agent-os-framework
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.
What this skill does
# Agent OS Framework
> Generate standardized .agent-os structure for AI-native repository workflows.
## Quick Start
```bash
# Generate full .agent-os structure
/agent-os-framework
# Generate for existing project
/agent-os-framework --update
# Generate specific component
/agent-os-framework --component mission
```
## When to Use
**USE when:**
- Setting up new repository
- Adding AI workflow support
- Documenting product vision
- Creating decision records
**DON'T USE when:**
- Project has complete .agent-os
- Non-product repositories (e.g., dotfiles)
## Prerequisites
- Repository initialized with git
- Basic project understanding
- Stakeholder input for mission
## Overview
Creates complete .agent-os structure:
1. **product/** - Core product documentation
2. **specs/** - Feature specifications
3. **standards/** - Code style guidelines
4. **instructions/** - Workflow instructions
## Directory Structure
```
.agent-os/
├── product/
│ ├── mission.md # Product pitch, users, pain points
│ ├── tech-stack.md # Technology choices
│ ├── roadmap.md # Development phases
│ └── decisions.md # Decision log
├── specs/
│ └── README.md # Spec index
├── standards/
│ ├── code-style.md # Coding guidelines
│ └── testing.md # Testing guidelines
└── instructions/
├── create-spec.md # How to create specs
└── execute-tasks.md # How to execute tasks
```
## Core Templates
### 1. mission.md
```markdown
# Mission: [Project Name]
> [One-line pitch describing the project's core purpose]
## Product Pitch
[2-3 paragraph description of what the product does, why it exists, and what problem it solves]
## Target Users
### Primary Users
- **[User Type 1]**: [Description and needs]
- **[User Type 2]**: [Description and needs]
### Secondary Users
- **[User Type 3]**: [Description and needs]
## Pain Points Addressed
### Before This Product
1. **[Pain Point 1]**: [Description of the problem]
2. **[Pain Point 2]**: [Description of the problem]
3. **[Pain Point 3]**: [Description of the problem]
### After This Product
1. **[Solution 1]**: [How this product solves the problem]
2. **[Solution 2]**: [How this product solves the problem]
3. **[Solution 3]**: [How this product solves the problem]
## Success Metrics
| Metric | Current | Target | Timeframe |
|--------|---------|--------|-----------|
| [Metric 1] | [Current value] | [Target value] | [When] |
| [Metric 2] | [Current value] | [Target value] | [When] |
| [Metric 3] | [Current value] | [Target value] | [When] |
## Differentiators
### What Makes This Unique
1. **[Differentiator 1]**: [Description]
2. **[Differentiator 2]**: [Description]
3. **[Differentiator 3]**: [Description]
### Competitive Landscape
- **[Competitor 1]**: [How we differ]
- **[Competitor 2]**: [How we differ]
## Non-Goals
Things explicitly out of scope:
- [Non-goal 1]
- [Non-goal 2]
- [Non-goal 3]
---
*Last Updated: [Date]*
*Version: 1.0.0*
```
### 2. tech-stack.md
```markdown
# Tech Stack: [Project Name]
> Technical architecture and technology choices
## Overview
| Category | Technology | Version | Purpose |
|----------|-----------|---------|---------|
| Language | Python | 3.11+ | Primary development |
| Package Manager | UV | Latest | Fast dependency management |
| Testing | pytest | 7.4+ | Test framework |
| Visualization | Plotly | 5.15+ | Interactive charts |
| Data | Pandas | 2.0+ | Data processing |
## Core Technologies
### Python 3.11+
**Why**: Modern async support, performance improvements, type hints
**Usage**: All source code in `src/`
### UV Package Manager
**Why**: 10-100x faster than pip, reliable lockfiles
**Usage**: `uv venv`, `uv pip install`
### pytest
**Why**: Industry standard, excellent fixtures, plugins
**Usage**: All tests in `tests/`
### Plotly
**Why**: Interactive plots, HTML export, professional appearance
**Usage**: All visualizations must be interactive (no static matplotlib)
### Pandas
**Why**: Data manipulation, time series, CSV handling
**Usage**: Data loading and transformation
## Development Tools
| Tool | Purpose | Configuration |
|------|---------|---------------|
| ruff | Linting | pyproject.toml |
| black | Formatting | pyproject.toml |
| mypy | Type checking | pyproject.toml |
| pytest-cov | Coverage | pytest.ini |
## Infrastructure
### Version Control
- **Git**: Source control
- **GitHub**: Remote repository
- **Branch Strategy**: main → feature branches → PR
### CI/CD
- **GitHub Actions**: Automated testing
- **Coverage**: Minimum 80%
## Data Storage
| Type | Location | Format |
|------|----------|--------|
| Raw data | data/raw/ | CSV, JSON |
| Processed | data/processed/ | CSV, Parquet |
| Results | data/results/ | CSV, JSON |
| Reports | reports/ | HTML |
## External Dependencies
### APIs
- [API 1]: [Purpose]
- [API 2]: [Purpose]
### Services
- [Service 1]: [Purpose]
- [Service 2]: [Purpose]
