analyzthis_design 1.6.0 → 1.8.0

package/README.md

@@ -1,6 +1,6 @@
 # Analyzthis_Design
 
-A set of AI design personas and a task-first evaluation framework that plugs into Cursor, Claude Code, and Codex CLI as slash commands.
+A set of AI design personas and a task-first evaluation framework that plugs into Cursor, Claude Code, and Codex CLI as slash commands — plus an agentic MoE router with shared session state so you can call the same graph from any IDE or from the CLI.
 
 Install once. Run structured UX critiques, multi-phase ideation, and task-grounded screen reviews — directly inside your AI chat.
 
@@ -38,150 +38,162 @@ npx analyzthis_design --target all
 
 | Command | What it does |
 |---|---|
-| `/ux-story-gate` | **Recommended first step.** Discovers PRDs and user stories from your knowledge bank and repo, builds a task map, routes to the right personas, and synthesises findings by task with P0/P1/P2 priorities. |
-| `/design-critic` | 4-persona critique → `SHIP / REVISE / BLOCK` verdict with a Composite Score out of 20. |
+| `/persona-orchestrator` | **Recommended agentic entry point.** Loads MoE router + session state, runs ux-story-gate intake, executes the right persona chain, enforces DS / hierarchy / verify gates, synthesises a SHIP/REVISE/BLOCK verdict. |
+| `/ux-story-gate` | Task-first gate: discovers PRDs, DS/Figma discovery, MoE routing, browser verify, assess-only mode. |
+| `/design-critic` | 4-persona critique → `SHIP / REVISE / BLOCK` verdict with a Composite Score out of 20 + Information Hierarchy Gate. |
 | `/ux-ideator` | 6-phase ideation → two competing IA concepts, deliberation, delight pass, feasibility check. |
 
 ### 7 Individual Personas
 
-Invoke directly for targeted, already-grounded questions. For full screen evaluation, prefer `/ux-story-gate`.
+Invoke directly for targeted, already-grounded questions. For full screen evaluation, prefer `/persona-orchestrator` or `/ux-story-gate`.
 
 | Command | Persona | What they evaluate |
 |---|---|---|
-| `/arjun` | UX Agent | UX Honeycomb (7 dimensions, A–F): Useful, Usable, Findable, Credible, Accessible, Desirable, Valuable |
-| `/meera` | Business Agent | Retention, ARR, GTM lever, adoption risk by customer segment |
-| `/priya` | Feasibility Agent | Engineering effort (T-shirt sizing, 2-axis model), state machine traps, implementation risks |
-| `/zara` | Delight Agent | Picks exactly ONE peak delight moment — or says "speed is the craft" for working surfaces |
-| `/noor` | IA Architect | Minimalist, progressive-disclosure wireframe — Concept A, ≤3 nav levels |
-| `/anuj` | Power-User Advocate | Dense, expert-optimized wireframe — Concept B, bulk actions, keyboard shortcuts |
+| `/arjun` | UX + Visual Design | UX Honeycomb + Visual Design Audit (hierarchy, color, type, spacing, components, style fit, micro-interactions) |
+| `/meera` | Business Agent | Retention, ARR, GTM lever, adoption risk; hierarchy vs north-star check |
+| `/priya` | Feasibility Agent | Engineering effort (T-shirt sizing, 2-axis model), state machine traps |
+| `/zara` | Delight Agent | Exactly ONE peak delight moment — never contrast/token recovery (routes to DS Gate + Arjun) |
+| `/noor` | IA Architect | Minimalist Concept A + declared ranked information hierarchy |
+| `/anuj` | Power-User Advocate | Dense Concept B — bulk actions, keyboard shortcuts, hierarchy kept prominent |
 | `/raj` | Arbitrator | Resolves persona stalemates using 5 ranked product principles. Never speaks first. |
 
