analyzthis_design 2.1.2 → 2.2.0

package/README.md

@@ -4,6 +4,12 @@ A set of AI design personas and a task-first evaluation framework that plugs int
 
 Install once. Run structured UX critiques, multi-phase ideation, and task-grounded screen reviews — directly inside your AI chat. **No external LLM API keys required** for CLI orchestrator runs: **`/devi`** voices each persona from your host IDE (Cursor, Claude, etc.).
 
+## v2.2 — project-scoped knowledge bank
+
+Knowledge sources are now scoped per project by default. `collect`, `connect`, `sync`, `disconnect`, and `status` operate on the project derived from your current working directory, and the built `knowledge-bank` skill is written into that project's local skills directory (`<project>/.claude/skills/knowledge-bank/SKILL.md`, `<project>/.cursor/skills/...`, etc.). Invoking a skill from one project never reads another project's vaults.
+
+Pass `--global` to opt into the legacy merged behavior (read `config.sources` and write into `~/.claude/skills/...`). Use `--global` only when you deliberately want cross-project blending.
+
 ## v2.0 — chunked execution by default
 
 `npx analyzthis_design run --task "..."` now uses a **frontier planner + cheap chunk models**:
@@ -15,7 +21,7 @@ Install once. Run structured UX critiques, multi-phase ideation, and task-ground
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.1.2 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.2.0 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
@@ -536,12 +542,14 @@ npx analyzthis_design feedback status
 
 **What does NOT get sent:** project paths, repo names, emails, API keys, full source trees.
 
-**Maintainer setup (Supabase):**
+**Maintainer setup (vendor-neutral HTTP endpoint):**
 
-1. Create a Supabase project
-2. Run `supabase/migrations/001_persona_feedback.sql` in the SQL editor
-3. Copy `supabase/feedback-config.example.json` into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`)
-4. View submissions in Supabase Table Editor → `persona_feedback`
+The `feedback submit` client is a plain HTTPS POST with an `apikey` header — it works with any REST endpoint that accepts anonymous inserts, not only Supabase. A reference schema (with row-level security for insert-only anon access) lives in [`supabase/migrations/001_persona_feedback.sql`](./supabase/migrations/001_persona_feedback.sql) in the repo. That folder is **not** shipped in the npm package, so installing `analyzthis_design` does not pull a Supabase-branded folder into `node_modules`.
+
+1. Stand up any HTTP endpoint that accepts anonymous JSON inserts (Supabase with RLS is one option; a small Cloudflare Worker or a self-hosted Postgres + thin API work too).
+2. If you use the reference schema, run `supabase/migrations/001_persona_feedback.sql` in your SQL editor.
+3. Copy the endpoint URL and anon key into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`).
+4. Read submissions from your endpoint's dashboard.
 
 Users can also file GitHub issues via **Persona feedback** template if they prefer not to use CLI submit.
 
@@ -869,6 +877,22 @@ skills/
 
 ---
 
+## Marketing site
+
+The public lab site lives in `website/` and is deployed on Vercel as **analyzthis-lab** (site only — not the npm package). Copy now names two doors: lab products for people who already use Cursor or Claude, and custom teams that arrive in a firm’s existing tools. The Vercel project root is `website/` with no build step — do not set Output Directory to `public`.
+
+- Live: [https://analyzthis-lab.vercel.app](https://analyzthis-lab.vercel.app)
+- Design team deep-dive: [https://analyzthis-lab.vercel.app/design](https://analyzthis-lab.vercel.app/design) (`website/design.html`)
+- Form test (does not write to Airtable): add `?form=mock` to the URL
+- Leads go to Airtable through `website/api/lead.js`. Each step is saved; unfinished fills are marked `partial`.
+- Booking uses Google Calendar: [https://calendar.app.google/KtKJ7hCAx1duA8m58](https://calendar.app.google/KtKJ7hCAx1duA8m58)
+- Form views are counted first-party (no cookies, no third-party pixel). They are only stored if you set the optional `AIRTABLE_EVENTS_TABLE` env var to a separate Airtable table; without it the count is discarded and the Leads table is never touched.
+- There is exactly one privacy disclosure, in the `.privacy-note` directly above the inquiry form. If you change what the site collects, update that sentence — do not add a second notice elsewhere on the page.
+- Header layout: the real `logo.svg` sits left, nav links centre, one orange CTA right. No webfont is loaded, so the wordmark must stay an SVG.
+- The hero is tuned so the primary CTA and trust ticks stay above the fold at 1440×800 — check that before changing hero padding or the `h1` clamp.
+
+---
+
 ## License
 
 MIT — [Rishikesh Joshi](https://github.com/rishikeshjoshi)

package/dist/README.md

@@ -4,6 +4,12 @@ A set of AI design personas and a task-first evaluation framework that plugs int
 
 Install once. Run structured UX critiques, multi-phase ideation, and task-grounded screen reviews — directly inside your AI chat. **No external LLM API keys required** for CLI orchestrator runs: **`/devi`** voices each persona from your host IDE (Cursor, Claude, etc.).
 
+## v2.2 — project-scoped knowledge bank
+
+Knowledge sources are now scoped per project by default. `collect`, `connect`, `sync`, `disconnect`, and `status` operate on the project derived from your current working directory, and the built `knowledge-bank` skill is written into that project's local skills directory (`<project>/.claude/skills/knowledge-bank/SKILL.md`, `<project>/.cursor/skills/...`, etc.). Invoking a skill from one project never reads another project's vaults.
+
+Pass `--global` to opt into the legacy merged behavior (read `config.sources` and write into `~/.claude/skills/...`). Use `--global` only when you deliberately want cross-project blending.
+
 ## v2.0 — chunked execution by default
 
 `npx analyzthis_design run --task "..."` now uses a **frontier planner + cheap chunk models**:
@@ -15,7 +21,7 @@ Install once. Run structured UX critiques, multi-phase ideation, and task-ground
 
 Use `npx analyzthis_design run-unchunked` for the legacy single-pass orchestrator.
 
