Best use case
budget-review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
It is a strong fit for teams already working in Codex.
Project directory path (default current directory)
Teams using budget-review should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/budget-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How budget-review Compares
| Feature / Agent | budget-review | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Project directory path (default current directory)
Which AI agents support this skill?
This skill is designed for Codex.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Budget Review Command
Analyze marketing budget performance with spend tracking, ROI analysis, and optimization recommendations.
## What This Command Does
1. **Tracks Spending**
- Budget vs. actual
- Category breakdown
- Variance analysis
2. **Analyzes ROI**
- Channel efficiency
- Campaign ROI
- Cost per acquisition
3. **Provides Recommendations**
- Reallocation opportunities
- Efficiency improvements
- Forecasting
## Orchestration Flow
```
Budget Review Request
↓
[Budget Planner] → Budget Analysis
↓
[Marketing Analyst] → Performance Correlation
↓
[Attribution Specialist] → Channel ROI
↓
[Campaign Orchestrator] → Campaign Efficiency
↓
[Reporting Specialist] → Budget Report
↓
Budget Review Complete
```
## Agents Involved
| Agent | Role | Output |
|-------|------|--------|
| Budget Planner | Lead analysis | Budget tracking |
| Marketing Analyst | Performance | ROI analysis |
| Attribution Specialist | Attribution | Channel efficiency |
| Campaign Orchestrator | Campaigns | Campaign costs |
| Reporting Specialist | Reporting | Final report |
## Output Artifacts
Saved to `.aiwg/marketing/budget/`:
- `budget-review-{period}.md` - Budget analysis
- `roi-analysis.md` - ROI breakdown
- `variance-report.md` - Budget vs. actual
- `recommendations.md` - Optimization suggestions
- `forecast.md` - Forward projections
## Parameter Handling
### --guidance Parameter
**Purpose**: Provide upfront direction to tailor priorities and approach
**Examples**:
```bash
--guidance "Q4 optimization, reallocate underperforming channels"
--guidance "New budget request justification"
--guidance "Year-end close, maximize ROI"
```
**How Applied**:
- Parse guidance for keywords: priority, timeline, audience, focus, constraints
- Adjust agent emphasis and output depth based on stated priorities
- Modify deliverable order based on timeline constraints
- Influence scope and detail level based on context
### --interactive Parameter
**Purpose**: Guide through discovery questions for comprehensive input
**Questions Asked** (if --interactive):
1. What is the review period?
2. What triggered this review?
3. Are there specific channels to analyze?
4. What is the decision context (optimization, new request)?
5. Who needs this analysis?
## Usage Examples
```bash
# Quarterly review
/budget-review "Q3 2024"
# YTD paid media
/budget-review "YTD" --budget-area paid-media
# Monthly all areas
/budget-review "October 2024" --budget-area all
# With strategic guidance
/budget-review "Example" --guidance "Your specific context here"
# Interactive mode
/budget-review "Example" --interactive
```
## Success Criteria
- [ ] Spending tracked against budget
- [ ] Variances explained
- [ ] ROI calculated by channel/campaign
- [ ] Optimization opportunities identified
- [ ] Reallocation recommendations provided
- [ ] Forecast updated
## References
- @$AIWG_ROOT/agentic/code/frameworks/media-marketing-kit/README.md — Media marketing kit framework overview
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/vague-discretion.md — Measurable ROI thresholds and review criteria
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/subagent-scoping.md — Multi-agent budget analysis orchestration
- @$AIWG_ROOT/docs/cli-reference.md — CLI referenceRelated Skills
pr-reviewer
Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.
review-synthesis
Aggregate multi-reviewer feedback into consolidated, prioritized, and actionable recommendations
pr-review
Conduct comprehensive PR review from multiple perspectives (PM, Developer, QA, Security)
flow-security-review-cycle
Orchestrate continuous security validation, threat modeling, vulnerability management, and security gate enforcement across SDLC phases
brand-review
Project directory path (default current directory)
aiwg-orchestrate
Route structured artifact work to AIWG workflows via MCP with zero parent context cost
venv-manager
Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.
pytest-runner
Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
vitest-runner
Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
eslint-checker
Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.
repo-analyzer
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
YouTube Acquisition
yt-dlp patterns for acquiring content from YouTube and video platforms