 ### Supporting skills
 
 | Command | Purpose |
 |---|---|
-| `/design-personas` | Session context template — fill in once before a session to ground all 7 personas in project-specific data |
+| `/design-personas` | Session context template — fill in once before a session |
 | `/knowledge-bank` | Auto-populated from your connected vault. All personas read this first. |
+| `/design-reference` | CSV reference data (colors, typography, UX guidelines, stacks, …) |
 
 ---
 
-## UX Story Gate — How it works
+## Agentic system (v1.8)
+
+```
+User ask / Figma URL
+        ↓
+  /persona-orchestrator
+        ↓
+  ux-story-gate Phases 0–1.5 (PRD + DS/Figma + MoE router)
+        ↓
+  MoE subset OR design-critic / ideation chain
+        ↓
+  Hard gates: DS tokens → Information Hierarchy → Browser verify
+        ↓
+  Session state persisted  →  SHIP / REVISE / BLOCK
+```
+
+**Shared session state** lives at `~/.analyzthis_design/sessions/{project-id}/session-state.json` so Ask→Agent turns do not re-derive the task map, DS checklist, or routing decision.
+
+```bash
+npx analyzthis_design session init
+npx analyzthis_design session show
+npx analyzthis_design session reset
+```
 
-`/ux-story-gate` is the task-first entry point for any screen evaluation. It runs in 5 phases:
+**Portable agent graph** (same manifests for Cursor / Claude / Codex / CLI):
 
-**Phase 0 — PRD Discovery (automatic)**
-Before asking you anything, it scans:
-1. Your connected knowledge bank for user stories, PRDs, acceptance criteria
-2. The current repo for `PRD*.md`, `docs/**/*.md`, `requirements/*.md`, and any file containing "user story / acceptance criteria / done when"
+```
+agents/
+  manifests/     # one JSON per persona + orchestrator
+  router.json    # MoE problem-type → expert list
+  chain.json     # default + ideation sequential graphs
+  session-schema.json
+```
 
-It builds a draft task map from what it finds and asks you to confirm — you correct, not fill in from scratch.
+**Standalone runtime (v2):**
 
-**Phase 1 — Task Map Gate**
-If no PRD context is found anywhere, it asks for the task map manually:
-- Which persona? (e.g. Retailer Admin, Media Sales)
-- What task? (verb + object)
-- How often? (daily / weekly / one-time)
-- Done when?
-- Fails when?
+```bash
+# Print routing only (no API calls)
+npx analyzthis_design run --task "Fix contrast on landing page" --dry-run
 
-**Phase 2 — Field Veto Pass**
-Every field, button, and section on the screen gets a verdict:
-- ✅ Keep — maps to a task
-- ❌ Cut — no task owner
-- ⚠️ Clarify — ambiguous
+# Call Anthropic / OpenAI per persona step
+export ANTHROPIC_API_KEY=sk-...
+npx analyzthis_design run --task "Review this screen" --figma https://figma.com/... --provider anthropic
+```
 
-**Phase 3 — Scale & States**
-Forces declaration of scale (rows/entities), and checks for Empty / Error / Loading / Edge states before personas run.
+Provider defaults live in `~/.analyzthis_design/config.json`:
 
-**Phase 4 — Persona Routing**
-Routes to the right personas based on task characteristics — not screen type.
+```json
+{
+  "orchestrator": { "provider": "anthropic", "model": "claude-sonnet-4-20250514" },
+  "research": { "provider": "https://example.com/search?q={query}" }
+}
+```
 
-**Phase 5 — Synthesis**
-A Task × Finding table with P0 / P1 / P2 priorities and a build-ready verdict.
+**Web research:**
+
+```bash
+npx analyzthis_design research --url https://example.com/design-tokens
+npx analyzthis_design research --query "EY design system tokens"
+```
+
+Writes to `~/.analyzthis_design/sessions/{id}/web-context.md` and merges into the knowledge bank on `sync`.
 