-**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.1.2 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
+**npm:** [analyzthis_design](https://www.npmjs.com/package/analyzthis_design) · **Current version:** 2.2.0 · **Step-by-step guide:** [HOW-TO-USE.md](./HOW-TO-USE.md)
 
 ---
 
@@ -536,12 +542,14 @@ npx analyzthis_design feedback status
 
 **What does NOT get sent:** project paths, repo names, emails, API keys, full source trees.
 
-**Maintainer setup (Supabase):**
+**Maintainer setup (vendor-neutral HTTP endpoint):**
 
-1. Create a Supabase project
-2. Run `supabase/migrations/001_persona_feedback.sql` in the SQL editor
-3. Copy `supabase/feedback-config.example.json` into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`)
-4. View submissions in Supabase Table Editor → `persona_feedback`
+The `feedback submit` client is a plain HTTPS POST with an `apikey` header — it works with any REST endpoint that accepts anonymous inserts, not only Supabase. A reference schema (with row-level security for insert-only anon access) lives in [`supabase/migrations/001_persona_feedback.sql`](./supabase/migrations/001_persona_feedback.sql) in the repo. That folder is **not** shipped in the npm package, so installing `analyzthis_design` does not pull a Supabase-branded folder into `node_modules`.
+
+1. Stand up any HTTP endpoint that accepts anonymous JSON inserts (Supabase with RLS is one option; a small Cloudflare Worker or a self-hosted Postgres + thin API work too).
+2. If you use the reference schema, run `supabase/migrations/001_persona_feedback.sql` in your SQL editor.
+3. Copy the endpoint URL and anon key into `~/.analyzthis_design/config.json` under `"feedback"` (or set env vars `ANALYZTHIS_FEEDBACK_URL` + `ANALYZTHIS_FEEDBACK_ANON_KEY`).
+4. Read submissions from your endpoint's dashboard.
 
 Users can also file GitHub issues via **Persona feedback** template if they prefer not to use CLI submit.
 
@@ -869,6 +877,22 @@ skills/
 
 ---
 
+## Marketing site
+
+The public lab site lives in `website/` and is deployed on Vercel as **analyzthis-lab** (site only — not the npm package). Copy now names two doors: lab products for people who already use Cursor or Claude, and custom teams that arrive in a firm’s existing tools. The Vercel project root is `website/` with no build step — do not set Output Directory to `public`.
+
+- Live: [https://analyzthis-lab.vercel.app](https://analyzthis-lab.vercel.app)
+- Design team deep-dive: [https://analyzthis-lab.vercel.app/design](https://analyzthis-lab.vercel.app/design) (`website/design.html`)
+- Form test (does not write to Airtable): add `?form=mock` to the URL
+- Leads go to Airtable through `website/api/lead.js`. Each step is saved; unfinished fills are marked `partial`.
+- Booking uses Google Calendar: [https://calendar.app.google/KtKJ7hCAx1duA8m58](https://calendar.app.google/KtKJ7hCAx1duA8m58)
+- Form views are counted first-party (no cookies, no third-party pixel). They are only stored if you set the optional `AIRTABLE_EVENTS_TABLE` env var to a separate Airtable table; without it the count is discarded and the Leads table is never touched.
+- There is exactly one privacy disclosure, in the `.privacy-note` directly above the inquiry form. If you change what the site collects, update that sentence — do not add a second notice elsewhere on the page.
+- Header layout: the real `logo.svg` sits left, nav links centre, one orange CTA right. No webfont is loaded, so the wordmark must stay an SVG.
+- The hero is tuned so the primary CTA and trust ticks stay above the fold at 1440×800 — check that before changing hero padding or the `h1` clamp.
+
+---
+
 ## License
 
 MIT — [Rishikesh Joshi](https://github.com/rishikeshjoshi)

package/dist/bin/cli.js

@@ -33,14 +33,20 @@ Usage:
   welcome    Print getting-started banner for your AI tool (--target)
 
 ── Knowledge bank commands ──────────────────────────────────
-  connect    Register a vault or knowledge folder as a source
-  sync       Read all sources and build the knowledge-bank skill
-  disconnect Remove a source from the registry
-  status     Show connected sources and last sync time
+  connect    Register a vault or knowledge folder as a source (scoped to cwd project)
+  sync       Read this project's sources and build the knowledge-bank skill
+  disconnect Remove a source from this project's registry
+  status     Show this project's sources and last sync time
   collect    Kavi: scan codebase → Obsidian vault → enrich → sync knowledge bank
              (--vault path, --dry-run, --no-enrich, --no-web, --no-discover,
               --web-limit N, --target cursor|claude|codex|grok|windsurf|agents|all)
 
