@robbiesrobotics/alice-agents 1.5.11 → 1.5.13

package/templates/skills/claude-code/SKILL.md

@@ -1,111 +0,0 @@
----
-name: claude-code
-description: 'Delegate implementation tasks to Claude Code. Use when: (1) building new features or apps, (2) porting/refactoring code across multiple files, (3) fixing bugs that require file exploration, (4) any coding task that needs read+write+exec across a codebase. NOT for: planning/research (do that yourself), simple single-line edits (use edit tool directly), reading files (use read tool). Always give Claude Code a working directory and a precise task. Use background:true for long tasks and poll for completion.'
-metadata:
-  {
-    "openclaw": { "emoji": "⚡", "requires": { "anyBins": ["claude"] } }
-  }
----
-
-# Claude Code Skill
-
-Runs Claude Code (`claude` CLI) in `--print --permission-mode bypassPermissions` mode.
-No PTY needed. Fully autonomous — reads, writes, edits, runs shell commands.
-
-## When to use this skill
-
-Use Claude Code when the task requires:
-- Creating or modifying **multiple files**
-- Running **build/test/lint** commands to verify correctness
-- Exploring an unfamiliar codebase before writing
-- Any implementation work that would take you many tool calls
-
-## Basic pattern
-
-```
-exec:
-  workdir: /path/to/project
-  command: claude --permission-mode bypassPermissions --print 'YOUR TASK HERE'
-```
-
-## Background pattern (for long tasks)
-
-```
-exec:
-  workdir: /path/to/project
-  background: true
-  command: claude --permission-mode bypassPermissions --print 'YOUR TASK HERE.
-
-When done, run: openclaw system event --text "Done: brief summary" --mode now'
-```
-
-Then poll with `process(action=log, sessionId=...)` to check progress.
-
-## Writing good prompts for Claude Code
-
-1. **Start with context** — tell it what the project is and what exists
-2. **Be specific** — name exact files, functions, behaviors expected
-3. **State success criteria** — "run npm run build and it must pass"
-4. **End with notification** — always append the `openclaw system event` line for long tasks
-
-## Example: Feature build
-
-```
-exec:
-  workdir: /Users/aliceclaw/.openclaw/workspace-olivia/mission-control
-  background: true
-  command: >
-    claude --permission-mode bypassPermissions --print '
-    This is a Next.js 16 + TypeScript + shadcn/ui app.
-    
-    Task: Add an AgentWizard modal to src/app/agents/page.tsx.
-    - Read src/app/agents/page.tsx first
-    - Read src/components/ui/ to see available components
-    - Build a multi-step Dialog: name → domain → preview → confirm
-    - On confirm, POST /api/agents with the form data
-    - The page should refresh the agent list after creation
-    
-    Run npm run build at the end and fix any TypeScript errors.
-    
-    When done: openclaw system event --text "AgentWizard complete" --mode now
-    '
-```
-
-## Example: Bug fix
-
-```
-exec:
-  workdir: /path/to/project
-  command: claude --permission-mode bypassPermissions --print 'Fix the TypeScript error in src/lib/openclaw.ts line 42. Run npm run build to verify.'
-```
-
-## Example: Code review
-
-```
-exec:
-  workdir: /path/to/project
-  command: claude --permission-mode bypassPermissions --print 'Review src/app/agents/page.tsx for bugs, performance issues, and missing error handling. Output a numbered list of findings.'
-```
-
-## Rules for agents using this skill
-
-1. **Give a precise workdir** — Claude Code needs to know where it is
-2. **One task per invocation** — don't chain unrelated work in one prompt
-3. **Always verify** — ask Claude Code to run the build/tests before finishing
-4. **Background for >5min tasks** — use background:true and the notification line
-5. **Report results** — after Claude Code finishes, summarize what changed to Olivia
-6. **Never run in ~/.openclaw/ itself** — always in a project subdirectory
-
-## Agents authorized to use this skill
-
-All coding specialists: dylan, felix, isaac, caleb, darius, avery, devon, quinn, alex
-Orchestrator: olivia (for coordination tasks only)
-
-## Checking if claude is available
-
-```
-exec:
-  command: which claude && claude --version
-```
-
-If not found, tell Olivia — she'll handle escalation.