 ---
 
-## Knowledge Bank — Connect your vault
+## UX Story Gate — How it works
+
+`/ux-story-gate` is the task-first gate for any screen evaluation:
 
-The knowledge bank lets you connect an Obsidian vault or any markdown folder so that personas read your actual project context — brand guidelines, design decisions, PRDs, research — before forming any opinion.
+| Phase | What it does |
+|---|---|
+| 0 | PRD discovery from knowledge bank + repo |
+| 0.5 | DS / Figma discovery + DS Token Checklist (exit criteria) |
+| 1 | Task map intake gate |
+| 1.5 | MoE problem-type router → writes `routing_decision` to session state |
+| 2 | Field veto pass |
+| 3 | Scale & states declaration |
+| 4 | Per-task persona routing |
+| 4.5 | Browser verify gate (navigate → snapshot → primary flow → mobile+desktop screenshot) |
+| 5 | Task × Finding synthesis |
+| 5.5 | Assess-only mode — no code changes until you say build / implement / apply |
+
+---
+
+## Knowledge Bank — Connect your vault
 
 ```bash
-# Connect a vault (all notes)
 npx analyzthis_design connect --vault ~/Documents/MyVault
-
-# Connect with tag filter (only notes tagged #design, #brand, #prd)
 npx analyzthis_design connect --vault ~/vault --tags design,brand,prd,product
-
-# Connect with folder filter
 npx analyzthis_design connect --vault ~/vault --include Design,Brand,PRDs,Research
-
-# Sync to Cursor
 npx analyzthis_design sync
-
-# Sync to all tools
 npx analyzthis_design sync --target all
-
-# Check what's connected
 npx analyzthis_design status
-
-# Remove a source
 npx analyzthis_design disconnect --vault ~/Documents/MyVault
 ```
 
-Once synced, the knowledge bank is auto-read at the start of every persona session. Your project-specific context takes full precedence over built-in persona defaults.
+PRDs and user stories are surfaced at the top of the knowledge bank. Brand / design-system notes feed Phase 0.5. Web research merges under **Web Research Context**.
 
-**PRDs and user stories** in your vault are automatically detected and surfaced at the top of the knowledge bank — `ux-story-gate` reads them in Phase 0 to build the task map without you having to type it out.
-
-Config is stored at `~/.analyzthis_design/config.json` — global across all projects.
+Config: `~/.analyzthis_design/config.json`.
 
 ---
 
 ## CLI Reference
 
 ```bash
-# ── Install ────────────────────────────────────────────────────────────────
-npx analyzthis_design                          # install for Cursor
-npx analyzthis_design --target claude          # install for Claude Code
-npx analyzthis_design --target codex           # install for Codex CLI
-npx analyzthis_design --target all             # install for all tools
-npx analyzthis_design --force                  # overwrite existing skills
-
-# ── Remove ─────────────────────────────────────────────────────────────────
-npx analyzthis_design remove                   # remove from Cursor
-npx analyzthis_design remove --target all      # remove from all tools
-
-# ── List ───────────────────────────────────────────────────────────────────
-npx analyzthis_design list                     # show Cursor installs
-npx analyzthis_design list --target all        # show all tool installs
-
-# ── Knowledge bank ─────────────────────────────────────────────────────────
-npx analyzthis_design connect --vault <path>
-npx analyzthis_design connect --vault <path> --tags design,prd,brand
-npx analyzthis_design connect --vault <path> --include Design,PRDs,Research
-npx analyzthis_design sync
-npx analyzthis_design sync --target all
+# Install / remove / list
+npx analyzthis_design
+npx analyzthis_design --target all
+npx analyzthis_design --force
+npx analyzthis_design remove --target all
+npx analyzthis_design list --target all
+
+# Knowledge bank
+npx analyzthis_design connect --vault <path> [--tags ...] [--include ...]
+npx analyzthis_design sync [--target all]
 npx analyzthis_design disconnect --vault <path>
 npx analyzthis_design status
-```
 
----
+# Session (agentic)
+npx analyzthis_design session init|show|reset [--project id] [--all]
 
-## How it fits together
+# Research
+npx analyzthis_design research --url <url>
+npx analyzthis_design research --query <text>
 
-```
-Your vault / repo PRDs
-        ↓
-  knowledge bank  ←── npx analyzthis_design sync
-        ↓
-  /ux-story-gate
-        ↓
-  Phase 0: read knowledge bank + scan repo for PRDs
-        ↓
-  Build task map (or confirm draft from PRDs)
-        ↓
-  Route to: /noor  /anuj  /arjun  (+/meera  /zara  as needed)
-        ↓
-  Task × Finding table  →  P0 / P1 / P2 verdict
+# Standalone orchestrator
+npx analyzthis_design run --task "..." [--figma URL] [--provider anthropic|openai] [--dry-run] [--output path]
 ```
 