+  Scope flags (connect/sync/disconnect/status):
+  --project <id>   Explicit project id (overrides cwd-derived id)
+  --global         Use the legacy merged pool (config.sources → ~/.claude/skills/...)
+                   instead of per-project scoping. Only use when you want
+                   multiple projects' notes blended together.
+
 ── Design spec commands ─────────────────────────────────────
   spec show      Print design_spec from session state
   spec validate  Validate a DesignSpec JSON file (--file) or session
@@ -61,7 +67,7 @@ Usage:
   feedback list     List feedback entries for this project (--all for every project)
   feedback export   Export rejected + correction JSONL pairs for training
                     (--persona <id>, --all, --output <path>, --include-positive)
-  feedback submit   Opt-in: send anonymized corrections to community store (Supabase)
+  feedback submit   Opt-in: send anonymized corrections to a community store (HTTP endpoint)
                     (--yes skip prompt, --dry-run preview, --all unsent across projects)
   feedback status   Show submit consent, endpoint config, unsent count
   feedback revoke   Revoke opt-in consent for community submit
@@ -175,9 +181,11 @@ Usage:
   npx analyzthis_design connect --vault ~/Documents/MyVault
   npx analyzthis_design connect --vault ~/docs --tags design,brand,product
   npx analyzthis_design connect --vault ~/vault --include Design,Research
-  npx analyzthis_design sync                               # sync to Cursor
-  npx analyzthis_design sync --target all                  # sync to all tools
-  npx analyzthis_design status                             # show sources
+  npx analyzthis_design sync                               # sync to Cursor (project-scoped)
+  npx analyzthis_design sync --target all                  # sync to all tools (project-scoped)
+  npx analyzthis_design sync --global                      # legacy: blend all projects into ~/.claude/skills/
+  npx analyzthis_design status                             # show this project's sources
+  npx analyzthis_design status --global                    # show the legacy merged pool
   npx analyzthis_design disconnect --vault ~/Documents/MyVault
 
   npx analyzthis_design session init                       # start a new session for this repo
@@ -255,6 +263,7 @@ const vaultVal   = getFlag('vault');
 const tagsVal    = getFlag('tags');
 const includeVal = getFlag('include');
 const projectVal = getFlag('project');
+const globalFlag = flags.includes('--global');
 const allFlag    = flags.includes('--all');
 const urlVal     = getFlag('url');
 const queryVal   = getFlag('query');
@@ -352,8 +361,10 @@ switch (cmd) {
     try {
       const tags    = tagsVal    ? tagsVal.split(',').map(t => t.trim())    : [];
       const include = includeVal ? includeVal.split(',').map(t => t.trim()) : [];
-      const abs = connect({ vaultPath: vaultVal, tags, include });
+      const abs = connect({ vaultPath: vaultVal, tags, include, project: projectVal, global: globalFlag });
+      const scopeLabel = globalFlag ? 'global (merged across projects)' : (projectVal || `project derived from ${path.resolve(process.cwd())}`);
       console.log(`\n✅ Connected: ${abs}`);
+      console.log(`   Scope: ${scopeLabel}`);
       if (tags.length)    console.log(`   Tags filter:    ${tags.join(', ')}`);
       if (include.length) console.log(`   Folder filter:  ${include.join(', ')}`);
       console.log(`\n   Run "npx analyzthis_design sync" to build the knowledge bank.\n`);
@@ -369,7 +380,7 @@ switch (cmd) {
       console.error('\n  ✗  --vault is required.  Example: npx analyzthis_design disconnect --vault ~/Documents/MyVault\n');
       process.exit(1);
     }
-    disconnect(vaultVal);
+    disconnect(vaultVal, { project: projectVal, global: globalFlag });
     console.log(`\n🗑  Disconnected: ${path.resolve(vaultVal)}\n`);
     break;
   }
@@ -381,9 +392,10 @@ switch (cmd) {
       console.error(`\n  ✗  Unknown target "${targetVal}". Choose: ${ALL_TARGET_IDS.join(', ')}, all\n`);
       process.exit(1);
     }
-    console.log('\n⏳ Syncing knowledge bank...\n');
+    const scopeLabel = globalFlag ? 'global (merged across projects)' : (projectVal || `project derived from ${path.resolve(process.cwd())}`);
+    console.log(`\n⏳ Syncing knowledge bank (${scopeLabel})...\n`);
     try {
-      const result = sync({ targets });
+      const result = sync({ targets, project: projectVal, global: globalFlag });
       if (result.message) {
         console.log(`  ⚠  ${result.message}\n`);
       } else {
@@ -399,18 +411,22 @@ switch (cmd) {
   }
 
   case 'status': {
-    const cfg = status();
-    if (!cfg.sources || cfg.sources.length === 0) {
-      console.log('\n  No knowledge sources connected.\n  Run: npx analyzthis_design connect --vault /path/to/vault\n');
+    const view = status({ project: projectVal, global: globalFlag });
+    if (!view.sources || view.sources.length === 0) {
+      const scopeHint = view.scope === 'global'
+        ? 'Run: npx analyzthis_design connect --vault /path/to/vault --global'
+        : 'Run: npx analyzthis_design collect (from inside the project) or npx analyzthis_design connect --vault /path/to/vault';
+      console.log(`\n  No knowledge sources connected for this ${view.scope} scope.\n  ${scopeHint}\n`);
     } else {
-      console.log(`\n📚 Knowledge bank sources (${cfg.sources.length}):\n`);
-      for (const s of cfg.sources) {
+      const scopeLabel = view.scope === 'global' ? 'global (merged across projects)' : `project: ${view.projectId}`;
+      console.log(`\n📚 Knowledge bank sources (${view.sources.length}) — ${scopeLabel}:\n`);
+      for (const s of view.sources) {
         console.log(`  • ${s.path}`);
-        if (s.tags.length)    console.log(`    Tags:    ${s.tags.join(', ')}`);
-        if (s.include.length) console.log(`    Folders: ${s.include.join(', ')}`);
+        if (s.tags && s.tags.length)    console.log(`    Tags:    ${s.tags.join(', ')}`);
+        if (s.include && s.include.length) console.log(`    Folders: ${s.include.join(', ')}`);
         console.log(`    Added:   ${s.addedAt}`);
       }
-      if (cfg.lastSync) console.log(`\n  Last sync: ${cfg.lastSync}`);
+      if (view.lastSync) console.log(`\n  Last sync: ${view.lastSync}`);
       console.log('');
     }
     break;