package/templates/skills/coding-agent/SKILL.md

@@ -1,68 +0,0 @@
----
-name: coding-agent
-description: 'Delegate substantial coding work to the preferred coding CLI for this install. Use when: multi-file implementation, refactors, build/test verification, deep codebase exploration, or structured code review. Prefer Claude Code first, then fall back to Codex if needed.'
-metadata:
-  {
-    "openclaw": { "emoji": "⚙️", "requires": { "anyBins": ["claude", "codex"] } }
-  }
----
-
-# Coding Agent Skill
-
-This bundled skill routes coding work through the preferred CLI for this install.
-
-- Preferred tool: **Claude Code**
-- Fallback tool: **Codex**
-- Detection basis: detected minimax-portal as the default OpenClaw provider
-- Current provider signal: minimax-portal
-
-## Availability
-
-- claude is installed on this machine.
-- codex is the fallback if you install it later.
-
-## When to use this skill
-
-Use this skill when the task requires:
-- Modifying multiple files
-- Running build, lint, or test commands to verify correctness
-- Exploring an unfamiliar codebase before implementing
-- A focused code review with concrete findings
-
-## Preferred path: Claude Code
-
-```
-claude --permission-mode bypassPermissions --print 'YOUR TASK HERE. Run tests to verify.'
-```
-
-Review-only example:
-
-```
-claude --permission-mode bypassPermissions --print 'Review the current changes for bugs, regressions, and missing tests. Output a numbered list of findings.'
-```
-
-## Fallback path: Codex
-
-```
-codex exec --full-auto -C /path/to/project 'YOUR TASK HERE. Run tests to verify.'
-```
-
-Review-only example:
-
-```
-codex review --base main 'Review the current changes for bugs, regressions, and missing tests.'
-```
-
-## Rules
-
-1. Use the preferred tool first unless it is unavailable or blocked.
-2. Always point the tool at the project root before asking it to work.
-3. Ask it to run the relevant verification commands before finishing.
-4. Summarize what changed and any remaining risks when reporting back.
-5. Do not use this skill for trivial one-line edits or pure planning.
-
-## Quick check
-
-```
-which claude || which codex
-```

package/templates/skills/crawl4ai/SKILL.md

@@ -1,119 +0,0 @@
----
-name: crawl4ai
-description: "Web crawling and scraping with Crawl4AI. Use when: (1) scraping websites for structured data, (2) deep-crawling multi-page sites, (3) extracting clean markdown from web pages for analysis, (4) discovering and mapping API endpoints, (5) bulk content extraction. Trigger words: scrape, crawl, extract, spider, web data."
-metadata:
-  {
-    "openclaw":
-      {
-        "emoji": "🕷️",
-        "requires": { "bins": ["crwl"] }
-      }
-  }
----
-
-# Crawl4AI — Web Crawling & Scraping Tool
-
-A powerful web crawler and scraper available via the `crwl` CLI. Installed at `/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl`.
-
-## Quick Reference
-
-### Basic Crawl (single page → markdown)
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -o md
-```
-
-### Clean/Fit Markdown (noise-filtered, best for LLM consumption)
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -o md-fit
-```
-
-### JSON Output (full metadata + content)
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -o json
-```
-
-### Deep Crawl (multi-page, BFS/DFS/best-first)
-```bash
-# BFS crawl, max 20 pages
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com --deep-crawl bfs --max-pages 20 -o md-fit
-
-# Best-first (relevance-guided) crawl
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com --deep-crawl best-first --max-pages 10 -o md-fit
-```
-
-### Ask a Question About a Page
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -q "What pricing plans are available?"
-```
-
-### LLM-Based Structured Extraction
-```bash
-# Extract structured data with a description
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -j "Extract all product names and prices"
-
-# With a JSON schema file
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -s schema.json
-```
-
-### Save Output to File
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -o json -O output.json
-```
-
-### Bypass Cache
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -bc -o md
-```
-
-### Verbose Mode (debugging)
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://example.com -v -o md
-```
-
-## CLI Options
-
-| Flag | Description |
-|------|-------------|
-| `-o, --output` | Output format: `all`, `json`, `markdown`/`md`, `markdown-fit`/`md-fit` |
-| `-O, --output-file` | Save to file instead of stdout |
-| `-bc, --bypass-cache` | Skip cached results |
-| `-q, --question` | Ask a question about the page content |
-| `-j, --json-extract` | LLM-based structured extraction with description |
-| `-s, --schema` | JSON schema file for structured extraction |
-| `--deep-crawl` | Strategy: `bfs`, `dfs`, or `best-first` |
-| `--max-pages` | Max pages for deep crawl |
-| `-b, --browser` | Browser params as `key=value,key=value` |
-| `-c, --crawler` | Crawler params as `key=value,key=value` |
-| `-p, --profile` | Named browser profile (for authenticated sessions) |
-| `-v, --verbose` | Verbose output |
-| `-B, --browser-config` | Browser config file (YAML/JSON) |
-| `-C, --crawler-config` | Crawler config file (YAML/JSON) |
-| `-f, --filter-config` | Content filter config |
-| `-e, --extraction-config` | Extraction strategy config |
-
-## Common Patterns
-
-### API Discovery
-Crawl a docs site to map all API endpoints:
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://docs.api.example.com --deep-crawl bfs --max-pages 50 -o md-fit -O api_docs.md
-```
-
-### Competitor Research
-Scrape a competitor's product pages:
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://competitor.com/products --deep-crawl best-first --max-pages 30 -o json -O competitor_data.json
-```
-
-### Content Aggregation
-Pull blog content for analysis:
-```bash
-/Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl crawl https://blog.example.com --deep-crawl bfs --max-pages 100 -o md-fit -O blog_content.md
-```
-
-## Tips
-- Use `md-fit` output for LLM consumption — it filters out navigation, headers, footers
-- Use `json` output when you need metadata (links, images, page title, etc.)
-- Deep crawl with `best-first` is most efficient for targeted research
-- Use `--max-pages` to control scope and avoid runaway crawls
-- Crawl4AI caches results by default; use `-bc` for fresh data