 ---
@@ -189,28 +201,22 @@ Your vault / repo PRDs
 ## Repository structure
 
 ```
-bin/
-  cli.js              CLI entry point
+agents/                 Portable MoE graph (manifests, router, chain, session schema)
+bin/cli.js              CLI entry point
 lib/
-  install.js          Skill installation logic (copies to ~/.cursor/skills/ etc.)
-  knowledge.js        Vault reading, sync, PRD categorisation
-scripts/
-  obfuscate.js        Build step — obfuscates lib/ and bin/ into dist/ before publish
+  install.js            Skill installation
+  knowledge.js          Vault sync + web-context merge
+  session.js            Shared session-state.json
+  research.js           URL / query → web-context.md
+  orchestrator/run.js   Standalone LLM runtime (v2)
+scripts/obfuscate.js    Build step → dist/
 skills/
-  arjun/              UX Agent — Honeycomb scoring
-  meera/              Business Agent — retention, ARR, GTM
-  priya/              Feasibility Agent — effort sizing
-  zara/               Delight Agent — peak-end moment
-  noor/               IA Architect — minimalist Concept A
-  anuj/               Power-User Advocate — dense Concept B
-  raj/                Arbitrator — stalemate resolution
-  design-critic/      Orchestrator — 4-persona critique
-  ux-ideator/         Orchestrator — 6-phase ideation
-  ux-story-gate/      Orchestrator — task-first gate + PRD discovery
-  design-personas/    Session context template
-  knowledge-bank/     Auto-populated from connected vault
-  design-reference/   12 CSV files — colors, typography, UX guidelines,
-                      component patterns, charts, icons, 16 framework stacks
+  persona-orchestrator/ Agentic entry point
+  ux-story-gate/        Task-first gate + DS/MoE/verify/assess phases
+  design-critic/        4-persona critique + hierarchy gate
+  ux-ideator/           6-phase ideation
+  arjun/ meera/ priya/ zara/ noor/ anuj/ raj/
+  design-personas/ knowledge-bank/ design-reference/
 ```
 
 ---
@@ -220,6 +226,7 @@ skills/
 - Node.js 16+
 - [Cursor](https://cursor.com) with Agent Mode (for `/skill` commands)
 - Claude Code or Codex CLI if using those targets
+- For `run` (non–dry-run): `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`
 