package/dist/lib/collect.js

@@ -767,22 +767,26 @@ async function collect(opts = {}) {
     }
   }
 
-  // Auto-connect discovered sources + Kavi vault, then sync knowledge bank
-  console.log(`\n⏳ Wiring knowledge bank...`);
+  // Auto-connect discovered sources + Kavi vault, then sync knowledge bank.
+  // Scoped to the current project so this project's vault never bleeds into
+  // another project's knowledge bank (the v2.2 project-scoping fix).
+  console.log(`\n⏳ Wiring knowledge bank (project: ${projectId})...`);
   const connectResult = discoverSources
     ? connectDiscoveredSources({
       discoveries: sourceDiscoveries,
       kaviVaultPath: vaultPath,
       config,
       autoConnect: config.collect?.auto_connect_discovered !== false,
+      project: projectId,
+      cwd,
     })
     : { connected: [], skipped: [] };
   if (connectResult.connected.length > 0) {
     console.log(`   Auto-connected ${connectResult.connected.length} source(s):`);
     for (const p of connectResult.connected) console.log(`   • ${p}`);
   }
-  knowledge.connect({ vaultPath, tags: [], include: [] });
-  const syncResult = knowledge.sync({ targets });
+  knowledge.connect({ vaultPath, tags: [], include: [], project: projectId, cwd });
+  const syncResult = knowledge.sync({ targets, project: projectId, cwd });
   cache.invalidatePrefix('kb:');
 
   if (syncResult.message) {

package/dist/lib/knowledge.js

@@ -1,9 +1,10 @@
 #!/usr/bin/env node
 'use strict';
 
-const fs   = require('fs');
-const path = require('path');
-const os   = require('os');
+const fs     = require('fs');
+const path   = require('path');
+const os     = require('os');
+const crypto = require('crypto');
 
 const CONFIG_DIR        = path.join(os.homedir(), '.analyzthis_design');
 const CONFIG_FILE       = path.join(CONFIG_DIR, 'config.json');
@@ -32,9 +33,14 @@ const CATEGORIES = {
 // ─── Config helpers ──────────────────────────────────────────────────────────
 
 function loadConfig() {
-  if (!fs.existsSync(CONFIG_FILE)) return { sources: [] };
-  try { return JSON.parse(fs.readFileSync(CONFIG_FILE, 'utf8')); }
-  catch { return { sources: [] }; }
+  if (!fs.existsSync(CONFIG_FILE)) return { sources: [], projects: {} };
+  try {
+    const cfg = JSON.parse(fs.readFileSync(CONFIG_FILE, 'utf8'));
+    if (!cfg.sources) cfg.sources = [];
+    if (!cfg.projects) cfg.projects = {};
+    return cfg;
+  }
+  catch { return { sources: [], projects: {} }; }
 }
 
 function saveConfig(config) {
@@ -42,6 +48,79 @@ function saveConfig(config) {
   fs.writeFileSync(CONFIG_FILE, JSON.stringify(config, null, 2));
 }
 
+// ─── Project scoping ─────────────────────────────────────────────────────────
+// Knowledge sources are scoped per project by default. Each project's sources
+// live under config.projects[projectId].sources and the master knowledge-bank
+// is written into that project's local skills directory (e.g.
+// <projectRoot>/.claude/skills/knowledge-bank/SKILL.md), so invoking a skill
+// from one project never reads another project's vaults.
+//
+// Pass { global: true } (or --global on the CLI) to opt into the legacy merged
+// behavior: read config.sources and write into ~/.claude/skills/... This is the
+// only path that ever blends multiple projects' notes together.
+
+function resolveProjectScope({ project, global, cwd } = {}) {
+  // Explicit --global wins: read the legacy merged pool, write to global skills dirs.
+  if (global) return { scope: 'global', projectId: null, projectRoot: null };
+
+  // --project <id> (or a caller-provided project id): use that id, rooted at cwd.
+  let projectId = project;
+  let projectRoot = path.resolve(cwd || process.cwd());
+
+  // Default: auto-derive a project id from cwd, the same way session.js does.
+  if (!projectId) {
+    const abs = path.resolve(cwd || process.cwd());
+    const slug = path.basename(abs).toLowerCase().replace(/[^a-z0-9]+/g, '-').replace(/^-+|-+$/g, '') || 'project';
+    const hash = crypto.createHash('sha1').update(abs).digest('hex').slice(0, 8);
+    projectId = `${slug}-${hash}`;
+  }
+
+  return { scope: 'project', projectId, projectRoot };
+}
+
+// Return the sources array for a resolved scope, creating the project entry
+// on first use. For global scope, returns the legacy top-level config.sources.
+function scopedSources(config, scopeInfo, { create = false } = {}) {
+  if (scopeInfo.scope === 'global') return config.sources;
+  if (!config.projects[scopeInfo.projectId] && create) {
+    config.projects[scopeInfo.projectId] = { sources: [], addedAt: new Date().toISOString() };
+  }
+  const proj = config.projects[scopeInfo.projectId];
+  return proj ? proj.sources : null;
+}
+
+// Per-tool skill roots, expressed relative to a project root, mirroring the
+// global TARGETS layout in platforms.js. Used when writing project-local
+// knowledge-bank files so each project's skills load only inside that project.
+const PROJECT_REL_TARGETS = [
+  { id: 'cursor',   rel: ['.cursor', 'skills'],                       layout: 'dir'  },
+  { id: 'claude',   rel: ['.claude', 'skills'],                        layout: 'dir'  },
+  { id: 'claude-cmds', rel: ['.claude', 'commands'],                  layout: 'flat' },
+  { id: 'codex',    rel: ['.codex', 'skills'],                        layout: 'dir'  },
+  { id: 'grok',     rel: ['.grok', 'skills'],                         layout: 'dir'  },
+  { id: 'windsurf', rel: ['.codeium', 'windsurf', 'skills'],          layout: 'dir'  },
+  { id: 'agents',   rel: ['.agents', 'skills'],                       layout: 'dir'  },
+];
+
+function projectTargets(projectRoot, requestedTargets) {
+  // requestedTargets is the resolved list from resolveTargets (e.g. ['cursor'],
+  // ['claude'], or ALL_TARGET_IDS). claude-cmds is always paired with claude.
+  const want = new Set(requestedTargets);
+  const out = [];
+  for (const t of PROJECT_REL_TARGETS) {
+    if (t.id === 'claude-cmds') {
+      if (want.has('claude')) out.push(t);
+    } else if (want.has(t.id)) {
+      out.push(t);
+    }
+  }
+  return out.map((t) => ({
+    id: t.id,
+    root: path.join(projectRoot, ...t.rel),
+    layout: t.layout,
+  }));
+}
+
 // ─── Vault reading ───────────────────────────────────────────────────────────
 
