<objective> Generate implementation walkthrough for human review after run completion. </objective> <triggers> - Run completed successfully - Invoked by run-execute skill </triggers>

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

<llm critical="true"> <mandate>ALWAYS generate walkthrough after run completion</mandate> <mandate>Document DECISIONS, not just changes</mandate> <mandate>Include verification steps — how to test this works</mandate> </llm> <flow> <step n="1" title="Gather Implementation Data"> <action>Read run log from .specs-fire/runs/{run-id}/run.md</action> <action>Collect:</action> <substep>Work item details (id, title, intent)</substep> <substep>Files created during implementation</substep> <substep>Files modified during implementation</substep> <substep>Decisions made during execution</substep> <substep>Tests added and coverage</substep> </step> <step n="2" title="Analyze Implementation"> <action>For each file created/modified:</action> <substep>Identify purpose of the file</substep> <substep>Summarize key changes</substep> <substep>Note patterns or approaches used</substep> </step> <step n="3" title="Document Key Details"> <action>Extract implementation highlights:</action> <substep>Main flow/algorithm implemented</substep> <substep>Security considerations (if applicable)</substep> <substep>Performance considerations (if applicable)</substep> <substep>Integration points with existing code</substep> </step> <step n="4" title="Create Verification Steps"> <action>Generate how-to-verify section:</action> <substep>Commands to run the feature</substep> <substep>Expected behavior/output</substep> <substep>Manual test scenarios</substep> </step> <step n="5" title="Generate Walkthrough"> <action>Generate walkthrough using template: templates/walkthrough.md.hbs</action> <action>Save to: .specs-fire/runs/{run-id}/walkthrough.md</action> <output> Walkthrough generated: .specs-fire/runs/{run-id}/walkthrough.md </output> </step> </flow>

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

markdown

---
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}

## 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} |

## 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}

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

</output_template>

<success_criteria> <criterion>Walkthrough generated with all sections</criterion> <criterion>Files changed documented with purposes</criterion> <criterion>Decisions recorded with rationale</criterion> <criterion>Verification steps included</criterion> <criterion>Saved to run folder</criterion> </success_criteria>