Menu
Analyzes codebase to find similar features, reusable utilities, and architectural patterns
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
DEPRECATED - Use domain-specific skills instead. Routes to bazinga-db-core, bazinga-db-workflow, bazinga-db-agents, or bazinga-db-context.
Task groups and development planning. Use when managing task groups, development plans, or success criteria.
Agent logs, reasoning, and token tracking. Use when logging interactions, saving reasoning, tracking tokens, or managing events.
Validates BAZINGA completion claims with independent verification. Spawned ONLY when PM sends BAZINGA. Acts as final quality gate - verifies test failures, coverage, evidence, and criteria independently. Returns ACCEPT or REJECT verdict.
Build complete agent prompts deterministically via Python script. Use BEFORE spawning any BAZINGA agent (Developer, QA, Tech Lead, PM, etc.).
Context packages and learning patterns. Use when managing context packages, error patterns, or strategies.
| version | 1.0.0 |
| name | codebase-analysis |
| description | Analyzes codebase to find similar features, reusable utilities, and architectural patterns |
| author | BAZINGA Team |
| tags | ["development","analysis","codebase","context"] |
| allowed-tools | ["Bash","Read"] |
You are the codebase-analysis skill. Your role is to analyze a codebase and provide developers with relevant context for their implementation tasks.
When invoked with a task description and session ID, you must:
python3 .claude/skills/codebase-analysis/scripts/analyze_codebase.py \
--task "$TASK_DESCRIPTION" \
--session "$SESSION_ID" \
--cache-enabled
Note: Output path defaults to bazinga/artifacts/{session_id}/skills/codebase-analysis/report.json (session-isolated)
# Read from session-isolated artifact directory
cat bazinga/artifacts/$SESSION_ID/skills/codebase-analysis/report.json
Return a concise summary including:
CODEBASE ANALYSIS COMPLETE
## Similar Features Found
- User registration (auth/register.py) - 85% similarity
* Email validation pattern
* Token generation approach
* Database transaction handling
## Reusable Utilities
- EmailService (utils/email.py) - send_email(), validate_email()
- TokenGenerator (utils/tokens.py) - generate_token(), verify_token()
## Architectural Patterns
- Service layer pattern (business logic in services/)
- Repository pattern for data access
## Suggested Implementation Approach
1. Create PasswordResetService in services/
2. Reuse EmailService for sending reset emails
3. Use TokenGenerator for reset tokens
4. Follow transaction pattern from register.py
Full analysis: bazinga/artifacts/{session_id}/skills/codebase-analysis/report.json
If analysis times out or fails:
For detailed documentation: .claude/skills/codebase-analysis/references/usage.md