hours-design.md` (skill: `office-hours`)
-   - **Stage 2 — Wedge validation + landing page + PRD** → produces `01-narrative/{PMF, LANDING, PRD}.md` (skill: `zero-to-prototype`)
-   - **Brand pack** → produces brand guidelines + summary + color palette + typography system + tone-of-voice (voice/messaging/copy) + logo guidelines into `06-product-ip/brand/` (skill: `brand-pack`)
-   - **Prototype host** → public URL for the landing page and/or wedge prototype via cloudflared ingress + systemd-managed dev server (skill: `prototype-host`)
-   - **Stage 3 — Business plan** → produces `01-narrative/business-plan.md` (skill: `investor-data-room` Stage 3)
-   - **Stage 3b — Term sheet** → produces `html/prospectus/term_sheet.html` (skill: `investor-data-room` Stage 3b)
-   - **Stage 4 — Deck blueprint** → produces `01-narrative/deck-blueprint.md` (skill: `investor-data-room` Stage 4)
-   - **Stage 4b — Prospectus** → produces `html/prospectus/index.html` (skill: `investor-data-room` Stage 4b)
-   - **Stage 5 — Rendered PDFs** → produces `html/{business-plan,prospectus,deck}/*.pdf` (skill: `investor-data-room` Stage 5)
-
-After these three steps land, the operator sees the project + task list before any skill produces output. Subsequent turns execute the tasks one at a time, calling the relevant venture-studio skill to produce that section's artefact.
-
-## Skill routing
-
-The following intent phrases route to specific skills. These calls are gated by the scaffold-first principle: refuse to fire any of them until the data-room scaffold + Project + Tasks exist.
-
-| Operator says | Skill |
-|---|---|
-| "I want to think this through" / "office hours" / "is this worth building" | `office-hours` |
-| "let's brand this" / "tokens for the brand" / "logo and palette" | `brand-pack` |
-| "validate this idea" / "let's find PMF" / "draft the landing page" / "write the PRD" | `zero-to-prototype` |
-| "host the landing" / "host the prototype" / "deploy this" / "give me a public URL" | `prototype-host` |
-| "build me a data room" / "scaffold the data room" | `investor-data-room` (Stage 2) |
-| "draft the business plan" | `investor-data-room` (Stage 3) |
-| "draft the term sheet" | `investor-data-room` (Stage 3b) |
-| "draft the deck blueprint" / "build the deck" | `investor-data-room` (Stage 4) |
-| "draft the prospectus" / "investment prospectus" | `investor-data-room` (Stage 4b) |
-| "render the PDFs" / "print-ready deliverables" | `investor-data-room` (Stage 5) |
-
-When the operator's intent matches a row but the scaffold does not yet exist, run the first-conversation routing sequence above before the skill fires.
-
-## Project & Task hygiene during execution
-
-- Before starting any artefact's task, mark its Task `in_progress` via the `work` plugin (or the `projects` plugin's helpers). When the artefact is on disk and verified, mark it `completed`.
-- If a section reveals a new artefact the operator wants (e.g. a competitor-claims-rebuttal in `08-market/`), `work-create` a new Task under the same Project, then proceed.
-- The Project's health signal (green/amber/red) is computed from Task state. Use `project-get` at the start of each turn to surface what's outstanding.
-
-## Research routing
-
-Every structured-research task — market sizing (TAM/SAM/SOM + CAGR), compliance research (DMCC / ICO ADM / EU AI Act), competitor scans, comparable rounds and exit comparables, named-acquirer enumeration — routes through the `research-assistant` specialist with the five `deep-research` skills (`deep-research`, `book-mirror`, `strategic-reading`, `academic-verify`, `data-research`). Dispatch the specialist; do not call `WebSearch` or `WebFetch` directly from a venture-studio skill. The specialist returns structured findings with citations the data-room artefacts can quote verbatim.
-
-## Tone
-
-Founder-facing. Direct, evidence-based, no flattery. You are the chief of staff for a one-person founding team — your job is to keep every artefact tracked and every deadline visible, while the operator focuses on the parts only they can do (customer conversations, founder signal, vision).
-
-## References
-
-The five skills shipped under this plugin carry their own SKILL.md detail:
-
-- `skills/office-hours/SKILL.md` — YC office-hours forcing questions in startup + builder modes; outputs the design-doc substrate every later artefact derives from.
-- `skills/brand-pack/SKILL.md` — brand identity (palette, typography, tone, logo) tokenised for the data-room artefacts to consume.
-- `skills/zero-to-prototype/SKILL.md` — 31 frameworks for customer discovery, validation, positioning, PMF measurement, landing page, PRD.
-- `skills/prototype-host/SKILL.md` — scaffolds the landing page or wedge prototype, allocates a port, edits the brand's cloudflared ingress, runs the dev server under a systemd-user unit, and verifies the public URL returns HTTP 200.
-- `skills/investor-data-room/SKILL.md` — full seed-raise pack: data room scaffold, business plan, term sheet, deck blueprint, prospectus, A4 print pipeline.

package/payload/platform/plugins/venture-studio/bin/scaffold.sh

@@ -1,116 +0,0 @@
-#!/usr/bin/env bash
-# Venture-studio data-room scaffold — deterministic enforcement of the
-# scaffold-first principle (Task 286 + feedback_doctrine_paragraph_is_not_a_gate).
-#
-# Creates exactly one Project (with nine pre-seeded artefact Tasks) in
-# the graph, then materialises the ten-section data-room directory tree
-# on disk. The venture-studio agent's downstream skills are gated on
-# both signals existing — see venture-studio/PLUGIN.md.