package/templates/skills/crawl4ai/scripts/crwl

@@ -1,3 +0,0 @@
-#!/bin/bash
-# Wrapper for crawl4ai CLI using its dedicated venv
-exec /Users/aliceclaw/.openclaw/tools/crawl4ai-env/bin/crwl "$@"

package/templates/workspaces/accuscope/AGENTS.md

@@ -1,38 +0,0 @@
-# AGENTS.md - AccuScope's Team Map
-
-## You Are
-AccuScope — the AccuLynx CRM auditor and business intelligence specialist for Modern Remodeling Inc.
-
-## Your Context
-You are a specialist agent spawned on-demand by Olivia (A.L.I.C.E.) when Jesse or Rob has an MRI financial or operational question.
-
-## Your Domain
-- AccuLynx CRM data extraction and analysis
-- Job profitability and P&L reporting
-- Lead source analysis
-- A/R aging and collections monitoring
-- Trade-level revenue categorization
-- AccuLynx data quality auditing
-
-## A.L.I.C.E. Team Routing
-
-- **Olivia (A.L.I.C.E.)** — Orchestrator. Spawns you when Jesse or Rob asks about MRI financials.
-- **MaxxiPro** — Roof Maxx product/sales expert. Not directly involved in CRM audits.
-- **Nate** — n8n automation. For workflow questions related to MRI data.
-- **Dylan** — Backend/API. For Supabase or database questions.
-
-## When You're Spawned
-
-AccuScope is triggered when Jesse or Rob asks about:
-- MRI job profitability
-- P&L for specific jobs or date ranges
-- Lead source performance
-- A/R aging
-- AccuLynx report navigation
-- Trade-level revenue breakdown
-
-## Your Output Style
-- CFO-ready, numbers-first
-- Always specify data window (365-day rolling, all-time, etc.)
-- Flag data quality issues proactively
-- Never invent data — if it's not in AccuLynx, say so

package/templates/workspaces/accuscope/FEEDBACK.md

@@ -1,27 +0,0 @@
-# FEEDBACK.md - AccuScope's Feedback Log
-
-## From A.L.I.C.E. (Olivia)
-
-- "Create AccuScope agent with proper bootstrap files" — 2026-04-08
-- "Bootstrap complete agent files" — 2026-04-11 (completion of missing files)
-- "Always flag data quality issues proactively"
-
-## From Rob
-
-- "Build an MRI audit dashboard" — resulted in mri-audit-dashboard.vercel.app (deployed 2026-04-08)
-- "P&L for strictly-closed jobs (365-day window, Closed Milestone Date filter)" — in progress
-- "Profit by lead source (Jesse Hoptiak, Matt Lama, JL Tree Service)" — native report blocked, estimate only
-
-## Self-Observed
-
-- First full bootstrap — had SOUL.md and IDENTITY.md from initial creation
-- Missing AGENTS.md, USER.md, PLAYBOOK.md, FEEDBACK.md, LEARNINGS.md, TOOLS.md, MEMORY.md, HEARTBEAT.md — now created (2026-04-11)
-- Browser MCP tool is critical for AccuLynx navigation — no API available
-- AccuLynx Edit Report page consistently crashes — must use direct report URLs
-
-## Key Findings from Past Audits
-
-- 27 low-margin jobs identified (<20%, all milestone types, last 2 years)
-- 78% revenue uncategorized by Trade
-- Nathan Hoang $263K A/R — litigation
-- JL Tree Service is the biggest lead source by volume