 ---
 

package/agents/chain.json

@@ -0,0 +1,27 @@
+{
+  "description": "Default sequential graph for a full multi-persona critique (design-critic). The MoE router in router.json can select a subset of this chain for narrower asks instead of running it end to end.",
+  "default_chain": [
+    { "step": 1, "persona": "arjun",  "handoff_from": null,     "handoff_to": "meera" },
+    { "step": 2, "persona": "meera",  "handoff_from": "arjun",  "handoff_to": "priya" },
+    { "step": 3, "persona": "priya",  "handoff_from": "meera",  "handoff_to": "zara" },
+    { "step": 4, "persona": "zara",   "handoff_from": "priya",  "handoff_to": null }
+  ],
+  "ideation_chain": [
+    { "step": 1, "persona": "meera", "handoff_to": ["noor", "anuj"] },
+    { "step": 2, "persona": "noor",  "handoff_from": "meera", "handoff_to": "arjun" },
+    { "step": 2, "persona": "anuj",  "handoff_from": "meera", "handoff_to": "arjun" },
+    { "step": 3, "persona": "arjun", "handoff_from": ["noor", "anuj"], "handoff_to": "zara" },
+    { "step": 4, "persona": "zara",  "handoff_from": "arjun", "handoff_to": "priya" },
+    { "step": 5, "persona": "priya", "handoff_from": "zara",  "handoff_to": "raj" },
+    { "step": 6, "persona": "raj",   "handoff_from": "priya", "handoff_to": null }
+  ],
+  "gates": [
+    { "name": "ds_gate", "runs": "before persona chain (ux-story-gate Phase 0.5)" },
+    { "name": "information_hierarchy_gate", "runs": "after persona chain, before re-evaluation/BLOCK escalation" },
+    { "name": "verify_gate", "runs": "after persona chain, before synthesis (ux-story-gate Phase 4.5)" }
+  ],
+  "escalation": {
+    "condition": "stalemate or BLOCK verdict from any persona",
+    "route_to": "raj"
+  }
+}

package/agents/manifests/anuj.json

@@ -0,0 +1,23 @@
+{
+  "id": "anuj",
+  "role": "power_user",
+  "system_skill": "skills/anuj/SKILL.md",
+  "inputs": ["task_map", "session_context", "information_hierarchy"],
+  "outputs": ["concept_b_wireframe"],
+  "allowed_tools": ["design-reference", "stacks"],
+  "allowed_jobs": [
+    "audit density, bulk actions, keyboard shortcuts for daily-use surfaces",
+    "produce Concept B wireframe",
+    "keep rank #1 of the declared information hierarchy prominent even at full density"
+  ],
+  "forbidden_jobs": [
+    "propose density audits for surfaces with task Frequency != daily/weekly",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["daily_use", "data_density", "bulk_actions", "keyboard_shortcuts"],
+  "never_route_for": ["one_time_use_surfaces", "learning_products_without_daily_frequency"],
+  "chain_position": 1,
+  "handoff_from": [],
+  "handoff_to": ["arjun"],
+  "requires_session_state": true
+}

package/agents/manifests/arjun.json

@@ -0,0 +1,25 @@
+{
+  "id": "arjun",
+  "role": "ux_visual",
+  "system_skill": "skills/arjun/SKILL.md",
+  "inputs": ["task_map", "session_context", "ds_checklist", "figma_context", "information_hierarchy"],
+  "outputs": ["ux_critique", "visual_audit", "combined_score"],
+  "allowed_tools": ["design-reference", "browser_verify", "figma_mcp"],
+  "allowed_jobs": [
+    "UX Honeycomb critique",
+    "Visual Design Audit (hierarchy, color, typography, spacing, components, style fit, micro-interactions)",
+    "diagnose visual issues against declared information hierarchy and DS tokens"
+  ],
+  "forbidden_jobs": [
+    "brand-system recovery as a primary job (diagnostic only — cite tokens, do not ship !important overrides)",
+    "delight pass (hand off to Zara)",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["ux", "accessibility", "responsive", "interaction_bug", "visual_quality"],
+  "never_route_for": ["business_priority", "build_effort", "delight_moment"],
+  "chain_position": 2,
+  "handoff_from": ["noor"],
+  "handoff_to": ["meera"],
+  "requires_session_state": true,
+  "hard_gates": ["ds_gate", "information_hierarchy_gate"]
+}

