Vous ne pouvez pas sélectionner plus de 25 sujets Les noms de sujets doivent commencer par une lettre ou un nombre, peuvent contenir des tirets ('-') et peuvent comporter jusqu'à 35 caractères.

step-e-02-apply-edits.md 3.0KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130
  1. ---
  2. name: 'step-e-02-apply-edits'
  3. description: 'Apply modifications to the teaching workflow based on edit plan'
  4. workflowPath: '{skill-root}'
  5. ---
  6. # Edit Step 2: Apply Edits
  7. ## STEP GOAL:
  8. To apply the approved edits to the teach-me-testing workflow files while maintaining integrity and quality standards.
  9. ## MANDATORY EXECUTION RULES (READ FIRST):
  10. ### Universal Rules:
  11. - 🛑 NEVER edit without showing user the changes first
  12. - 📖 CRITICAL: Read complete step file before action
  13. - ✅ SPEAK OUTPUT In {communication_language}
  14. ### Role Reinforcement:
  15. - ✅ You are a workflow architect applying modifications
  16. - ✅ Collaborative edits with user approval
  17. ### Step-Specific Rules:
  18. - 🎯 Focus on applying approved edits only
  19. - 🚫 FORBIDDEN to make unapproved changes
  20. - 💬 Show changes before applying
  21. ## EXECUTION PROTOCOLS:
  22. - 🎯 Apply edits systematically
  23. - 💾 Validate after each edit
  24. - 📖 Document changes made
  25. ## MANDATORY SEQUENCE
  26. ### 1. Review Edit Plan
  27. "**Applying approved edits to teach-me-testing workflow**
  28. From step-e-01, we identified:
  29. {Summarize edit plan from previous step}
  30. Let me apply these changes systematically."
  31. ### 2. Apply Edits by Category
  32. **For each file to be edited:**
  33. 1. Load the current file
  34. 2. Show the proposed changes (before/after)
  35. 3. Ask: "Apply this edit? [Y/N]"
  36. 4. If Y: Make the edit
  37. 5. If N: Skip this edit
  38. 6. Confirm edit applied successfully
  39. ### 3. Validate Edits
  40. After all edits applied:
  41. **Check:**
  42. - Frontmatter still valid
  43. - File references still correct
  44. - Menu handling logic intact
  45. - Step sequence maintained
  46. "**Validation:**
  47. All edits applied successfully:
  48. - {list files modified}
  49. Checking integrity:
  50. - ✅ Frontmatter valid
  51. - ✅ File references correct
  52. - ✅ Menu logic intact
  53. - ✅ Step sequence maintained"
  54. ### 4. Summary of Changes
  55. "**Edit Summary:**
  56. **Files Modified:** {count}
  57. {List each file with changes made}
  58. **Changes Applied:**
  59. {Summarize what was changed}
  60. **Workflow Status:** ✅ Edits complete, workflow intact
  61. **Next:** You can run the workflow to test your changes, or run validation mode to check quality."
  62. ### 5. Completion
  63. "**Edit Mode Complete!**
  64. The teach-me-testing workflow has been updated.
  65. **Modified files:**
  66. {List paths to modified files}
  67. **Recommended next steps:**
  68. 1. Run validation: `bmad run teach-me-testing -v`
  69. 2. Test the workflow: `bmad run teach-me-testing`
  70. 3. Make additional edits if needed"
  71. **This is the final edit step - workflow ends here.**
  72. ---
  73. ## 🚨 SUCCESS METRICS
  74. ✅ Edits applied to approved files only, changes validated, workflow integrity maintained, user informed of modifications.
  75. **Master Rule:** Show changes, get approval, apply edits, validate integrity.
  76. ## On Complete
  77. Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
  78. If the resolver succeeds and returns a non-empty `workflow.on_complete`, execute that value as the final terminal instruction before exiting.
  79. If the resolver fails, returns no output, or resolves an empty value, skip the hook and exit normally.