@robbiesrobotics/alice-agents 1.5.8 → 1.5.9

package/README.md

@@ -2,7 +2,7 @@
 
 **Adaptive Learning & Intelligent Coordination Engine**
 
-One conversation. One orchestrator. Ten starter agents — with 21 more in Pro. A.L.I.C.E. turns your agent runtime into a full AI team — talk to A.L.I.C.E. (or just Alice), and she routes your request to the right expert.
+One conversation. One orchestrator. Ten starter agents — with 23 more in Pro. A.L.I.C.E. turns your agent runtime into a full AI team — talk to A.L.I.C.E. (or just Alice), and she routes your request to the right expert.
 
 **NemoClaw compatible** — A.L.I.C.E. v1.2.7+ runs natively on [NVIDIA NemoClaw](https://nvidia.com/nemoclaw), the secure open-source agent runtime. Agents execute inside the OpenShell sandbox for enterprise-grade security.
 
@@ -16,7 +16,7 @@ That's it. The installer detects your runtime (NemoClaw or OpenClaw) and sets ev
 
 ## What You Get
 
-**Starter** includes 10 agents. **Pro** unlocks 21 more — [sign up at getalice.av3.ai](https://getalice.av3.ai/signup?plan=pro)
+**Starter** includes 10 agents. **Pro** unlocks 23 more — [sign up at getalice.av3.ai](https://getalice.av3.ai/signup?plan=pro)
 
 **A.L.I.C.E. | Control Cloud** is available as a Pro add-on. If enabled during install, the package now:
 - installs the `mission-control-bridge` plugin into your OpenClaw home
@@ -58,6 +58,9 @@ An orchestrator (A.L.I.C.E., also addressable as Alice or Olivia) backed by spec
 | **Parker** | Project Management | 📅 | Pro |
 | **Aria** | Autonomous Research | 🔬 | Pro |
 | **Nate** | n8n Automation | 🔧 | Pro |
+| **MaxxiPro** | Roof Maxx Expert | 🏠 | Pro |
+| **AccuScope** | AccuLynx CRM Auditor | 📊 | Pro |
+| **SmokeTestAgent** | QA Specialist | 🧪 | Pro |
 
 ## Model Flexibility
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@robbiesrobotics/alice-agents",
-  "version": "1.5.8",
+  "version": "1.5.9",
   "description": "A.L.I.C.E. \u2014 31 AI agents for OpenClaw. One conversation, one team.",
   "bin": {
     "alice-agents": "bin/alice-install.mjs",