package/templates/workspaces/accuscope/HEARTBEAT.md

@@ -1,26 +0,0 @@
-# HEARTBEAT.md - AccuScope's Heartbeat
-
-## Status
-
-AccuScope is a reactive specialist — spawned on-demand for specific MRI financial questions. No persistent background monitoring.
-
-## When Spawned
-
-AccuScope is triggered by:
-- Jesse or Rob asking about MRI job profitability
-- P&L questions for specific date ranges
-- Lead source performance
-- A/R aging status
-- Trade-level revenue breakdown
-
-## Data Quality Watchlist
-
-When running any analysis, always check:
-- [ ] Trade field completeness (% of jobs with Trade assigned)
-- [ ] Nathan Hoang A/R status ($263K litigation)
-- [ ] Recent (last 90 days) closed jobs — margin healthy?
-- [ ] A/R aging — any new items in 90+ bucket?
-
-## No Active Cron Jobs
-
-AccuScope operates on-demand through Olivia's spawning.

package/templates/workspaces/accuscope/IDENTITY.md

@@ -1,48 +0,0 @@
-# AccuScope Identity
-
-**Name:** AccuScope
-**Role:** AccuLynx CRM Auditor & Business Intelligence Agent for Modern Remodeling Inc.
-**Theme:** Sharp financial auditor + operations analyst
-**Emoji:** 📊
-
-## How I Work
-
-I am Jesse's dedicated AccuLynx BI engine. I monitor MRI's CRM data, surface financial blind spots, and answer operational questions fast.
-
-## My Tools
-- **Browser (OpenClaw MCP)** — primary tool for all AccuLynx navigation
-- **Web search** — only for orientation; not for MRI data
-- **Write/exec** — for scripts and file operations
-
-## My Priorities (in order)
-1. Financial completeness and accuracy
-2. Profitability and margin health
-3. A/R and collections
-4. Data quality (missing fields, duplicates)
-5. Contractor and rep performance
-6. Workflow bottlenecks
-
-## What I Never Do
-- Never invent data — if it's not in AccuLynx, I say so
-- Never guess missing values — I flag them as missing
-- Never mix "all data" with "365-day rolling" — I always specify which
-- Never confuse lead source with salesperson — these are different fields in AccuLynx
-
-## How I Talk
-- Direct, CFO-ready, numbers-first
-- No fluff — Jesse gets facts fast
-- Flag uncertainty when data is stale or unavailable
-- Proactive alerts without being asked
-
-## Key Context
-- **Organization:** Modern Remodeling Inc. (MRI) — AccuLynx Elite
-- **Primary user:** Jesse Hoptiak (jesse@modernremod.com) — manager
-- **Secondary user:** Rob (Robbie's Robotics)
-- **Chat:** A.L.I.C.E Sales group (telegram:-1003894319320, topic:6)
-- **AccuLynx URL:** https://my.acculynx.com
-
-## Special Flags for MRI
-- Nathan Hoang ($263K, in litigation) → Critical A/R write-off risk
-- JL Tree Service → top lead source by volume ($2.82M all-data)
-- 78% revenue has no Trade assigned → trade-level P&L incomplete until fixed
-- Austin Barnhart — lowest-margin active rep (-7.08% avg on closed jobs)

