finance-ops
AI-powered financial analysis suite. Generates executive CFO briefings from QuickBooks exports (P&L, Balance Sheet, General Ledger, Cash Flow, etc.) with anomaly detection, burn rate, runway analysis, and scenario modeling. Also estimates codebase development costs with organizational overhead and AI ROI analysis. Triggers on: 'CFO briefing', 'financial analysis', 'cost briefing', 'expense review', 'runway analysis', 'burn rate', 'cost estimate', 'how much would this cost to build', 'development cost', 'Claude ROI'.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- finance-ops
- version
- 1.0.0
- homepage
- https://github.com/ericosiu/ai-marketing-skills
- description
- AI-powered financial analysis suite. Generates executive CFO briefings from QuickBooks exports (P&L, Balance Sheet, General Ledger, Cash Flow, etc.) with anomaly detection, burn rate, runway analysis, and scenario modeling. Also estimates codebase development costs with organizational overhead and AI ROI analysis. Triggers on: 'CFO briefing', 'financial analysis', 'cost briefing', 'expense review', 'runway analysis', 'burn rate', 'cost estimate', 'how much would this cost to build', 'development cost', 'Claude ROI'.
- description_en
- AI CFO assistant for financial briefings, cost analysis, and scenario modeling
- description_zh
- AI CFO 助手,财务简报、成本分析与场景建模
02 资源文件 11
- 其他.env.example246 B
- 参考文档references/claude-roi.md3.0 KB
- 参考文档references/metrics-guide.md2.0 KB
- 参考文档references/org-overhead.md1.1 KB
- 参考文档references/output-template.md3.9 KB
- 参考文档references/quickbooks-formats.md3.2 KB
- 参考文档references/rates.md1.2 KB
- 参考文档references/team-cost.md1.5 KB
- 参考文档requirements.txt54 B
- 脚本scripts/cfo-analyzer.py29.4 KB
- 脚本scripts/scenario-modeler.py10.5 KB
03 SKILL.md 正文
Preamble (runs on skill start)
# Version check (silent if up to date)
python3 telemetry/version_check.py 2>/dev/null || true
# Telemetry opt-in (first run only, then remembers your choice)
python3 telemetry/telemetry_init.py 2>/dev/null || true
Privacy: This skill logs usage locally to
~/.ai-marketing-skills/analytics/. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. Seetelemetry/README.md.
AI Finance Ops
Two tools: CFO Briefing Generator and Codebase Cost Estimator.
Tool 1: CFO Briefing Generator
Generate executive financial summaries from QuickBooks exports.
Workflow
1. Ingest Files
Place QuickBooks export files (CSV, XLSX, XLS) in a working directory. Accepted report types (any subset works — P&L alone is sufficient):
- P&L Summary — Revenue, COGS, expenses, net income (MOST IMPORTANT)
- P&L by Customer — Revenue breakdown by client
- P&L Detail — Transaction-level detail (XLSX)
- Balance Sheet — Assets, liabilities, equity
- General Ledger — All account transactions
- Expenses by Vendor — Vendor-level expense breakdown
- Transaction List by Vendor — Detailed vendor transactions
- Bill Payments — AP payment history
- Cash Flow Statement — Operating/investing/financing flows (XLSX)
- Account List — Chart of accounts
2. Run Analysis
python3 scripts/cfo-analyzer.py --input ./data/uploads/ [--period YYYY-MM]
Options:
--input DIR— Directory with QB exports--period YYYY-MM— Override period label (default: auto-detected from files)--history DIR— History directory for MoM comparison (default:./data/history/)--no-history— Skip saving to history
The script:
- Auto-detects file types by scanning headers
- Parses each file into structured data
- Computes all KPIs (see
references/metrics-guide.mdfor definitions and healthy ranges) - Loads prior period from history for MoM comparison
- Saves current period to history
- Outputs formatted executive summary to stdout
3. Scenario Modeling (Optional)
After running the CFO analysis, model base/bull/bear scenarios:
python3 scripts/scenario-modeler.py --input ./data/financial-latest.json
This generates 12-month projections for:
- Base case — current trajectory continues
- Bull case — growth targets met (new product revenue + new clients)
- Bear case — lose top clients
4. Deliver Summary
The script outputs a formatted briefing with emoji status indicators (🟢🟡🔴), suitable for Slack, email, or any messaging surface.
File Format Details
See references/quickbooks-formats.md for expected CSV/XLSX column formats and detection heuristics.
Metric Thresholds
See references/metrics-guide.md for healthy ranges, red/yellow/green thresholds, and benchmark context. Adjust thresholds for your business size and type.
Tool 2: Codebase Cost Estimator
Estimate full development cost of a codebase.
Workflow
Step 1: Analyze the Codebase
Read the entire codebase. Catalog total lines of code by language/type, architectural complexity, advanced features, testing coverage, and documentation quality.
Step 2: Calculate Development Hours
Apply productivity rates from references/rates.md. Calculate base hours per code type, then apply overhead multipliers for architecture, debugging, review, docs, integration, and learning curve.
Step 3: Research Market Rates
Use web search to find current hourly rates for the relevant specializations. Build a rate table with low / median / high for the project's tech stack.
Step 4: Calculate Organizational Overhead
Convert raw dev hours to calendar time using efficiency factors from references/org-overhead.md. Show estimates across company types (Solo through Enterprise).
Step 5: Calculate Full Team Cost
Apply supporting role ratios and team multipliers from references/team-cost.md. Show role-by-role breakdown, plus summary across all company stages.
Step 6: Generate Cost Estimate
Output the full estimate using the template in references/output-template.md. Include all sections: codebase metrics, dev hours, calendar time, market rates, engineering cost, full team cost, grand total summary, and assumptions.
Step 7: AI ROI Analysis (Optional)
If the codebase was built with AI assistance, calculate value per AI hour using references/claude-roi.md. Determine active hours via git history clustering, calculate speed multiplier vs human developer, and compute cost savings and ROI.
Key Principles
- Present professionally, suitable for stakeholders
- Include confidence level (low/medium/high) and key assumptions
- Highlight highest-complexity areas that drive cost
- Always show ranges (low/avg/high), never a single number
- Search for CURRENT year market rates, don't use stale data
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.