package/agents/manifests/design-critic.json

@@ -0,0 +1,21 @@
+{
+  "id": "design-critic",
+  "role": "orchestrator",
+  "system_skill": "skills/design-critic/SKILL.md",
+  "inputs": ["task_map", "session_context", "figma_context", "ds_checklist"],
+  "outputs": ["composite_score", "task_finding_table", "verdict"],
+  "allowed_tools": ["design-reference", "browser_verify", "figma_mcp"],
+  "allowed_jobs": [
+    "run the full persona chain (Arjun -> Meera -> Priya -> Zara) for a full screen review",
+    "enforce the Information Hierarchy Gate",
+    "escalate to Raj on stalemate/BLOCK"
+  ],
+  "forbidden_jobs": [
+    "run without a completed ux-story-gate pass",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["full_screen_review", "multi_persona_critique"],
+  "chain": ["arjun", "meera", "priya", "zara"],
+  "escalates_to": "raj",
+  "requires_session_state": true
+}

package/agents/manifests/meera.json

@@ -0,0 +1,23 @@
+{
+  "id": "meera",
+  "role": "business",
+  "system_skill": "skills/meera/SKILL.md",
+  "inputs": ["task_map", "session_context", "arjun_output", "information_hierarchy"],
+  "outputs": ["business_impact", "hierarchy_metric_check"],
+  "allowed_tools": ["design-reference"],
+  "allowed_jobs": [
+    "north-star metric impact assessment",
+    "segment / GTM / retention analysis",
+    "check that rank #1 on screen matches the actual business-critical driver"
+  ],
+  "forbidden_jobs": [
+    "visual or UX critique (route to Arjun)",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["business_priority", "pricing", "access_control", "monetization", "retention"],
+  "never_route_for": ["visual_quality", "ia_structure"],
+  "chain_position": 3,
+  "handoff_from": ["arjun"],
+  "handoff_to": ["priya"],
+  "requires_session_state": true
+}

package/agents/manifests/noor.json

@@ -0,0 +1,24 @@
+{
+  "id": "noor",
+  "role": "information_architect",
+  "system_skill": "skills/noor/SKILL.md",
+  "inputs": ["task_map", "session_context", "figma_context"],
+  "outputs": ["concept_a_wireframe", "information_hierarchy"],
+  "allowed_tools": ["design-reference"],
+  "allowed_jobs": [
+    "declare ranked information hierarchy",
+    "propose minimalist IA / progressive disclosure structure",
+    "produce Concept A wireframe"
+  ],
+  "forbidden_jobs": [
+    "brand token recovery",
+    "contrast / accessibility fixes (route to Arjun)",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["structure", "ia", "navigation", "nested_ui", "wizard", "form"],
+  "never_route_for": ["brand", "contrast", "design_system_compliance"],
+  "chain_position": 1,
+  "handoff_from": [],
+  "handoff_to": ["arjun", "anuj"],
+  "requires_session_state": true
+}

package/agents/manifests/persona-orchestrator.json

@@ -0,0 +1,17 @@
+{
+  "id": "persona-orchestrator",
+  "role": "entry_point",
+  "system_skill": "skills/persona-orchestrator/SKILL.md",
+  "inputs": ["user_ask", "figma_url"],
+  "outputs": ["session_state", "task_finding_table", "verdict"],
+  "allowed_tools": ["design-reference", "figma_mcp", "browser_verify", "knowledge-bank"],
+  "allowed_jobs": [
+    "single entry point for agentic runs: load router + session, run ux-story-gate, execute chain or MoE subset, run gates, synthesize verdict"
+  ],
+  "forbidden_jobs": [
+    "bypass ux-story-gate phases 0-1.5",
+    "implement code without explicit build approval (respect assess-only mode)"
+  ],
+  "reads": ["agents/router.json", "agents/chain.json", "agents/session-schema.json"],
+  "requires_session_state": true
+}

