@arthai/agents 1.0.0

package/dist/plugins/prime/skills/consulting/SKILL.md

@@ -0,0 +1,282 @@
+---
+name: consulting
+description: "Run a full AI consulting engagement. Usage: /consulting <client-name> [--phase discovery|assess|propose|design|deliver|track] [-- <brief>]"
+user-invocable: true
+arguments: "<client-name> [--phase] [-- brief]"
+---
+
+# AI Consulting Engagement Orchestrator
+
+Run structured AI consulting engagements for SMB and mid-market clients. This skill orchestrates the full engagement lifecycle — from initial discovery through delivery and tracking — coordinating all sub-skills and maintaining engagement state.
+
+## Steps
+
+### Step 1: Parse Arguments and Load Engagement State
+
+Parse the command arguments:
+- `<client-name>` (required): The client identifier, used for directory naming and file lookups
+- `--phase <phase>` (optional): Jump to a specific phase. One of: `discovery`, `assess`, `propose`, `design`, `deliver`, `track`
+- `-- <brief>` (optional): Free-text brief describing the engagement context or specific request
+
+Check if an engagement already exists for this client:
+
+```bash
+# Check for existing engagement
+ls consulting-toolkit/clients/{client-name}/engagement.json 2>/dev/null
+```
+
+If `engagement.json` exists, read it and resume from the current phase. If it does not exist, initialize a new engagement.
+
+### Step 2: Initialize Client Workspace
+
+If this is a new engagement, create the client directory structure:
+
+```bash
+mkdir -p consulting-toolkit/clients/{client-name}
+```
+
+Create `consulting-toolkit/clients/{client-name}/engagement.json` with this schema:
+
+```json
+{
+  "client": "{client-name}",
+  "engagement_id": "{client-name}-{YYYYMMDD}",
+  "created": "YYYY-MM-DDTHH:MM:SSZ",
+  "updated": "YYYY-MM-DDTHH:MM:SSZ",
+  "status": "active",
+  "current_phase": "discovery",
+  "phases": {
+    "discovery": { "status": "not_started", "started": null, "completed": null, "deliverables": [] },
+    "assess": { "status": "not_started", "started": null, "completed": null, "deliverables": [] },
+    "propose": { "status": "not_started", "started": null, "completed": null, "deliverables": [] },
+    "design": { "status": "not_started", "started": null, "completed": null, "deliverables": [] },
+    "deliver": { "status": "not_started", "started": null, "completed": null, "deliverables": [] },
+    "track": { "status": "not_started", "started": null, "completed": null, "deliverables": [] }
+  },
+  "brief": "{brief or null}",
+  "contacts": [],
+  "decisions": [],
+  "risks": [],
+  "value_captured": {
+    "total_projected": 0,
+    "total_actual": 0,
+    "by_initiative": []
+  }
+}
+```
+
+Create `consulting-toolkit/clients/{client-name}/profile.md` with this stub:
+
+```markdown
+# Client Profile: {Client Name}
+
+> Generated by AI Consulting Toolkit | v1.0 | {date}
+
+## Company Overview
+- **Company:** {client-name}
+- **Industry:** [TBD]
+- **Size:** [employees]
+- **Revenue:** [annual revenue range]
+- **Location:** [HQ location]
+
+## Key Contacts
+| Name | Role | Email | Decision Authority |
+|------|------|-------|--------------------|
+|      |      |       |                    |
+
+## Business Context
+[To be completed during discovery phase]
+
+## AI Maturity Score
+[To be completed during assessment phase]
+- Strategy: _/5
+- Data: _/5
+- Technology: _/5
+- People: _/5
+- Process: _/5
+- **Total: _/25**
+
+## Current Technology Stack
+[To be completed during discovery phase]
+
+## Pain Points & Priorities
+[To be completed during discovery phase]
+
+## Engagement History
+| Date | Phase | Activity | Outcome |
+|------|-------|----------|---------|
+|      |       |          |         |
+```
+
+### Step 3: Route to Active Phase
+
+Based on the current phase (from `engagement.json` or `--phase` argument), execute the appropriate skill:
+
+**Phase: `discovery`**
+```
+Run /client-discovery {client-name} -- {brief}
+```
+Activities:
+- Structured interview guide generation
+- Business model canvas completion
+- Technology stack assessment
+- Data landscape mapping
+- Stakeholder identification
+- Pain point prioritization
+
+Output: Updated `profile.md`, interview notes, data inventory
+
+**Phase: `assess`**
+```
+Run /opportunity-map {client-name}
+```
+Activities:
+- AI Maturity Model assessment (Deloitte-adapted)
+- MECE problem decomposition of key challenges
+- Jobs-to-be-Done AI opportunity analysis
