Agent skill
walkthrough-generate
Generate implementation walkthrough for human review after run completion. Documents decisions, changes, and verification steps.
Install this agent skill to your Project
npx add-skill https://github.com/fabriqaai/specs.md/tree/main/src/flows/fire/agents/builder/skills/walkthrough-generate
SKILL.md
<degrees_of_freedom> LOW — Follow walkthrough structure precisely. Be thorough but concise. </degrees_of_freedom>
<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}
## Architecture (if multi-component)
### Pattern Used
{Pattern and rationale - e.g., Repository pattern for data access abstraction}
### Layer Structure
```text
┌─────────────────────────────┐
│ Presentation │
├─────────────────────────────┤
│ Application │
├─────────────────────────────┤
│ Domain │
├─────────────────────────────┤
│ Infrastructure │
└─────────────────────────────┘
```
## Files Changed
### Created
| File | Purpose |
|------|---------|
| `{path}` | {purpose} |
### Modified
| File | Changes |
|------|---------|
| `{path}` | {changes} |
## Domain Model (if entities created)
### Entities
| Entity | Properties | Business Rules |
|--------|------------|----------------|
| {name} | {props} | {rules} |
### Value Objects
| Value Object | Properties | Constraints |
|--------------|------------|-------------|
| {name} | {props} | {constraints} |
## Key Implementation Details
### 1. {Detail Title}
{description of implementation approach}
## Security Considerations (if applicable)
| Concern | Approach |
|---------|----------|
| {concern} | {approach} |
## Performance Considerations (if applicable)
| Requirement | Implementation |
|-------------|----------------|
| {requirement} | {implementation} |
## 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}
## Test Coverage
- Tests added: {count}
- Coverage: {percentage}%
- Status: {passing/failing}
## Ready for Review
- [x] All acceptance criteria met
- [x] Tests passing
- [x] No critical issues
- [ ] Documentation updated (if applicable)
- [x] Developer notes captured
## 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 applicable sections Structure overview explains architecture (NO CODE) Architecture pattern documented (if multi-component) Domain model documented (if entities created) Files changed documented with purposes Security considerations documented (if security-relevant) Performance considerations documented (if performance-relevant) Decisions recorded with rationale Deviations from plan documented (or "None") Dependencies added listed with reasons Verification steps included Ready for Review checklist completed Developer notes capture gotchas and tips Saved to run folder </success_criteria>
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
run-status
Display current run status and progress. Shows work item, mode, duration, and files changed.
run-plan
Plan the scope of a run by discovering available work items and suggesting groupings. Invoked before run-execute.
code-review
Review code written during a run, auto-fix no-brainer issues, and suggest improvements requiring confirmation. Invoked after tests pass.
run-execute
Execute work items based on their assigned mode (autopilot, confirm, validate). Supports single-item and multi-item (batch/wide) runs.
route
Analyze project state and route user to the appropriate agent based on current context.
Didn't find tool you were looking for?