walkthrough-generate

name	walkthrough-generate
description	Generate implementation walkthrough for human review after run completion. Documents decisions, changes, and verification steps.
version	1.0.0

Generate implementation walkthrough for human review after run completion. - Run completed successfully - Invoked by run-execute skill

<degrees_of_freedom> LOW — Follow walkthrough structure precisely. Be thorough but concise. </degrees_of_freedom>

ALWAYS generate walkthrough after run completion Document DECISIONS, not just changes Include verification steps — how to test this works Track DEVIATIONS from plan — compare to original work item List ALL new dependencies added during implementation Capture developer notes — gotchas save future debugging time Read run log from .specs-fire/runs/{run-id}/run.md Read work item plan from .specs-fire/intents/{intent}/work-items/{work-item}/ Collect: Work item details (id, title, intent) Files created during implementation Files modified during implementation Decisions made during execution Tests added and coverage Dependencies added (new packages in package.json, requirements.txt, etc.) Deviations from the original work item plan For each file created/modified: Identify purpose of the file Summarize key changes Note patterns or approaches used Document structure overview: How the pieces fit together architecturally Data flow or component relationships Keep high-level, NO CODE Extract implementation highlights: Main flow/algorithm implemented Security considerations (if applicable) Performance considerations (if applicable) Integration points with existing code Document deviations from plan: Compare implementation to original work item plan Note any changes and explain WHY they were made If no deviations, state "None" Capture developer notes: Gotchas or non-obvious behaviors Tips for future developers Context that would save debugging time Generate how-to-verify section: Commands to run the feature Expected behavior/output Manual test scenarios Generate walkthrough using template: templates/walkthrough.md.hbs Save to: .specs-fire/runs/{run-id}/walkthrough.md Walkthrough generated: .specs-fire/runs/{run-id}/walkthrough.md

<output_template> Walkthrough (.specs-fire/runs/{run-id}/walkthrough.md):

---
run: {run-id}
work_item: {work-item-id}
intent: {intent-id}
generated: {timestamp}
mode: {mode}
---

# Implementation Walkthrough: {title}

## Summary

{2-3 sentences describing what was implemented}

## Structure Overview

{High-level description of how pieces fit together - NO CODE}

## Files Changed

### Created

| File | Purpose |
|------|---------|
| `{path}` | {purpose} |

### Modified

| File | Changes |
|------|---------|
| `{path}` | {changes} |

## Key Implementation Details

### 1. {Detail Title}

{description of implementation approach}

## Decisions Made

| Decision | Choice | Rationale |
|----------|--------|-----------|
| {decision} | {choice} | {rationale} |

## Deviations from Plan

{Changes from work item plan and why, or "None"}

## Dependencies Added

| Package | Why Needed |
|---------|------------|
| `{package}` | {reason} |

## How to Verify

1. **{Step Title}**
   ```bash
   {command}
   ```
   Expected: {expected output}

2. **{Step Title}**
   {manual verification steps}

## Test Coverage

- Tests added: {count}
- Coverage: {percentage}%
- Status: {passing/failing}

## Developer Notes

{Gotchas, tips, or context for future work - keep brief}

---
*Generated by specs.md - fabriqa.ai FIRE Flow Run {run-id}*

</output_template>

<success_criteria> Walkthrough generated with all sections Structure overview explains architecture (NO CODE) Files changed documented with purposes Decisions recorded with rationale Deviations from plan documented (or "None") Dependencies added listed with reasons Verification steps included Developer notes capture gotchas and tips Saved to run folder </success_criteria>