package/templates/skills/acculynx/SKILL.md

@@ -0,0 +1,183 @@
+---
+name: acculynx
+description: 'Analyze AccuLynx CRM CSV exports and build a live visual P&L dashboard on Vercel. Use when: Jesse or Rob drops AccuLynx CSV files in the A.L.I.C.E Sales chat and asks for analysis, a visual dashboard, or a PDF report. Covers Job Profitability Report and Job Expenses Report. Handles data quality flagging, trade/rep/stage breakdowns, and Vercel deployment.'
+metadata:
+  {
+    "openclaw": { "emoji": "📊", "requires": { "anyBins": ["python3", "node", "npx", "vercel"] } }
+  }
+---
+
+# AccuLynx Analysis Skill
+
+Builds a full visual P&L + Cash Flow dashboard from AccuLynx CSV exports and deploys it live to Vercel.
+
+## Trigger Phrases
+- "analyze acculynx"
+- "build acculynx dashboard"
+- "upload acculynx csv"
+- "drop acculynx"
+- "refresh the dashboard"
+- "acclynx report"
+- Any message with a `.csv` attachment from AccuLynx in the A.L.I.C.E Sales thread
+
+## Two CSV Types (know the difference)
+
+### 1. Job Profitability Report
+**Filename pattern:** `Job_Profitability_Report*.csv`
+**What it contains:** Per-job revenue, expenses, profit, margin %, stage, trades, salesperson
+**Key columns:** `Contract Amount`, `Orders Total`, `Profit`, `Profit %`, `Total Expenses`, `Primary Salesperson`, `Order Trades`, `Current Milestone`
+**Use for:** Overall P&L, top/bottom jobs, rep performance, trade profitability, margin distributions, data quality
+**NOT for:** Cash flow (that's the Expenses Report)
+
+### 2. Job Expenses Report
+**Filename pattern:** `Job_Expenses_Report*.csv` or `job_expenses_report*.csv`
+**What it contains:** Weekly cash outflows (paid expenses, unbudgeted/additional costs)
+**Key columns:** `Payment Date (by week)`, `Total Paid Expenses`, `Paid Expenses Count`, `Additional Expenses Total`, `Additional Expenses Count`
+**Use for:** Cash flow analysis, monthly expense trends, peak payout weeks
+**NOT for:** Per-job profitability (use the Profitability Report for that)
+
+## Standard Workflow
+
+### Step 1 — Save the CSV(s)
+When a CSV arrives via Telegram media attachment, it's auto-saved to:
+```
+/Users/aliceclaw/.openclaw/media/inbound/
+```
+Look for the newest matching file. The filename will contain the report type and date.
+
+### Step 2 — Analyze the Data
+Write and run a Python analysis script. Key things to compute:
+
+**From Job Profitability Report:**
+```python
+import csv
+from collections import defaultdict
+
+jobs = []
+with open('/path/to/Job_Profitability_Report*.csv') as f:
+    reader = csv.DictReader(f)
+    for row in reader:
+        try:
+            jobs.append({
+                'name': row['Job Name'],
+                'contract': float(row['Contract Amount'] or 0),
+                'profit': float(row['Profit'] or 0),
+                'profit_pct': float(row['Profit %'] or 0),
+                'expenses': float(row['Total Expenses'] or 0),
+                'salesperson': row['Primary Salesperson'],
+                'trades': row['Order Trades'],
+                'milestone': row['Current Milestone'],
+            })
+        except: pass
+```
+Compute: total revenue/profit/expenses, overall margin, profitable/lost counts, by-stage summaries, by-rep summaries, by-trade summaries, top 10/bottom 10 jobs, data quality issues (zero contract, missing trades, pending losses).
+
+**From Job Expenses Report:**
+```python
+rows = []
+with open('/path/to/job_expenses_report*.csv') as f:
