Analyzes existing brownfield projects to map documentation structure to SpecWeave's PRD/HLD/Spec/Runbook pattern. Scans folders, classifies documents, detects external tools (Jira, ADO, GitHub), and creates project context map for just-in-time migration. Activates for brownfield, existing project, migrate, analyze structure, legacy documentation.
View on GitHubanton-abyzov/specweave
sw
January 25, 2026
Select agents to install to:
npx add-skill https://github.com/anton-abyzov/specweave/blob/main/plugins/specweave/skills/brownfield-analyzer/SKILL.md -a claude-code --skill brownfield-analyzerInstallation paths:
.claude/skills/brownfield-analyzer/# Brownfield Analyzer
**Self-contained brownfield project analysis for ANY existing codebase.**
---
## Purpose
Analyze existing projects and create migration plan to SpecWeave structure. Two paths supported: Quick Start (incremental) or Comprehensive (upfront).
---
## Two Migration Paths
### Path 1: Quick Start (Recommended for Large Projects)
**Best for**: 50k+ LOC, fast iteration, small teams
**Process**:
1. Initial scan: Document core architecture (1-3 hours)
2. Start working immediately
3. Per increment: Document โ Modify โ Update docs
4. Documentation grows with changes
**Benefits**:
- Start in days, not weeks
- Focus where it matters
- No analysis paralysis
### Path 2: Comprehensive Upfront
**Best for**: <50k LOC, teams, regulated industries
**Process**:
1. Full analysis (1-4 weeks)
2. Document all modules, business rules
3. Create baseline tests
4. Then start increments
**Benefits**:
- Complete context upfront
- Full regression coverage
- Team coordination
- Compliance ready
### Automatic Recommendation
| Project Size | LOC | Upfront Effort | Recommended |
|--------------|-----|----------------|-------------|
| Small | <10k | 4-8 hours | Comprehensive |
| Medium | 10k-50k | 1-2 weeks | User Choice |
| Large | 50k-200k | 2-4 weeks | Quick Start |
| Very Large | 200k+ | 1-3 months | Quick Start (Mandatory) |
---
## Analysis Workflow
### Step 1: Project Assessment
```bash
# Scan project
find . -type f -name "*.ts" -o -name "*.js" -o -name "*.py" | wc -l
find . -type f \( -name "*.ts" -o -name "*.js" \) -exec wc -l {} + | awk '{sum+=$1} END {print sum}'
```
**Calculate**:
- Total files
- Total LOC
- Module count
- Test coverage (if exists)
**Output**:
```
๐ Project Analysis
Files: 1,245
LOC: 45,678
Modules: 23
Tests: 45% coverage
๐ก Recommendation: Medium project โ User choice (Quick Start or Comprehensive)
```
### Step 2: Document Classification
Scan for documentation:
**PRD Candidates** (Product Requirements):
- `requireme