 // Recursively collect all .md files under a directory
@@ -103,29 +182,54 @@ function categorize(title, tags, body) {
 
 /**
  * Register a vault or folder as a knowledge source.
+ *
+ * By default the source is scoped to the project derived from cwd, so it only
+ * feeds critiques run from that project. Pass { global: true } to register it
+ * in the legacy merged pool (config.sources) instead.
+ *
  * Options:
  *   include  — array of sub-folder prefixes to include, e.g. ['Design', 'Brand']
  *   tags     — array of tags to filter by, e.g. ['ux', 'design', 'brand']
+ *   project  — explicit project id (overrides cwd-derived id)
+ *   global   — when true, register in the legacy merged pool instead
+ *   cwd      — working directory used to derive the project id (default: process.cwd())
  */
-function connect({ vaultPath, include = [], tags = [] }) {
+function connect({ vaultPath, include = [], tags = [], project, global = false, cwd } = {}) {
   const abs = path.resolve(vaultPath);
   if (!fs.existsSync(abs)) throw new Error(`Path does not exist: ${abs}`);
 
   const config = loadConfig();
-  // Replace any existing entry with the same path
-  config.sources = config.sources.filter(s => s.path !== abs);
-  config.sources.push({ path: abs, include, tags, addedAt: new Date().toISOString() });
+  const scopeInfo = resolveProjectScope({ project, global, cwd });
+  const sources = scopedSources(config, scopeInfo, { create: true });
+  // Replace any existing entry with the same path within this scope
+  const filtered = sources.filter(s => s.path !== abs);
+  filtered.push({ path: abs, include, tags, addedAt: new Date().toISOString() });
+  if (scopeInfo.scope === 'global') {
+    config.sources = filtered;
+  } else {
+    config.projects[scopeInfo.projectId].sources = filtered;
+  }
   saveConfig(config);
   return abs;
 }
 
 /**
  * Remove a vault/folder from the knowledge sources list.
+ * Accepts the same { project, global, cwd } options as connect() to target
+ * the right scope.
  */
-function disconnect(vaultPath) {
+function disconnect(vaultPath, opts = {}) {
   const abs = path.resolve(vaultPath);
   const config = loadConfig();
-  config.sources = config.sources.filter(s => s.path !== abs);
+  const scopeInfo = resolveProjectScope(opts);
+  const sources = scopedSources(config, scopeInfo);
+  if (!sources) return; // nothing in this scope yet
+  const filtered = sources.filter(s => s.path !== abs);
+  if (scopeInfo.scope === 'global') {
+    config.sources = filtered;
+  } else if (config.projects[scopeInfo.projectId]) {
+    config.projects[scopeInfo.projectId].sources = filtered;
+  }
   saveConfig(config);
 }
 
@@ -133,19 +237,38 @@ function disconnect(vaultPath) {
  * Read all connected sources, filter notes, build knowledge-bank.md,
  * and copy it to all requested target AI tool directories.
  *
- * targets — array of tool names: 'cursor', 'claude', 'codex'
+ * By default the bank is scoped to the project derived from cwd: it reads
+ * only that project's sources and writes into that project's local skills
+ * directory (<projectRoot>/.claude/skills/knowledge-bank/SKILL.md, etc.), so
+ * invoking a skill from one project never pulls in another project's vaults.
+ *
+ * Pass { global: true } (or --global) to opt into the legacy merged behavior:
+ * read config.sources and write into ~/.claude/skills/... so multiple
+ * projects' notes blend together. Use this only when you deliberately want
+ * cross-project blending.
+ *
+ * targets — array of tool names: 'cursor', 'claude', 'codex', 'grok',
+ *           'windsurf', 'agents', or ['all']
+ * project — explicit project id (overrides cwd-derived id)
+ * global   — when true, use the legacy merged pool
+ * cwd      — working directory used to derive the project id
  */
-function sync({ targets = ['cursor'] } = {}) {
+function sync({ targets = ['cursor'], project, global = false, cwd } = {}) {
   const config = loadConfig();
-
-  if (!config.sources || config.sources.length === 0) {
-    return { synced: 0, message: 'No sources connected. Run: npx analyzthis_design connect --vault /path/to/vault' };
+  const scopeInfo = resolveProjectScope({ project, global, cwd });
+  const sources = scopedSources(config, scopeInfo) || [];
+
+  if (!sources || sources.length === 0) {
+    const hint = scopeInfo.scope === 'global'
+      ? 'No sources connected. Run: npx analyzthis_design connect --vault /path/to/vault --global'
+      : `No sources connected for project "${scopeInfo.projectId}". Run: npx analyzthis_design collect (from inside the project) or npx analyzthis_design connect --vault /path/to/vault`;
+    return { synced: 0, message: hint };
   }
 