+    reader = csv.DictReader(f)
+    for row in reader:
+        rows.append({
+            'date': row['Payment Date (by week)'],
+            'paid': float(row['Total Paid Expenses']),
+            'additional': float(row['Additional Expenses Total']),
+            'count': int(row['Paid Expenses Count']),
+        })
+```
+Compute: total paid, avg weekly, monthly aggregation, peak week, trend over time.
+
+### Step 3 — Build the Dashboard
+Use Next.js 14 + Tailwind CSS + Chart.js (via CDN in layout.tsx).
+
+**Project location:** `/tmp/acculynx-dashboard/`
+**Vercel deploy token:** `<VERCEL_TOKEN>`
+
+**Standard sections:**
+1. About This Data (explain both CSV types)
+2. Portfolio KPIs (revenue, profit, margin, win rate)
+3. Cash Flow Analysis (expenses data — if Job Expenses Report available)
+4. P&L by Job Stage
+5. Top 10 Jobs vs Biggest Losses
+6. Sales Rep Performance (bar charts for profit and margin)
+7. Trade Type Profitability
+8. Margin / Profit Distributions
+9. Data Quality Issues (zero contract, missing trades, pending losses)
+
+**Required package.json dependencies:**
+```json
+{
+  "dependencies": {
+    "next": "^14.2.0",
+    "react": "^18.3.0",
+    "react-dom": "^18.3.0"
+  },
+  "devDependencies": {
+    "typescript": "^5.4.0",
+    "tailwindcss": "^3.4.0",
+    "autoprefixer": "^10.4.0",
+    "postcss": "^8.4.0",
+    "@types/node": "^20.0.0",
+    "@types/react": "^18.3.0",
+    "@types/react-dom": "^18.3.0"
+  }
+}
+```
+
+**Chart.js CDN (add to layout.tsx head):**
+```tsx
+<script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.0/dist/chart.umd.min.js" />
+```
+
+**Build command:** `cd /tmp/acculynx-dashboard && npm run build`
+**Deploy command:** `cd /tmp/acculynx-dashboard && npx vercel deploy --prod --yes --token <VERCEL_TOKEN>`
+
+### Step 4 — Deploy and Report
+1. Run build — fix any TypeScript errors (common: `const` redeclaration, missing `any` type on Chart.js callbacks)
+2. Deploy to Vercel with the token above
+3. Reply in the Telegram thread with the live URL
+4. Summarize key findings in the message
+
+## Common Issues
+
+### TypeScript error: Parameter 'ctx' implicitly has 'any' type
+```tsx
+// Wrong:
+label: ctx => ...
+// Right:
+label: (ctx: any) => ...
+```
+
+### BUILD ERROR: 'const' declarations must be initialized
+Spaces in constant names — use underscores:
+```python
+# Wrong:
+BREAK EVEN = 11
+# Right:
+BREAK_EVEN = 11
+```
+
+### Chart.js not loading
+Load via CDN script tags in `layout.tsx <head>` — don't use npm install for Chart.js in this setup.
+
+## Key Thresholds (construction industry)
+- **Good margin:** 30%+
+- **Acceptable margin:** 20–30%
+- **Warning:** <20% or any negative
+- **Roofing typically:** 10–20% (thin — flag if <10%)
+- **Service trades:** usually high margin (40%+)
+- **Overall portfolio margin:** good at >15%
+
+## Data Quality Flags to Always Report
+1. Jobs with `Contract Amount = 0` — profit can't be calculated
+2. Jobs with `Profit % = 0` but nonzero profit — margin not computable
+3. Jobs with no `Order Trades` — unclassified
+4. Approved/Completed/Invoiced jobs with negative profit — embedded losses
+5. `Additional Expenses` with no corresponding payments — unbudgeted costs
+
+## Reply Format
+Always lead with the dashboard URL, then summarize:
+1. Key P&L numbers (revenue, profit, margin)
+2. The most important insight (worst job, worst rep, worst trade, or cash flow flag)
+3. Data quality summary
+4. Ask: "Want me to set up weekly auto-refresh?"

