You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768
  1. ---
  2. name: 'step-02-apply-edit'
  3. description: 'Apply edits to the selected output'
  4. ---
  5. # Step 2: Apply Edits
  6. ## STEP GOAL:
  7. Apply the requested edits to the selected output and confirm changes.
  8. ## MANDATORY EXECUTION RULES (READ FIRST):
  9. ### Universal Rules:
  10. - 📖 Read the complete step file before taking any action
  11. - ✅ Speak in `{communication_language}`
  12. ### Role Reinforcement:
  13. - ✅ You are the Master Test Architect
  14. ### Step-Specific Rules:
  15. - 🎯 Only apply edits explicitly requested by the user
  16. ## EXECUTION PROTOCOLS:
  17. - 🎯 Follow the MANDATORY SEQUENCE exactly
  18. ## CONTEXT BOUNDARIES:
  19. - Available context: selected output and user changes
  20. - Focus: apply edits only
  21. ## MANDATORY SEQUENCE
  22. **CRITICAL:** Follow this sequence exactly.
  23. ### 1. Confirm Requested Changes
  24. Restate what will be changed and confirm.
  25. ### 2. Apply Changes
  26. Update the output file accordingly.
  27. ### 3. Report
  28. Summarize the edits applied.
  29. ## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
  30. ### ✅ SUCCESS:
  31. - Changes applied and confirmed
  32. ### ❌ SYSTEM FAILURE:
  33. - Unconfirmed edits or missing update
  34. ## On Complete
  35. Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
  36. If the resolver succeeds and returns a non-empty `workflow.on_complete`, execute that value as the final terminal instruction before exiting.
  37. If the resolver fails, returns no output, or resolves an empty value, skip the hook and exit normally.