   const sections = { prd: [], brand: [], product: [], design: [], research: [], tech: [], web: [], other: [] };
   let totalFiles = 0;
 
-  for (const source of config.sources) {
+  for (const source of sources) {
     const files = readMarkdownFiles(source.path);
 
     for (const filePath of files) {
@@ -184,7 +307,7 @@ function sync({ targets = ['cursor'] } = {}) {
   } catch { /* no session / research available — fine */ }
 
   // Build the knowledge-bank markdown
-  const sourceList = config.sources.map(s => s.path).join(', ');
+  const sourceList = sources.map(s => s.path).join(', ');
   const date       = new Date().toISOString().split('T')[0];
 
   // PRD/stories listed first — ux-story-gate reads this section in Phase 0
@@ -199,6 +322,10 @@ function sync({ targets = ['cursor'] } = {}) {
     { key: 'other',    heading: '## Additional Context' },
   ];
 
+  const scopeLabel = scopeInfo.scope === 'global'
+    ? 'global (merged across projects)'
+    : `project: ${scopeInfo.projectId}`;
+
   let md = `---
 name: knowledge-bank
 description: Personal knowledge bank — takes precedence over all built-in persona defaults.
@@ -208,6 +335,7 @@ disable-model-invocation: true
 # Knowledge Bank
 
 > Last synced: ${date}
+> Scope: ${scopeLabel}
 > Sources: ${sourceList}
 > Files loaded: ${totalFiles}
 
@@ -232,53 +360,63 @@ disable-model-invocation: true
     md += `_No matching files found. Check your --tags or --include filters, or remove filters to include all notes._\n`;
   }
 
-  // Write to the package's own skills/knowledge-bank/SKILL.md
+  // Write to the package's own skills/knowledge-bank/SKILL.md (source of truth)
   fs.mkdirSync(path.dirname(KNOWLEDGE_SKILL), { recursive: true });
   fs.writeFileSync(KNOWLEDGE_SKILL, md);
 
   // Build per-persona knowledge slices (priority + fallback)
   try {
     const session = require('./session');
-    const projectId = session.getProjectId();
+    const projectId = scopeInfo.scope === 'project' ? scopeInfo.projectId : session.getProjectId();
     writePersonaSlices(sections, sectionDefs, projectId);
   } catch {
     // sessions unavailable — skip slices
   }
 
-  // Copy knowledge-bank into every requested platform (dir and/or flat layout)
+  // Copy knowledge-bank into every requested platform.
+  // Project-scoped → write into <projectRoot>/.{tool}/skills/... (project-local,
+  //   loaded only when the skill is invoked from inside that project).
+  // Global-scoped → write into ~/.{tool}/skills/... (legacy merged behavior).
   const { TARGETS, resolveTargets } = require('./platforms');
   const copiedTo = [];
   const resolved = targets.includes('all')
     ? resolveTargets('all')
     : targets.filter((t) => TARGETS[t]);
 
-  for (const targetId of resolved) {
-    const t = TARGETS[targetId];
-    const destinations = [{ root: t.root, layout: t.layout }];
-    if (t.also) destinations.push({ root: t.also.root, layout: t.also.layout });
-
-    for (const dest of destinations) {
-      fs.mkdirSync(dest.root, { recursive: true });
-      if (dest.layout === 'dir') {
-        const skillDir = path.join(dest.root, 'knowledge-bank');
-        fs.mkdirSync(skillDir, { recursive: true });
-        fs.copyFileSync(KNOWLEDGE_SKILL, path.join(skillDir, 'SKILL.md'));
-      } else {
-        fs.copyFileSync(KNOWLEDGE_SKILL, path.join(dest.root, 'knowledge-bank.md'));
-      }
-      copiedTo.push(`${targetId} → ${dest.root}`);
+  const destinations = scopeInfo.scope === 'project'
+    ? projectTargets(scopeInfo.projectRoot, resolved)
+    : resolved.map((id) => {
+        const t = TARGETS[id];
+        const list = [{ root: t.root, layout: t.layout, id }];
+        if (t.also) list.push({ root: t.also.root, layout: t.also.layout, id: `${id}-cmds` });
+        return list;
+      }).flat();
+
+  for (const dest of destinations) {
+    fs.mkdirSync(dest.root, { recursive: true });
+    if (dest.layout === 'dir') {
+      const skillDir = path.join(dest.root, 'knowledge-bank');
+      fs.mkdirSync(skillDir, { recursive: true });
+      fs.copyFileSync(KNOWLEDGE_SKILL, path.join(skillDir, 'SKILL.md'));
+    } else {
+      fs.copyFileSync(KNOWLEDGE_SKILL, path.join(dest.root, 'knowledge-bank.md'));
     }
+    copiedTo.push(`${dest.id} → ${dest.root}`);
   }
 