package/templates/skills/acculynx/references/analysis_template.py

@@ -0,0 +1,116 @@
+import csv
+from collections import defaultdict
+
+jobs = []
+
+with open('/Users/aliceclaw/.openclaw/media/inbound/Job_Profitability_Report-4_08_2026_14_4_7---1ed402bb-54d3-4511-b88f-76cdbc4769ae.csv') as f:
+    reader = csv.DictReader(f)
+    for row in reader:
+        try:
+            contract = float(row['Contract Amount'] or 0)
+            orders_total = float(row['Orders Total'] or 0)
+            profit = float(row['Profit'] or 0)
+            profit_pct = float(row['Profit %'] or 0)
+            total_expenses = float(row['Total Expenses'] or 0)
+            salesperson = row['Primary Salesperson']
+            trades = row['Order Trades']
+            name = row['Job Name']
+            jobs.append({
+                'name': name,
+                'contract': contract,
+                'orders': orders_total,
+                'profit': profit,
+                'profit_pct': profit_pct,
+                'expenses': total_expenses,
+                'salesperson': salesperson,
+                'trades': trades
+            })
+        except:
+            pass
+
+# Sort by profit
+by_profit = sorted(jobs, key=lambda x: x['profit'], reverse=True)
+by_margin = sorted(jobs, key=lambda x: x['profit_pct'], reverse=True)
+losers = sorted(jobs, key=lambda x: x['profit'])
+
+total_profit = sum(j['profit'] for j in jobs)
+total_revenue = sum(j['contract'] for j in jobs)
+total_expenses = sum(j['expenses'] for j in jobs)
+profitable_count = len([j for j in jobs if j['profit'] > 0])
+lost_money_count = len([j for j in jobs if j['profit'] < 0])
+zero_count = len([j for j in jobs if j['profit'] == 0])
+
+print("=" * 72)
+print("JESSE -- FULL P&L ANALYSIS (Job Profitability Report)")
+print("=" * 72)
+
+print("\nOVERALL P&L SUMMARY")
+print(f"  Total Revenue:       ${total_revenue:>14,.2f}")
+print(f"  Total Expenses:     ${total_expenses:>14,.2f}")
+print(f"  TOTAL PROFIT:        ${total_profit:>14,.2f}")
+print(f"  Overall Margin:      {(total_profit/total_revenue*100):>14.1f}%")
+print(f"  ")
+print(f"  Jobs Profitable:     {profitable_count}")
+print(f"  Jobs Lost Money:     {lost_money_count}")
+print(f"  Jobs Break-Even:     {zero_count}")
+print(f"  Total Jobs:          {len(jobs)}")
+
+print("\n" + "=" * 72)
+print("TOP 10 JOBS BY PROFIT $")
+print("-" * 72)
+print(f"{'Job':<38} {'Profit':>10} {'Margin':>8} {'Salesperson':<20}")
+print("-" * 72)
+for j in by_profit[:10]:
+    print(f"{j['name'][:36]:<38} ${j['profit']:>9,.0f} {j['profit_pct']*100:>6.0f}%  {j['salesperson'][:18]:<20}")
+
+print("\n" + "=" * 72)
+print("TOP 10 JOBS BY MARGIN %")
+print("-" * 72)
+print(f"{'Job':<38} {'Margin':>8} {'Profit':>10} {'Salesperson':<20}")
+print("-" * 72)
+for j in by_margin[:10]:
+    if j['contract'] > 0:
+        print(f"{j['name'][:36]:<38} {j['profit_pct']*100:>6.0f}%  ${j['profit']:>9,.0f}  {j['salesperson'][:18]:<20}")
+
+print("\n" + "=" * 72)
+print("⚠️  JOBS THAT LOST MONEY")
+print("-" * 72)
+print(f"{'Job':<38} {'Loss':>10} {'Margin':>8} {'Salesperson':<20}")
+print("-" * 72)
+lost = [j for j in jobs if j['profit'] < 0]
+for j in sorted(lost, key=lambda x: x['profit'])[:10]:
+    print(f"{j['name'][:36]:<38} ${j['profit']:>9,.0f} {j['profit_pct']*100:>6.0f}%  {j['salesperson'][:18]:<20}")
+if not lost:
+    print("  No jobs with negative profit found")
+
+print("\n" + "=" * 72)
+print("SALESRep PERFORMANCE (Profit)")
+print("-" * 72)
+reps = defaultdict(lambda: {'profit': 0, 'revenue': 0, 'count': 0})
+for j in jobs:
+    reps[j['salesperson']]['profit'] += j['profit']
+    reps[j['salesperson']]['revenue'] += j['contract']
+    reps[j['salesperson']]['count'] += 1
+print(f"{'Salesperson':<22} {'Jobs':>5} {'Revenue':>12} {'Profit':>12} {'Margin':>8}")
+print("-" * 72)
+for rep, d in sorted(reps.items(), key=lambda x: x[1]['profit'], reverse=True):
+    margin = (d['profit']/d['revenue']*100) if d['revenue'] > 0 else 0
+    print(f"{rep[:20]:<22} {d['count']:>5} ${d['revenue']:>10,.0f} ${d['profit']:>10,.0f} {margin:>7.0f}%")
+
+print("\n" + "=" * 72)
+print("TRADE PERFORMANCE (Profit by Primary Trade)")
+print("-" * 72)
+trades = defaultdict(lambda: {'profit': 0, 'revenue': 0, 'count': 0})
+for j in jobs:
+    primary_trade = j['trades'].split(',')[0].strip() if j['trades'] else 'Unknown'
+    trades[primary_trade]['profit'] += j['profit']
+    trades[primary_trade]['revenue'] += j['contract']
+    trades[primary_trade]['count'] += 1
+print(f"{'Trade':<20} {'Jobs':>5} {'Revenue':>12} {'Profit':>12} {'Margin':>8}")
+print("-" * 72)
+for trade, d in sorted(trades.items(), key=lambda x: x[1]['profit'], reverse=True):
+    margin = (d['profit']/d['revenue']*100) if d['revenue'] > 0 else 0
+    print(f"{trade[:18]:<20} {d['count']:>5} ${d['revenue']:>10,.0f} ${d['profit']:>10,.0f} {margin:>7.0f}%")
+
+EOF
+python3 /tmp/acculynx_analysis.py