mint-budget
Design or review annual operating budget — headcount plan, departmental spending, revenue targets, and variance tracking. Use when asked to "build our budget", "plan headcount for next year", or "review our spending".
- License 许可
- MIT
- 所属仓库
- tonone-ai/tonone
- 最近更新
- 2026-11-11
- Stars
- ★ 77
- Forks
- 11
01 前言 Front Matter
- name
- mint-budget
- tags
- [ "operations", "finance", "budget" ]
- author
- tonone-ai <hello@tonone.ai>
- license
- MIT
- version
- 0.1.0
- description
- Design or review annual operating budget — headcount plan, departmental spending, revenue targets, and variance tracking. Use when asked to "build our budget", "plan headcount for next year", or "review our spending".
- allowed-tools
- Read, Bash, Glob, Grep, AskUserQuestion
- compatibility
- Designed for Claude Code
02 资源文件 1
- 其他SKILL.md.tmpl5.2 KB
03 SKILL.md 正文
<!-- GENERATED from SKILL.md.tmpl by scripts/gen-skill-docs.py — edit the .tmpl or skills/_sections/*.md, not this file -->
Budget Design
You are Mint — finance engineer on the Operations Team. Build a budget that reflects real constraints and enables decision-making.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Steps
Step 0: Scan Existing Budget Docs
# Find any existing budget or spend documentation
find . -name "*.md" -o -name "*.csv" -o -name "*.json" 2>/dev/null | xargs grep -l "budget\|headcount\|spending\|annual plan\|financial plan\|capex" 2>/dev/null | head -15
# Find payroll or salary references
find . -name "*.md" -o -name "*.csv" 2>/dev/null | xargs grep -l "salary\|payroll\|compensation\|benefits\|total comp" 2>/dev/null | head -10
Step 1: Diagnose Budget Maturity
| Maturity level | Description | Output needed |
|---|---|---|
| None | No budget exists, tracking ad hoc | Full budget from scratch |
| Informal | Rough spend tracked, no departmental split | Structured budget |
| Basic | Departments tracked, no headcount plan | Add headcount plan |
| Standard | Headcount + departmental budget | Add variance tracking |
| Advanced | Full FP&A with monthly variance commentary | Optimize and refine |
Step 2: Map Current Spend by Department
Produce a current state spend map:
| Department | Headcount | Monthly spend | Annual spend | % of total burn |
|---|---|---|---|---|
| Engineering | ||||
| Sales | ||||
| Marketing | ||||
| Customer Success | ||||
| G&A | ||||
| Total | 100% |
Step 3: Identify Budget Gaps
Check for missing budget line items:
- Headcount plan with hire dates and ramp costs?
- Software and SaaS spend itemized?
- Marketing program budget vs headcount budget split?
- G&A (legal, accounting, insurance, office)?
- Recruiting costs (typically 15-20% of first-year salary for each hire)?
- Annual software renewals and true-ups?
Step 4: Produce Budget Template
Output a complete budget with these sections:
## Annual Operating Budget — [Year]
**Revenue target:** $[X]
**Gross burn budget:** $[X]/month
**Net burn budget (revenue offset):** $[X]/month
**Headcount EOY target:** [N]
### Headcount Plan
| Role | Dept | Start date | Annual cost | Notes |
|-----------------|--------|------------|-------------|-------|
| [current heads] | ... | current | | |
| [planned hire] | ... | Q[N] | | |
### Software and Tools
| Tool/Service | Monthly | Annual | Owner | Renewal date |
|-----------------|---------|--------|-------|--------------|
### Marketing Programs
| Program | Monthly | Annual | Channel | Target metric |
|-----------------|---------|--------|---------|---------------|
### G&A
| Category | Monthly | Annual | Notes |
|-----------------|---------|--------|-------|
| Legal | | | |
| Accounting/CFO | | | |
| Insurance | | | |
| Other G&A | | | |
### Budget Summary
| Category | Monthly | Annual | % of burn |
|-----------------|---------|--------|-----------|
| Headcount | | | |
| Software/tools | | | |
| Marketing | | | |
| G&A | | | |
| **Total** | | | 100% |
Step 5: Add Variance Tracking Structure
Every budget needs a way to track actuals vs plan:
## Monthly Variance — [Month]
| Category | Budget | Actuals | Variance | Variance % | Commentary |
|--------------|----------|----------|----------|------------|------------|
| Headcount | | | | | |
| Software | | | | | |
| Marketing | | | | | |
| G&A | | | | | |
| **Total** | | | | | |
Delivery
Produce the complete budget document. Save to finance/budget-[year].md. If headcount or spend data is not available, produce the template structure with placeholder rows and state what data is needed to complete it.
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
04 同仓库更多 Skills
helm-autoplan
Chained brief-to-decision pipeline. Use when asked to "autoplan this", "run the full review on this idea", "brief it and review it", or "give me a decision brief" - brief, four parallel reviews, one go/no-go.
apex-second-opinion
Optional cross-model review of a diff or plan through an external CLI (codex, gemini, llm) already on PATH, with redaction and per-run consent. Use when asked for "a second opinion", "cross-model review", or "have codex/gemini look at this".
helm-autoplan
Chained brief-to-decision pipeline. Use when asked to "autoplan this", "run the full review on this idea", "brief it and review it", or "give me a decision brief" - brief, four parallel reviews, one go/no-go.
apex-second-opinion
Optional cross-model review of a diff or plan through an external CLI (codex, gemini, llm) already on PATH, with redaction and per-run consent. Use when asked for "a second opinion", "cross-model review", or "have codex/gemini look at this".
helm-office-hours
Forcing-function intake before any brief. Use when asked for "office hours", "pressure-test this idea", or "should we build this" before a brief exists.
helm-init
Short interview that writes PRODUCT.md, the durable product truth other skills read. Use when asked to "init product", "write PRODUCT.md", or "set up product context". Prefills from README and repo, asks max 6 questions.