-  // Persist lastSync timestamp
-  config.lastSync = new Date().toISOString();
+  // Persist lastSync timestamp on the scoped config entry
+  if (scopeInfo.scope === 'global') {
+    config.lastSync = new Date().toISOString();
+  } else if (config.projects[scopeInfo.projectId]) {
+    config.projects[scopeInfo.projectId].lastSync = new Date().toISOString();
+  }
   saveConfig(config);
 
   // Knowledge bank content just changed for every project — drop any cached
   // knowledge-bank slices so the next run re-reads the fresh sync.
   try { require('./cache').invalidatePrefix('kb:'); } catch { /* cache module unavailable — fine */ }
 
-  return { synced: totalFiles, copiedTo };
+  return { synced: totalFiles, copiedTo, scope: scopeLabel };
 }
 
 function loadManifest(id) {
@@ -376,10 +514,24 @@ function getPersonaSliceForPrompt(state, personaId) {
 }
 
 /**
- * Return current config (sources list, lastSync).
+ * Return the config view for the resolved scope.
+ * Accepts the same { project, global, cwd } options as connect/sync.
+ * Returns { scope, projectId, sources, lastSync } so the CLI can print
+ * a scope-aware status without leaking other projects' sources.
  */
-function status() {
-  return loadConfig();
+function status(opts = {}) {
+  const config = loadConfig();
+  const scopeInfo = resolveProjectScope(opts);
+  const sources = scopedSources(config, scopeInfo) || [];
+  const lastSync = scopeInfo.scope === 'global'
+    ? config.lastSync
+    : (config.projects[scopeInfo.projectId] && config.projects[scopeInfo.projectId].lastSync);
+  return {
+    scope: scopeInfo.scope,
+    projectId: scopeInfo.projectId,
+    sources,
+    lastSync,
+  };
 }
 
-module.exports = { connect, disconnect, sync, status, buildPersonaSlice, writePersonaSlices, readPersonaSlice, getPersonaSliceForPrompt, KNOWLEDGE_SLICE_ROOT };
+module.exports = { connect, disconnect, sync, status, buildPersonaSlice, writePersonaSlices, readPersonaSlice, getPersonaSliceForPrompt, KNOWLEDGE_SLICE_ROOT, resolveProjectScope };

package/dist/lib/source-discovery.js

@@ -449,9 +449,12 @@ function writeSourceManifestNotes({ discoveries, vaultPath, dryRun }) {
 }
 
 /**
- * Auto-connect discovered sources (high/medium confidence) into config.sources.
+ * Auto-connect discovered sources (high/medium confidence) into the project's
+ * scoped sources (config.projects[projectId].sources). Pass { project, cwd }
+ * so the scope matches the collect() call site; falls back to cwd-derived
+ * scoping inside knowledge.connect when omitted.
  */
-function connectDiscoveredSources({ discoveries, kaviVaultPath, config, autoConnect = true }) {
+function connectDiscoveredSources({ discoveries, kaviVaultPath, config, autoConnect = true, project, cwd }) {
   const connected = [];
   const skipped = [];
   if (!autoConnect) return { connected, skipped };
@@ -469,7 +472,7 @@ function connectDiscoveredSources({ discoveries, kaviVaultPath, config, autoConn
       continue;
     }
     try {
-      knowledge.connect({ vaultPath: d.path, tags: [], include: [] });
+      knowledge.connect({ vaultPath: d.path, tags: [], include: [], project, cwd });
       connected.push(d.path);
     } catch (err) {
       skipped.push({ path: d.path, reason: err.message });

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "analyzthis_design",
-  "version": "2.1.2",
-  "description": "8 AI design personas — v2.0 chunked execution with frontier planner + free/cheap chunk models, adversarial deliberation loops, opt-in community feedback, Kavi knowledge collection, DesignSpec producer path, wireframe skills, UX critique, Agent Skills for Cursor, Claude, Codex, Grok, Windsurf. Plain source — no obfuscation, no auto-install.",
+  "version": "2.2.0",
+  "description": "8 AI design personas — v2.2 project-scoped knowledge bank (no cross-project vault entanglement), v2.0 chunked execution with frontier planner + free/cheap chunk models, adversarial deliberation loops, opt-in community feedback, Kavi knowledge collection, DesignSpec producer path, wireframe skills, UX critique, Agent Skills for Cursor, Claude, Codex, Grok, Windsurf. Plain source — no obfuscation, no auto-install.",
   "keywords": [
     "cursor",
     "cursor-skill",
@@ -33,7 +33,6 @@
     "dist/",
     "skills/",
     "agents/",
-    "supabase/",
     ".github/",
     "scripts/validate-csvs.js",
     "README.md",

package/dist/supabase/deliberation-config.example.json

@@ -1,15 +0,0 @@
-{
-  "deliberation": {
-    "satisfaction_threshold": 0.4,
-    "max_rounds": 3,
-    "parallel_pairs": [["noor", "anuj"], ["meera", "priya"]],
-    "objection_token_cap": 600,
-    "prior_output_chars_first": 800,
-    "prior_output_chars_rebuttal": 400,
-    "prior_output_chars_produce": 1200,
-    "context_pack_chars_objection": 1500,
-    "context_pack_chars_produce": 3000,
-    "escalate_to_raj_after_round": 2,
-    "default_mode": "adversarial"
-  }
-}