+- Porter's Five Forces AI impact assessment
+- BCG Priority Matrix for AI initiatives
+- Market research on industry AI adoption
+
+Output: Maturity scorecard, opportunity register, priority matrix
+
+**Phase: `propose`**
+```
+Run /pitch-generator {client-name}
+Run /roi-calculator {client-name}
+```
+Activities:
+- Solution options development (2-3 alternatives)
+- ROI model for each recommended initiative
+- Risk assessment and mitigation plan
+- Pricing and engagement structure
+- Proposal document generation
+
+Output: Proposal document, ROI models, risk register
+
+**Phase: `design`**
+```
+Run /solution-architect {client-name}
+```
+Activities:
+- Technical architecture design
+- Integration mapping with existing systems
+- Data pipeline architecture
+- Build vs Buy analysis
+- Implementation sprint plan
+- Technology vendor evaluation
+
+Output: Architecture document, sprint plan, vendor comparison
+
+**Phase: `deliver`**
+```
+Run /deliverable-builder {client-name}
+```
+Activities:
+- Sprint execution tracking
+- Deliverable assembly and review
+- Client presentation preparation
+- Knowledge transfer documentation
+- Change management support
+
+Output: Final deliverables package, handoff documentation
+
+**Phase: `track`**
+```
+Run /engagement-tracker {client-name}
+```
+Activities:
+- Value realization tracking
+- Sprint scorecard updates
+- RAG status reporting
+- Phase transition readiness assessment
+- Engagement health monitoring
+
+Output: Status reports, value tracker updates, phase gate reviews
+
+### Step 4: Phase Transition Protocol
+
+When a phase is complete, follow this transition protocol:
+
+1. **Verify phase completion criteria:**
+   - All required deliverables produced
+   - Client review completed (or flagged for review)
+   - Decision log updated with phase decisions
+   - Risks identified and logged
+
+2. **Update engagement.json:**
+   - Set current phase status to `"completed"`
+   - Set completion timestamp
+   - Record deliverables produced
+   - Advance `current_phase` to next phase
+
+3. **Generate phase transition summary:**
+   ```markdown
+   ## Phase Transition: {previous_phase} -> {next_phase}
+
+   ### Completed
+   - [List of deliverables produced]
+
+   ### Key Decisions
+   - [Decision 1]: [Rationale]
+
+   ### Risks Carried Forward
+   - [Risk 1]: [Mitigation]
+
+   ### Next Phase Objectives
+   - [Objective 1]
+   - [Objective 2]
+   ```
+
+4. **Confirm with user** before advancing to the next phase. Never auto-advance without explicit approval.
+
+### Step 5: Engagement Status Report
+
+At any point, the user can request a status report. Generate it from `engagement.json`:
+
+```markdown
+# Engagement Status: {client-name}
+> {engagement_id} | Updated: {date}
+
+## Phase Progress
+| Phase     | Status       | Started    | Completed  | Deliverables |
+|-----------|-------------|------------|------------|--------------|
+| Discovery | [GREEN/AMBER/RED] | {date} | {date}     | {count}      |
+| Assess    | [status]    | {date}     | {date}     | {count}      |
+| Propose   | [status]    | {date}     | {date}     | {count}      |
+| Design    | [status]    | {date}     | {date}     | {count}      |
+| Deliver   | [status]    | {date}     | {date}     | {count}      |
+| Track     | [status]    | {date}     | {date}     | {count}      |
+
+## Value Summary
+- Projected Annual Value: ${total_projected}
+- Actual Value Captured: ${total_actual}
+- Realization Rate: {percentage}%
+
+## Open Risks ({count})
+{risk_list}
+
+## Recent Decisions ({count})
+{decision_list}
+
+## Next Actions
+{action_items}
+```
+
+### Step 6: Multi-Engagement Management
+
+When no client name is provided, list all active engagements:
+
+```bash
+ls consulting-toolkit/clients/*/engagement.json 2>/dev/null
+```
+
+Display a dashboard:
+
+```markdown
+# Active Engagements
+
+| Client | Phase | Status | Last Updated | Value Projected |
+|--------|-------|--------|--------------|-----------------|
+| ...    | ...   | ...    | ...          | ...             |
+```

package/dist/plugins/prime/skills/custom-domain/SKILL.md

@@ -0,0 +1,261 @@
+---
+name: custom-domain
+description: "Set up, diagnose, or fix custom domain configuration (DNS + app platform + auth + CORS). Commands: setup, check, fix"
+user-invocable: true
+arguments: "command"
+---
+
+# Custom Domain Skill
+
+Manage custom domain configuration across DNS provider, app platform, auth provider, and CORS.
