Skip to main content
ClaudeWave
Skill91 repo starsupdated 3mo ago

finalize-phase

The finalize-phase skill completes feature or epic workflows after successful deployment by generating comprehensive documentation, updating project roadmaps, archiving artifacts, and cleaning up Git branches. Use this skill immediately after deployment completes via /ship-prod, /deploy-prod, or /build-local, or when requested by the user to close out a workflow and preserve project knowledge.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow /tmp/finalize-phase && cp -r /tmp/finalize-phase/.claude/skills/finalize-phase ~/.claude/skills/finalize-phase
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

<objective>
Complete feature/epic workflow, generate walkthrough (epics only), update roadmap, archive artifacts, and preserve knowledge after deployment. Ensures clean workflow closure with self-improving workflow system.

This skill orchestrates the /finalize phase, the final step after successful deployment to production, direct-prod, or local build.

**For Epic Workflows (v5.0+)**:

- Generate comprehensive walkthrough.md with velocity metrics, sprint results, lessons learned
- Run post-mortem audit with pattern detection (after 2-3 epics)
- Offer workflow healing with improvement recommendations
- Detect patterns for custom skills/commands generation

**For Feature Workflows**:

- Standard finalization (roadmap, artifacts, docs, branches)

Inputs: Deployed feature/epic, phase artifacts, ship report, state.yaml
Outputs: walkthrough.md (epics only), updated roadmap, archived artifacts, updated documentation
Expected duration: 10-15 minutes (features), 20-30 minutes (epics with walkthrough)
</objective>

<quick_start>
After deployment completes, finalize the workflow:

**Epic Workflows (NEW in v5.0)**: 0. Generate walkthrough - Comprehensive epic summary with velocity metrics, sprint results, lessons learned, pattern detection

1. Run post-mortem audit - Final effectiveness analysis with improvement recommendations
2. Offer workflow healing - Apply discovered improvements with user approval

**All Workflows** (features + epics):

1. Update roadmap - Move to "Shipped" with completion date, version, production URL
2. Archive artifacts - Verify all phase artifacts in specs/NNN-slug/ or epics/NNN-slug/
3. Update documentation - README, CHANGELOG, user guides (if applicable)
4. Clean up branches - Delete feature branch locally and remotely
5. Commit finalization - Small commit documenting workflow closure

Key principles:

- Clean closure preserves knowledge and enables learning
- Epic walkthroughs enable self-improving workflow system
- Pattern detection (after 2-3 epics) suggests custom automation
  </quick_start>

<prerequisites>
Before beginning finalization:
- Deployment completed successfully (/ship-prod, /deploy-prod, or /build-local done)
- Ship report generated (ship-summary.md exists)
- All phase artifacts present in specs/NNN-slug/
- Git working tree clean (all changes committed)

If deployment incomplete, return to /ship phase.
</prerequisites>

<workflow>
<step number="0">
**Epic Walkthrough Generation** (Epic workflows only - NEW in v5.0)

Detect epic vs feature workflow and generate comprehensive walkthrough for epics.

**Detection**:

```bash
if [ -f "epics/*/epic-spec.xml" ]; then
  WORKSPACE_TYPE="epic"
  EPIC_DIR=$(dirname "epics/*/epic-spec.xml")
else
  WORKSPACE_TYPE="feature"
  # Skip to Step 1 (standard finalization)
  continue
fi
```

**If feature workflow**: Skip this step entirely, proceed to Step 1

**If epic workflow**: Generate walkthrough before standard finalization

**Walkthrough Generation Pipeline**:

1. **Gather all epic artifacts**:

   - epic-spec.xml (epic specification)
   - research.xml (research phase output)
   - plan.xml (plan phase output with meta-prompting)
   - sprint-plan.xml (task breakdown with dependency graph)
   - state.yaml (state tracking across phases)
   - audit-report.xml (workflow effectiveness analysis)
   - preview-report.xml (manual testing decision)
   - Sprint results from epics/NNN-slug/sprints/\*/

2. **Calculate velocity metrics**:

   - Expected parallelization multiplier (from sprint-plan.xml)
   - Actual parallelization multiplier (from audit-report.xml)
   - Time saved in hours (parallel vs sequential execution)
   - Duration from start to completion

3. **Extract key information**:

   - Epic goal and success metrics
   - Phases completed with timestamps
   - Sprint execution results (status, tasks, duration, contracts, tests)
   - Validation results (optimization, preview decision)
   - Key files modified
   - Next steps (enhancements, technical debt, monitoring needs)

4. **Generate walkthrough.xml and walkthrough.md**:

   - Use template: `.spec-flow/templates/walkthrough.xml`
   - Populate with metrics, sprint results, lessons learned
   - Write both machine-readable (XML) and human-readable (Markdown) versions

5. **Run post-mortem audit**:

   - Invoke `/audit-workflow --post-mortem`
   - Analyze velocity accuracy (expected vs actual)
   - Detect bottlenecks and inefficiencies
   - Generate improvement recommendations

6. **Pattern detection** (if 2+ epics completed):

   - Analyze patterns across completed epics
   - Detect code generation patterns (service boilerplate repeated 3x)
   - Detect architectural patterns (all services use DI + Repository)
   - Detect workflow patterns (always clarify auth approach)
   - Suggest custom skills/commands if confidence ≥80%

7. **Offer workflow healing**:

   - Display immediate improvements from audit recommendations
   - Categorize by priority (immediate vs deferred)
   - Offer `/heal-workflow` to apply improvements
   - Save deferred improvements for pattern-based optimization

8. **Commit walkthrough**:

```bash
git add epics/*/walkthrough.xml
git add epics/*/walkthrough.md
git add epics/*/audit-report.xml

git commit -m "docs: generate epic walkthrough

[EPIC SUMMARY]
Epic: ${epic_slug}
Duration: ${duration_hours}h
Velocity: ${velocity_multiplier}x (saved ${time_saved}h)

[SPRINTS COMPLETED]
Total: ${total_sprints}
Execution: ${execution_strategy}
Tasks: ${tasks_completed}/${total_tasks}

[QUALITY METRICS]
Audit Score: ${audit_score}/100
Phase Efficiency: ${phase_efficiency}/100

[LESSONS LEARNED]
- What worked: ${what_worked_summary}
- What struggled: ${what_struggled_summary}

{IF recommendations > 0}
Improvement recommendations: ${recommendations_count}
Run /heal-workflow to apply improvements
{ENDIF}

🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>"
```

9. **Present walkthrough summary** to user with:
   - Velocity metrics (expected