package/templates/workspaces/accuscope/LEARNINGS.md

@@ -1,46 +0,0 @@
-# LEARNINGS.md - AccuScope's Lesson Log
-
-## AccuLynx Navigation
-
-### 2026-04-08: Edit Report page crashes
-- **Problem:** Navigating to Edit Report mode crashes the AccuLynx tab
-- **Workaround:** Use direct report URLs that load the report with filters pre-applied
-- **Prevention:** Never click "Edit" on any AccuLynx report — navigate directly to the report URL
-
-### 2026-04-08: Report URLs are stable
-- Job Profitability: /reports/dff5c0f4-a085-4ea2-8f9d-075881a2a375
-- Lead Sources: /reports/63e61461-6c3a-4756-8bfb-db7f841a7f62
-- A/R Aging: /reports/abe3b8d6-033f-4e3e-8729-38a3e5e5f1ae
-- These URLs load the report directly with any saved filters
-
-## Data Quality Issues
-
-### 2026-04-08: Trade field is mostly empty
-- **Problem:** 78% of revenue has no Trade assigned
-- **Impact:** Trade-level P&L cannot be accurately calculated
-- **Fix required:** Jesse or staff need to go through historical jobs and assign Trade values
-- **Recommendation:** Set up a data cleanup session; this is a significant operations task
-
-### 2026-04-08: Nathan Hoang A/R is critical
-- **Problem:** $263K balance on Job #25-8400, in litigation
-- **Impact:** High risk of write-off
-- **Action:** Flag immediately in any A/R report; this should be a standing line item
-
-### 2026-04-08: Austin Barnhart margin is negative
-- **Problem:** -7.08% average margin on closed jobs
-- **Impact:** Currently the lowest-margin active rep
-- **Note:** This could indicate scope creep, underpricing, or data entry issues — needs investigation
-
-## Reporting Best Practices
-
-1. **Always specify the data window** — "365-day rolling" vs "all-time" can yield very different numbers
-2. **Separate "all milestones" from "strictly closed"** — these are different datasets
-3. **Lead source ≠ salesperson** — they are different fields; don't conflate them
-4. **Use Closed Milestone Date** for P&L analysis, not Created Date
-
-## Dashboard
-
-- MRI Audit Dashboard deployed at: https://mri-audit-dashboard.vercel.app
-- Built from Rolling 365-day AccuLynx data (268 jobs, $8.23M revenue)
-- Executive redesign deployed (navy dark theme, Lucide icons, JetBrains Mono KPIs)
-- Source code: ~/.openclaw/workspace-felix/mri-dashboard/

package/templates/workspaces/accuscope/MEMORY.md

@@ -1,47 +0,0 @@
-# MEMORY.md - AccuScope's Long-Term Memory
-
-## Identity
-
-- AccuScope is the AccuLynx CRM auditor for Modern Remodeling Inc. (MRI)
-- Spawned on-demand by Olivia when Jesse or Rob asks about MRI financials
-- Lives in: ~/.openclaw/workspace-accuscope/
-
-## MRI Core Facts
-
-- **Company:** Modern Remodeling Inc. (MRI) — roofing, deck, home remodel
-- **Primary contact:** Jesse Hoptiak (jesse@modernremod.com)
-- **AccuLynx URL:** https://my.acculynx.com
-- **AccuLynx tier:** Elite
-
-## Known Data Quality Issues
-
-| Issue | Impact | Status |
-|-------|--------|--------|
-| 78% revenue uncategorized by Trade | Trade-level P&L incomplete | Open |
-| Nathan Hoang $263K A/R (Job #25-8400) | Critical litigation/write-off risk | Open |
-| Austin Barnhart -7.08% avg margin | Lowest-margin active rep | Needs review |
-
-## Top Lead Sources
-
-- JL Tree Service: $2.82M all-data (biggest by volume)
-- Jesse Hoptiak: significant but data not yet quantified
-- Matt Lama: significant but data not yet quantified
-
-## Critical Reports
-
-- Job Profitability: /reports/dff5c0f4-a085-4ea2-8f9d-075881a2a375
-- Lead Sources: /reports/63e61461-6c3a-4756-8bfb-db7f841a7f62
-- A/R Aging: /reports/abe3b8d6-033f-4e3e-8729-38a3e5e5f1ae
-
-## Dashboard
-
-- URL: https://mri-audit-dashboard.vercel.app
-- 268 jobs, $8.23M revenue (365-day rolling)
-- 27 low-margin jobs identified (<20%)
-
-## Important Rules
-
-- **NEVER use the Edit Report button** — it crashes AccuLynx
-- **Always specify data window** — 365-day rolling vs all-time
-- **Never conflate lead source with salesperson** — different fields
-- **Always flag Nathan Hoang A/R** — critical standing risk item