+
+## Argument Parsing
+
+- `command`: Optional. One of: `setup`, `check`, `fix`. Defaults to `check` if omitted.
+
+## Discovery Phase (All Commands)
+
+Before any action, discover the project's domain stack by reading config and env vars:
+
+```
+1. DNS Provider — Check if Cloudflare is in use:
+   curl -sI https://<domain> | grep -i "server: cloudflare"
+   dig <domain> CNAME +short
+
+2. App Platform — Check Railway services:
+   railway status
+   railway domain (on frontend service)
+
+3. Auth Provider — Detect from frontend code:
+   grep -r "STYTCH\|AUTH0\|CLERK\|SUPABASE_AUTH\|FIREBASE_AUTH" frontend/.env* frontend/src/lib/
+
+4. Backend CORS — Check current config:
+   railway variables --kv --service backend | grep CORS
+   railway variables --kv --service backend | grep FRONTEND_URL
+
+5. Custom domain already set? —
+   curl -sI https://<domain> | head -10
+```
+
+Store discovered values for use in subsequent steps.
+
+---
+
+## `/custom-domain setup`
+
+Full end-to-end setup of a new custom domain.
+
+### Step 1: Add Custom Domain in Railway
+
+```bash
+railway service frontend
+railway domain <your-domain.com> --json
+```
+
+The JSON response contains `requiredValue` — this is the CNAME target for DNS. It is NOT the same as the public Railway URL. Railway assigns a separate routing hostname for custom domains.
+
+### Step 2: Configure DNS
+
+**If Cloudflare (recommended):**
+
+Check if Railway offers one-click Cloudflare integration in the dashboard:
+- Railway dashboard -> Frontend service -> Settings -> Custom Domain -> "Connect to Cloudflare"
+- This auto-configures CNAME + TXT verification record + proxy settings
+- Click **Authorize** when prompted
+
+**If manual DNS setup:**
+
+| Field | Value |
+|-------|-------|
+| Type | `CNAME` |
+| Name | `@` (root) or subdomain |
+| Target | `requiredValue` from Step 1 |
+| Proxy | DNS only (grey cloud) for manual; Proxied OK with Railway's Cloudflare integration |
+
+**If non-Cloudflare DNS provider:**
+- Add CNAME record pointing to the `requiredValue`
+- Add any TXT records Railway requires for verification
+- SSL will be provisioned by Railway via Let's Encrypt (may take 2-10 min)
+
+### Step 3: Update Backend CORS + FRONTEND_URL
+
+```bash
+railway service backend
+railway variables set 'CORS_ORIGINS=["https://<new-domain>","https://<existing-railway-frontend-url>"]'
+railway variables set 'FRONTEND_URL=https://<new-domain>'
+```
+
+**CRITICAL — JSON quoting for CORS_ORIGINS:**
+- Value MUST be valid JSON: `["https://domain1","https://domain2"]`
+- Use `railway variables set` CLI directly (NOT the MCP set-variables tool — it strips inner quotes)
+- Verify after setting: `railway variables --kv | grep CORS`
+- If inner quotes are missing, Pydantic (or similar config parser) fails to parse -> app crashes on deploy
+- Keep the old Railway URL in the array so both domains work simultaneously
+
+This triggers a backend redeploy. Wait for it to go green.
+
+### Step 4: Configure Auth Provider
+
+**If Stytch:**
+In Stytch Dashboard -> Live project:
+1. **Frontend SDKs -> Authorized environments** -> Add: `<your-domain.com>`
+2. **Redirect URLs** -> Add:
+   - `https://<your-domain.com>/authenticate` (type: Login)
+   - `https://<your-domain.com>/authenticate` (type: Sign-up)
+
+**If Auth0:** Add `https://<your-domain.com>` to Allowed Callback URLs, Allowed Logout URLs, Allowed Web Origins.
+
+**If Clerk:** Add domain to Clerk Dashboard -> Paths -> Allowed origins.
+
+**If Supabase Auth:** Add redirect URL in Supabase Dashboard -> Auth -> URL Configuration.
+
+No code changes needed for any of these — auth SDKs auto-detect the current domain.
+
+### Step 5: Verify
+
+```bash
+# DNS resolution
+nslookup <your-domain.com>
+
+# HTTPS + SSL working
+curl -sI https://<your-domain.com> | head -10
+# Should return HTTP/2 200
+
+# Backend CORS working (after deploy completes)
+curl -sI -H "Origin: https://<your-domain.com>" https://<backend-url>/health | grep -i "access-control"
+
+# Auth flow — test in browser
+# Navigate to https://<your-domain.com>/login and complete login
+```
+
+---
+
+## `/custom-domain check` (default)
+
+Diagnose the current domain setup. Run all checks and report pass/fail.
