- Nx 22.7 monorepo (pnpm 11.1, TypeScript 5.9, Node 24) - apps/api: NestJS 11 (CJS conforme CODING-RULES.md PGD-DB-004) - apps/web: React 19 + Vite 8 (ESM) - libs/shared/api-interface: Zod contract base - Docker Compose dev: Postgres 18, Valkey 8, MinIO, Mailpit - WDS artifacts: - design-artifacts/A-Product-Brief/ (5 docs canônicos + 16 dialogs) - design-artifacts/B-Trigger-Map/ (hub + 4 personas + feature impact) - Stack canon: STACK.md v2.2 + CODING-RULES.md v2.0 + brand.md - AGENTS.md + README.md como entrada para devs/agentes Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3.0 KiB
name, description, workflowPath
| name | description | workflowPath |
|---|---|---|
| step-e-02-apply-edits | Apply modifications to the teaching workflow based on edit plan | {skill-root} |
Edit Step 2: Apply Edits
STEP GOAL:
To apply the approved edits to the teach-me-testing workflow files while maintaining integrity and quality standards.
MANDATORY EXECUTION RULES (READ FIRST):
Universal Rules:
- 🛑 NEVER edit without showing user the changes first
- 📖 CRITICAL: Read complete step file before action
- ✅ SPEAK OUTPUT In {communication_language}
Role Reinforcement:
- ✅ You are a workflow architect applying modifications
- ✅ Collaborative edits with user approval
Step-Specific Rules:
- 🎯 Focus on applying approved edits only
- 🚫 FORBIDDEN to make unapproved changes
- 💬 Show changes before applying
EXECUTION PROTOCOLS:
- 🎯 Apply edits systematically
- 💾 Validate after each edit
- 📖 Document changes made
MANDATORY SEQUENCE
1. Review Edit Plan
"Applying approved edits to teach-me-testing workflow
From step-e-01, we identified: {Summarize edit plan from previous step}
Let me apply these changes systematically."
2. Apply Edits by Category
For each file to be edited:
- Load the current file
- Show the proposed changes (before/after)
- Ask: "Apply this edit? [Y/N]"
- If Y: Make the edit
- If N: Skip this edit
- Confirm edit applied successfully
3. Validate Edits
After all edits applied:
Check:
- Frontmatter still valid
- File references still correct
- Menu handling logic intact
- Step sequence maintained
"Validation:
All edits applied successfully:
- {list files modified}
Checking integrity:
- ✅ Frontmatter valid
- ✅ File references correct
- ✅ Menu logic intact
- ✅ Step sequence maintained"
4. Summary of Changes
"Edit Summary:
Files Modified: {count} {List each file with changes made}
Changes Applied: {Summarize what was changed}
Workflow Status: ✅ Edits complete, workflow intact
Next: You can run the workflow to test your changes, or run validation mode to check quality."
5. Completion
"Edit Mode Complete!
The teach-me-testing workflow has been updated.
Modified files: {List paths to modified files}
Recommended next steps:
- Run validation:
bmad run teach-me-testing -v - Test the workflow:
bmad run teach-me-testing - Make additional edits if needed"
This is the final edit step - workflow ends here.
🚨 SUCCESS METRICS
✅ Edits applied to approved files only, changes validated, workflow integrity maintained, user informed of modifications.
Master Rule: Show changes, get approval, apply edits, validate integrity.
On Complete
Run: python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete
If the resolver succeeds and returns a non-empty workflow.on_complete, execute that value as the final terminal instruction before exiting.
If the resolver fails, returns no output, or resolves an empty value, skip the hook and exit normally.