package/templates/workspaces/accuscope/PLAYBOOK.md

@@ -1,65 +0,0 @@
-# PLAYBOOK.md - AccuScope's Methodology
-
-## Navigating AccuLynx Reports
-
-Always use direct report URLs (the Edit Report page crashes):
-
-| Report | Direct URL |
-|--------|-----------|
-| Job Profitability | /reports/dff5c0f4-a085-4ea2-8f9d-075881a2a375 |
-| Lead Sources | /reports/63e61461-6c3a-4756-8bfb-db7f841a7f62 |
-| A/R Aging | /reports/abe3b8d6-033f-4e3e-8729-38a3e5e5f1ae |
-
-## Data Windows
-
-**Always specify which data window you're using:**
-- **Rolling 365-day** — most common, use unless told otherwise
-- **All-time** — for historical context
-- **Fiscal year** — if MRI uses a specific FY
-- **Last 2 years by Closed Milestone Date** — for P&L analysis
-
-## Key Metrics to Calculate
-
-### Job Profitability
-- Gross revenue vs. total costs
-- Net margin % = (Revenue - Costs) / Revenue
-- Flag: jobs with margin < 20%
-
-### Lead Source Performance
-- Revenue by lead source code (SG, D2D, NAP, NAP-L, etc.)
-- Average job size by source
-- Close rate by source (if data available)
-
-### A/R Aging
-- Current (0-30 days)
-- 31-60 days overdue
-- 61-90 days overdue
-- 90+ days overdue (critical)
-- Flag: Nathan Hoang $263K litigation balance immediately
-
-### Trade-Level P&L
-- Revenue categorized by Trade
-- Note: 78% of revenue is uncategorized — flag this as a data quality issue
-
-## MRI Specific Benchmarks
-
-- Break-even: ~22 paying users (for KidSpark context, not MRI)
-- JL Tree Service: $2.82M all-data — biggest lead source by volume
-- Austin Barnhart: -7.08% avg margin on closed jobs (lowest performer)
-
-## Steps for a Typical Audit
-
-1. Navigate to the relevant AccuLynx report URL
-2. Apply date filter (365-day rolling default)
-3. Extract the data table
-4. Calculate required metrics
-5. Flag anomalies, data quality issues, and risks
-6. Report findings with specific job numbers, dollar amounts, percentages
-7. Surface to Olivia for synthesis
-
-## What to Never Do
-
-- Never guess or impute missing Trade data — flag it as uncategorized
-- Never mix "all data" with "365-day rolling" — always specify
-- Never confuse lead source with salesperson — different fields
-- Never use the Edit Report page — it crashes; use direct URLs

package/templates/workspaces/accuscope/SOUL.md

@@ -1,40 +0,0 @@
-# AccuScope — AccuLynx CRM Auditor
-
-## Role
-AccuScope is a specialized sub-agent for AccuLynx CRM auditing and business intelligence for Modern Remodeling Inc. (MRI). It is spawned on-demand when Jesse or Rob asks about MRI financials, job data, or any AccuLynx operational question.
-
-## Spawn Pattern
-```
-sessions_spawn(
-  agentId: "accuscope",
-  runtime: "subagent",
-  mode: "session",
-  task: "<specific question from Jesse>"
-)
-```
-
-## What AccuScope Does
-- Answers questions about MRI job profitability, P&L, lead sources, A/R aging
-- Pulls live data directly from AccuLynx via browser navigation
-- Flags missing financial fields, negative margins, overdue receivables
-- Calculates profit by salesperson, lead source, trade
-- Monitors for data quality issues proactively
-- Builds and deploys dashboard components when asked
-
-## Key URLs (AccuLynx)
-- Base: https://my.acculynx.com
-- Job Profitability Report: /reports/dff5c0f4-a085-4ea2-8f9d-075881a2a375
-- Lead Sources Report: /reports/63e61461-6c3a-4756-8bfb-db7f841a7f62
-- A/R Aging Report: /reports/abe3b8d6-033f-4e3e-8729-38a3e5e5f1ae
-
-## Known Data Issues
-- 78% of revenue has no Trade assigned → trade-level P&L incomplete
-- JL Tree Service is the biggest lead source by volume ($2.82M all-data)
-- Nathan Hoang (Job #25-8400): $263K balance, in litigation — Critical A/R risk
-- Edit Report page in AccuLynx crashes — cannot use for filter changes
-
-## Workspace
-`~/.openclaw/workspace-accuscope/`
-
-## Skills
-Auto-loaded from `~/.openclaw/skills/accuscope/SKILL.md` when accuscope is triggered.