+
+```
+Domain Health Check:
+  DNS Resolution:     pass/fail (nslookup + CNAME target)
+  SSL Certificate:    pass/fail (curl -sI, check for valid cert)
+  Frontend Serving:   pass/fail (HTTP 200 from custom domain)
+  Backend CORS:       pass/fail (CORS_ORIGINS includes custom domain)
+  FRONTEND_URL:       pass/fail (points to custom domain)
+  Auth Provider:      pass/fail (domain in authorized list — manual check, remind user)
+  Railway Domain:     pass/fail (old .up.railway.app still works)
+```
+
+### Check Commands
+
+```bash
+# 1. DNS
+dig <domain> CNAME +short
+nslookup <domain>
+
+# 2. SSL
+curl -svI https://<domain> 2>&1 | grep -E "subject:|subjectAltName|SSL"
+
+# 3. Frontend
+curl -sI https://<domain> | head -5
+
+# 4. CORS
+railway service backend
+railway variables --kv | grep CORS_ORIGINS
+# Verify the custom domain is in the JSON array WITH quotes
+
+# 5. FRONTEND_URL
+railway variables --kv | grep FRONTEND_URL
+
+# 6. Railway URL still works
+curl -sI https://<railway-frontend-url> | head -3
+```
+
+---
+
+## `/custom-domain fix`
+
+Fix common domain issues based on symptoms.
+
+### Issue: CORS blocking (dashboard spinning after login)
+
+**Symptom:** Console error: `Access to fetch blocked by CORS policy: No 'Access-Control-Allow-Origin' header`
+
+**Fix:**
+```bash
+railway service backend
+# Check current value
+railway variables --kv | grep CORS_ORIGINS
+# Fix — ensure proper JSON with inner quotes
+railway variables set 'CORS_ORIGINS=["https://<custom-domain>","https://<railway-frontend-url>"]'
+# Verify
+railway variables --kv | grep CORS_ORIGINS
+# Wait for redeploy
+```
+
+### Issue: Backend crash after CORS change
+
+**Symptom:** Config parser error like `SettingsError: error parsing value for field "CORS_ORIGINS"`
+
+**Cause:** Inner quotes stripped from JSON array. MCP set-variables tool or Railway dashboard may mangle JSON.
+
+**Fix:** Use `railway variables set` CLI directly with single-quoted value:
+```bash
+railway variables set 'CORS_ORIGINS=["https://domain1","https://domain2"]'
+```
+
+### Issue: SSL certificate mismatch
+
+**Symptom:** `subjectAltName does not match host name`
+
+**Cause:** Railway hasn't provisioned SSL cert yet (takes 2-10 min), or Cloudflare proxy is off.
+
+**Fix:**
+- Wait 10 minutes and retry
+- If using Cloudflare, enable proxy (orange cloud) — Cloudflare provides instant SSL
+- Check Railway dashboard for domain verification status
+
+### Issue: Auth session refresh failing
+
+**Symptom:** Auth SDK reports session refresh failed, signs user out on the new domain.
+
+**Cause:** Custom domain not in auth provider's authorized environments/origins list.
+
+**Fix:** Add the domain in your auth provider's dashboard (see Step 4 of setup).
+
+### Issue: Cloudflare Insights CSP violation
+
+**Symptom:** `static.cloudflareinsights.com/beacon.min.js violates Content Security Policy`
+
+**Cause:** Cloudflare proxy injects analytics script; CSP doesn't allow it.
+
+**Fix:** Add to `script-src` in your security headers config:
+```
+https://static.cloudflareinsights.com
+```
+Non-blocking — only affects Cloudflare analytics, not app functionality.
+
+---
+
+## What Does NOT Need to Change
+
+- **Frontend env vars** — API URL stays as backend Railway URL (frontend talks to backend directly)
+- **Agent/worker services** — no changes needed
+- **Backend code** — CORS is configured via env vars, not hardcoded
+- **Old Railway URL** — continues working alongside custom domain (both serve the same app)
+
+## Project-Specific Reference
+
+Add a section at the bottom of your project's copy of this skill with your actual values:
+
+```markdown
+## Project Reference Values
+
+| Item | Value |
+|------|-------|
+| Custom domain | `your-domain.com` |
+| CNAME target | `xxx.up.railway.app` |
+| Frontend Railway URL | `frontend-production-xxx.up.railway.app` |
+| Backend Railway URL | `backend-production-xxx.up.railway.app` |
+| Auth provider | Stytch / Auth0 / Clerk / etc. |
+| DNS provider | Cloudflare / etc. |
+```