package/agents/manifests/priya.json

@@ -0,0 +1,23 @@
+{
+  "id": "priya",
+  "role": "feasibility",
+  "system_skill": "skills/priya/SKILL.md",
+  "inputs": ["task_map", "session_context", "meera_output", "tech_stack"],
+  "outputs": ["feasibility_analysis"],
+  "allowed_tools": ["design-reference", "stacks"],
+  "allowed_jobs": [
+    "T-shirt sizing (two-axis: UI x State)",
+    "risk and blocker identification",
+    "simpler-alternative sizing (modal vs accordion vs wizard, etc.)"
+  ],
+  "forbidden_jobs": [
+    "visual or business critique",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["build_effort", "implementation_risk", "modal_vs_wizard", "state_machine"],
+  "never_route_for": ["visual_quality", "delight_moment"],
+  "chain_position": 4,
+  "handoff_from": ["meera"],
+  "handoff_to": ["zara"],
+  "requires_session_state": true
+}

package/agents/manifests/raj.json

@@ -0,0 +1,22 @@
+{
+  "id": "raj",
+  "role": "arbitrator",
+  "system_skill": "skills/raj/SKILL.md",
+  "inputs": ["session_context", "persona_outputs"],
+  "outputs": ["arbitration_verdict"],
+  "allowed_tools": ["design-reference"],
+  "allowed_jobs": [
+    "resolve stalemates between personas using the 5 product principles",
+    "issue final SHIP / REVISE / BLOCK when personas disagree"
+  ],
+  "forbidden_jobs": [
+    "run when there is no stalemate or BLOCK condition",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["stalemate", "block", "conflicting_verdicts"],
+  "never_route_for": ["routine_single_persona_critique"],
+  "chain_position": 6,
+  "handoff_from": ["zara", "arjun", "meera", "priya", "noor", "anuj"],
+  "handoff_to": [],
+  "requires_session_state": true
+}

package/agents/manifests/ux-story-gate.json

@@ -0,0 +1,23 @@
+{
+  "id": "ux-story-gate",
+  "role": "orchestrator",
+  "system_skill": "skills/ux-story-gate/SKILL.md",
+  "inputs": ["user_ask", "prd_sources", "figma_context", "knowledge_bank"],
+  "outputs": ["task_map", "ds_checklist", "routing_decision", "session_state"],
+  "allowed_tools": ["design-reference", "figma_mcp", "browser_verify", "knowledge-bank"],
+  "allowed_jobs": [
+    "Phase 0: discover PRDs/user stories, build task map",
+    "Phase 0.5: DS/Figma discovery, DS token checklist",
+    "Phase 1: mental model of user personas",
+    "Phase 1.5: MoE routing decision",
+    "Phase 4.5: browser verify gate",
+    "Phase 5.5: assess-only mode gate"
+  ],
+  "forbidden_jobs": [
+    "skip phases 0-1.5 before handing off to persona chain"
+  ],
+  "routing_triggers": ["any_screen_or_flow_review"],
+  "hands_off_to": "persona-orchestrator",
+  "requires_session_state": true,
+  "mandatory_first_step": true
+}

package/agents/manifests/zara.json

@@ -0,0 +1,24 @@
+{
+  "id": "zara",
+  "role": "delight",
+  "system_skill": "skills/zara/SKILL.md",
+  "inputs": ["task_map", "session_context", "priya_output", "ds_checklist"],
+  "outputs": ["delight_pass"],
+  "allowed_tools": ["design-reference"],
+  "allowed_jobs": [
+    "identify exactly ONE structural or surface delight moment",
+    "add delight on top of an already DS-compliant, hierarchy-correct foundation"
+  ],
+  "forbidden_jobs": [
+    "contrast fixes, token drift correction, or any brand/design-system recovery — these are out of scope for Zara; refuse and route to the DS Gate + Arjun",
+    "run before the ds_gate has passed",
+    "implement code without explicit build approval"
+  ],
+  "routing_triggers": ["delight_moment", "onboarding", "empty_state", "first_impression"],
+  "never_route_for": ["contrast", "brand_tokens", "design_system_compliance", "accessibility_fix"],
+  "requires_ds_gate_pass": true,
+  "chain_position": 5,
+  "handoff_from": ["priya"],
+  "handoff_to": [],
+  "requires_session_state": true
+}