-#
-# Order of operations: graph write first, directories second. The CLI's
-# duplicate-name guard makes the script safely re-runnable after any
-# partial failure: a second run finds the existing Project, returns its
-# id, and retries the mkdir step.
-#
-# Usage:
-#   ACCOUNT_ID=<uuid> scaffold.sh <project-root> <business-name>
-#
-# Exit codes:
-#   0   scaffold complete (or already existed)
-#   2   bad arguments / missing ACCOUNT_ID
-#   1   graph write failed, directory mkdir failed, or CLI binary missing
-
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# Deployed layout per packages/create-maxy-code/scripts/bundle.js:
-#   <install>/premium-plugins/venture-studio/bin/scaffold.sh
-#   <install>/platform/plugins/work/mcp/dist/cli/project-create-cli.js
-CLI_BIN="${SCRIPT_DIR}/../../../platform/plugins/work/mcp/dist/cli/project-create-cli.js"
-
-if [[ $# -ne 2 ]]; then
-  echo "scaffold.sh: usage: ACCOUNT_ID=<uuid> $0 <project-root> <business-name>" >&2
-  exit 2
-fi
-
-PROJECT_ROOT="$1"
-BUSINESS_NAME="$2"
-
-if [[ -z "${ACCOUNT_ID:-}" ]]; then
-  echo "scaffold.sh: ACCOUNT_ID env var required" >&2
-  exit 2
-fi
-
-if [[ ! -d "$PROJECT_ROOT" ]]; then
-  echo "scaffold.sh: project root does not exist: $PROJECT_ROOT" >&2
-  exit 2
-fi
-
-if [[ ! -f "$CLI_BIN" ]]; then
-  echo "scaffold.sh: project-create CLI not built or missing at: $CLI_BIN" >&2
-  exit 1
-fi
-
-DATA_ROOM="${PROJECT_ROOT}/.docs/data-room"
-
-# Nine pre-seeded artefact tasks — order and names match
-# premium-plugins/venture-studio/PLUGIN.md § First-conversation routing.
-# Section order is preserved so the agent can walk them sequentially.
-# Prototype-host is slotted between Stage 2 (wedge + landing copy) and
-# Stage 3 (business plan): brand-pack and wedge are hard prerequisites
-# (the skill consumes 06-product-ip/brand/ tokens and 01-narrative/LANDING.md);
-# hosting before business plan keeps the founder's wedge-validation loop
-# (live URL) ahead of investor-pack work.
-PAYLOAD=$(cat <<JSON
-{
-  "accountId": "${ACCOUNT_ID}",
-  "name": "${BUSINESS_NAME}",
-  "description": "Venture-studio data room for ${BUSINESS_NAME}. Root: ${DATA_ROOM}",
-  "tier": "full",
-  "workItems": [
-    {"name": "Stage 1 — Office-hours design doc", "description": "Produces 01-narrative/office-hours-design.md via the office-hours skill."},
-    {"name": "Stage 2 — Wedge validation + landing page + PRD", "description": "Produces 01-narrative/{PMF,LANDING,PRD}.md via the zero-to-prototype skill."},
-    {"name": "Brand pack", "description": "Produces brand guidelines + summary + color palette + typography system + tone-of-voice (voice/messaging/copy) + logo guidelines into 06-product-ip/brand/ via the brand-pack skill."},
-    {"name": "Prototype host", "description": "Public URL for the landing page and/or wedge prototype via cloudflared ingress + systemd-managed dev server (skill: prototype-host)."},
-    {"name": "Stage 3 — Business plan", "description": "Produces 01-narrative/business-plan.md via investor-data-room Stage 3."},
-    {"name": "Stage 3b — Term sheet", "description": "Produces html/prospectus/term_sheet.html via investor-data-room Stage 3b."},
-    {"name": "Stage 4 — Deck blueprint", "description": "Produces 01-narrative/deck-blueprint.md via investor-data-room Stage 4."},
-    {"name": "Stage 4b — Prospectus", "description": "Produces html/prospectus/index.html via investor-data-room Stage 4b."},
-    {"name": "Stage 5 — Rendered PDFs", "description": "Produces html/{business-plan,prospectus,deck}/*.pdf via investor-data-room Stage 5."}
-  ]
-}
-JSON
-)
-
-# Graph write first. CLI returns {projectId, existing:bool} on stdout;
-# on any failure it exits non-zero with a literal stderr message that
-# propagates here verbatim — no prose-parsing for control flow
-# (memory: feedback_no_stdout_parsing_for_control_flow).
-RESULT=$(node "$CLI_BIN" "$PAYLOAD")
-echo "scaffold.sh: project-create CLI returned: $RESULT"
-
-# Directories second. The agent's pre-flight gate keys on the existence
-# of 01-narrative/ (it AND-checks with project-list); creating it last
-# means partial state (graph-only) is naturally invisible to the gate
-# until mkdir succeeds.
-for section in \
-  01-narrative \
-  02-corporate-legal \
-  03-cap-table \
-  04-financials \
-  05-team \
-  06-product-ip \
-  07-customers \
-  08-market \
-  09-traction-metrics \
-  10-supporting; do
-  mkdir -p "${DATA_ROOM}/${section}"
-done
-
-# Hosted-prototype source roots live alongside the numbered sections under
-# data-room/. The prototype-host skill populates this with one subdir per
-# surface (landing/, prototype/, etc.); creating the parent here so the
-# directory exists before the first invocation.
-mkdir -p "${DATA_ROOM}/prototype"
-
-echo "scaffold.sh: data-room scaffolded at ${DATA_ROOM}"