## Decision Rationale
### Why Python?
- Strong ecosystem for data analysis
- Excellent library support (Pandas, NumPy, Plotly)
- Team expertise
- Integration with existing tools
### Why UV over pip?
- Significantly faster installation
- Reliable dependency resolution
- Lockfile support
- workspace-hub standard
### Why Plotly over Matplotlib?
- Interactive by default
- Better HTML export
- Modern API
- workspace-hub HTML reporting standard
---
*Last Updated: [Date]*
*Version: 1.0.0*
```
### 3. roadmap.md
```markdown
# Roadmap: [Project Name]
> Development phases and milestones
## Vision
[Long-term vision for the product - where it will be in 1-2 years]
## Current Phase
**Phase [N]: [Phase Name]**
- Status: [In Progress / Planning / Complete]
- Target: [Date]
- Progress: [X]%
## Phase Overview
```
Phase 1: Foundation [████████████████████] 100%
Phase 2: Core Features [████████████░░░░░░░░] 60%
Phase 3: Enhancement [░░░░░░░░░░░░░░░░░░░░] 0%
Phase 4: Scale [░░░░░░░░░░░░░░░░░░░░] 0%
Phase 5: Optimization [░░░░░░░░░░░░░░░░░░░░] 0%
```
## Detailed Phases
### Phase 1: Foundation ✅
**Goal**: Establish project structure and basic functionality
**Duration**: 2 weeks
#### Deliverables
- [x] Project structure setup
- [x] Basic configuration
- [x] Core module implementation
- [x] Initial test coverage (80%+)
- [x] Documentation framework
#### Key Outcomes
- Working development environment
- Basic functionality operational
- CI/CD pipeline configured
---
### Phase 2: Core Features 🚧
**Goal**: Implement primary feature set
**Duration**: 4 weeks
#### Deliverables
- [x] Feature A implementation
- [x] Feature B implementation
- [ ] Feature C implementation
- [ ] Integration testing
- [ ] Documentation complete
#### Key Outcomes
- Primary use cases supported
- User-facing functionality complete
- Quality standards met
---
### Phase 3: Enhancement 📋
**Goal**: Add secondary features and improvements
**Duration**: 3 weeks
#### Deliverables
- [ ] Advanced Feature D
- [ ] Performance optimizations
- [ ] Additional integrations
- [ ] Extended test coverage
- [ ] User documentation
#### Key Outcomes
- Feature-complete product
- Performance targets met
- Full documentation
---
### Phase 4: Scale 📋
**Goal**: Prepare for production scale
**Duration**: 2 weeks
#### Deliverables
- [ ] Performance testing
- [ ] Load testing
- [ ] Security review
- [ ] Deployment automation
- [ ] Monitoring setup
#### Key Outcomes
- Production-ready
- Monitoring operational
- Runbook complete
---
### Phase 5: Optimization 📋
**Goal**: Continuous improvement
**Duration**: Ongoing
#### Deliverables
- [ ] User feedback integration
- [ ] Performance tuning
- [ ] Technical debt reduction
- [ ] Feature iteration
#### Key Outcomes
- Improved user satisfaction
- Better performance
- Reduced maintenance burden
## Milestones
| Milestone | Target Date | Status |
|-----------|------------|--------|
| MVP Complete | [Date] | ✅ |
| Beta Release | [Date] | 🚧 |
| Production Release | [Date] | 📋 |
| Feature ComplRelated in workspace-hub
data-validation-reporter
IncludedGenerate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.
claude-reflection
IncludedSelf-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences
interactive-report-generator
IncludedGenerate interactive HTML reports with Plotly visualizations from data analysis results. Supports dashboards, charts, and professional styling.
yaml-workflow-executor
IncludedExecute data processing workflows defined in YAML configuration files. Supports data loading, transformation, validation, and reporting pipelines.
bash-script-framework
IncludedCreate organized bash script structure with color output, menu systems, error handling, and cross-platform support. Standardizes CLI tooling.
pytest-fixture-generator
IncludedGenerate standardized pytest configuration with fixtures, markers, and coverage settings. Creates conftest.py and pytest.ini for workspace-hub compliant testing.