package/dist/supabase/feedback-config.example.json

@@ -1,7 +0,0 @@
-{
-  "feedback": {
-    "submit_enabled": true,
-    "submit_url": "https://YOUR_PROJECT.supabase.co/rest/v1/persona_feedback",
-    "anon_key": "YOUR_SUPABASE_ANON_KEY"
-  }
-}

package/dist/supabase/migrations/001_persona_feedback.sql

@@ -1,54 +0,0 @@
--- Persona feedback — anonymous community corrections for analyzthis_design
--- Run in Supabase SQL editor or via supabase db push
-
-create table if not exists public.persona_feedback (
-  id uuid primary key default gen_random_uuid(),
-  created_at timestamptz not null default now(),
-
-  install_id text not null,
-  package_version text,
-  feedback_id text,
-
-  persona text not null,
-  satisfied boolean not null default false,
-  rating smallint check (rating is null or (rating >= 1 and rating <= 5)),
-  tags text[] not null default '{}',
-
-  user_comment text,
-  assistant_rejected text,
-  assistant_preferred text,
-  task_summary text,
-  problem_type text,
-  mode text,
-  recorded_at timestamptz
-);
-
-create index if not exists persona_feedback_persona_idx on public.persona_feedback (persona);
-create index if not exists persona_feedback_created_at_idx on public.persona_feedback (created_at desc);
-create index if not exists persona_feedback_tags_idx on public.persona_feedback using gin (tags);
-
-alter table public.persona_feedback enable row level security;
-
--- Anonymous clients may INSERT only (no read/update/delete for anon)
-drop policy if exists "anon_insert_persona_feedback" on public.persona_feedback;
-create policy "anon_insert_persona_feedback"
-  on public.persona_feedback
-  for insert
-  to anon
-  with check (
-    char_length(coalesce(user_comment, '')) <= 2000
-    and char_length(coalesce(assistant_rejected, '')) <= 4000
-    and char_length(coalesce(assistant_preferred, '')) <= 4000
-    and persona ~ '^[a-z][a-z0-9_-]{0,31}$'
-  );
-
--- Service role (dashboard) can read everything — use Supabase dashboard or service key
-drop policy if exists "service_read_persona_feedback" on public.persona_feedback;
-create policy "service_read_persona_feedback"
-  on public.persona_feedback
-  for select
-  to service_role
-  using (true);
-
-comment on table public.persona_feedback is
-  'Anonymous opt-in persona correction data from analyzthis_design CLI (feedback submit).';

package/supabase/deliberation-config.example.json

@@ -1,15 +0,0 @@
-{
-  "deliberation": {
-    "satisfaction_threshold": 0.4,
-    "max_rounds": 3,
-    "parallel_pairs": [["noor", "anuj"], ["meera", "priya"]],
-    "objection_token_cap": 600,
-    "prior_output_chars_first": 800,
-    "prior_output_chars_rebuttal": 400,
-    "prior_output_chars_produce": 1200,
-    "context_pack_chars_objection": 1500,
-    "context_pack_chars_produce": 3000,
-    "escalate_to_raj_after_round": 2,
-    "default_mode": "adversarial"
-  }
-}

package/supabase/feedback-config.example.json

@@ -1,7 +0,0 @@
-{
-  "feedback": {
-    "submit_enabled": true,
-    "submit_url": "https://YOUR_PROJECT.supabase.co/rest/v1/persona_feedback",
-    "anon_key": "YOUR_SUPABASE_ANON_KEY"
-  }
-}

package/supabase/migrations/001_persona_feedback.sql

@@ -1,54 +0,0 @@
--- Persona feedback — anonymous community corrections for analyzthis_design
--- Run in Supabase SQL editor or via supabase db push
-
-create table if not exists public.persona_feedback (
-  id uuid primary key default gen_random_uuid(),
-  created_at timestamptz not null default now(),
-
-  install_id text not null,
-  package_version text,
-  feedback_id text,
-
-  persona text not null,
-  satisfied boolean not null default false,
-  rating smallint check (rating is null or (rating >= 1 and rating <= 5)),
-  tags text[] not null default '{}',
-
-  user_comment text,
-  assistant_rejected text,
-  assistant_preferred text,
-  task_summary text,
-  problem_type text,
-  mode text,
-  recorded_at timestamptz
-);
-
-create index if not exists persona_feedback_persona_idx on public.persona_feedback (persona);
-create index if not exists persona_feedback_created_at_idx on public.persona_feedback (created_at desc);
-create index if not exists persona_feedback_tags_idx on public.persona_feedback using gin (tags);
-
-alter table public.persona_feedback enable row level security;
-
--- Anonymous clients may INSERT only (no read/update/delete for anon)
-drop policy if exists "anon_insert_persona_feedback" on public.persona_feedback;
-create policy "anon_insert_persona_feedback"
-  on public.persona_feedback
-  for insert
-  to anon
-  with check (
-    char_length(coalesce(user_comment, '')) <= 2000
-    and char_length(coalesce(assistant_rejected, '')) <= 4000
-    and char_length(coalesce(assistant_preferred, '')) <= 4000
-    and persona ~ '^[a-z][a-z0-9_-]{0,31}$'
-  );
-
--- Service role (dashboard) can read everything — use Supabase dashboard or service key
-drop policy if exists "service_read_persona_feedback" on public.persona_feedback;
-create policy "service_read_persona_feedback"
-  on public.persona_feedback
-  for select
-  to service_role
-  using (true);
-
-comment on table public.persona_feedback is
-  'Anonymous opt-in persona correction data from analyzthis_design CLI (feedback submit).';