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.

step-05-generate-report.md 3.1KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116
  1. ---
  2. name: 'step-05-generate-report'
  3. description: 'Create NFR report and validation summary'
  4. outputFile: '{test_artifacts}/nfr-assessment.md'
  5. ---
  6. # Step 5: Generate Report & Validate
  7. ## STEP GOAL
  8. Produce the NFR evidence audit report and validate completeness.
  9. ## MANDATORY EXECUTION RULES
  10. - 📖 Read the entire step file before acting
  11. - ✅ Speak in `{communication_language}`
  12. ---
  13. ## EXECUTION PROTOCOLS:
  14. - 🎯 Follow the MANDATORY SEQUENCE exactly
  15. - 💾 Record outputs before proceeding
  16. - 📖 Load the next step only when instructed
  17. ## CONTEXT BOUNDARIES:
  18. - Available context: config, loaded artifacts, and knowledge fragments
  19. - Focus: this step's goal only
  20. - Limits: do not execute future steps
  21. - Dependencies: prior steps' outputs (if any)
  22. ## MANDATORY SEQUENCE
  23. **CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
  24. ## 1. Report Generation
  25. Use `nfr-report-template.md` to produce `{outputFile}` containing:
  26. - Category results (PASS/CONCERNS/FAIL)
  27. - Evidence summary
  28. - Remediation actions
  29. - Gate-ready YAML snippet (if applicable)
  30. ---
  31. ## 2. Polish Output
  32. Before finalizing, review the complete output document for quality:
  33. 1. **Remove duplication**: Progressive-append workflow may have created repeated sections — consolidate
  34. 2. **Verify consistency**: Ensure terminology, risk scores, and references are consistent throughout
  35. 3. **Check completeness**: All template sections should be populated or explicitly marked N/A
  36. 4. **Format cleanup**: Ensure markdown formatting is clean (tables aligned, headers consistent, no orphaned references)
  37. ---
  38. ## 3. Validation
  39. Validate against `checklist.md` and fix gaps.
  40. - [ ] CLI sessions cleaned up (no orphaned browsers)
  41. ---
  42. ## 4. Save Progress
  43. **Save this step's accumulated work to `{outputFile}`.**
  44. - **If `{outputFile}` does not exist** (first save), create it using the workflow template (if available) with YAML frontmatter:
  45. ```yaml
  46. ---
  47. stepsCompleted: ['step-05-generate-report']
  48. lastStep: 'step-05-generate-report'
  49. lastSaved: '{date}'
  50. ---
  51. ```
  52. Then write this step's output below the frontmatter.
  53. - **If `{outputFile}` already exists**, update:
  54. - Add `'step-05-generate-report'` to `stepsCompleted` array (only if not already present)
  55. - Set `lastStep: 'step-05-generate-report'`
  56. - Set `lastSaved: '{date}'`
  57. - Append this step's output to the appropriate section of the document.
  58. ---
  59. ## 5. Completion Summary
  60. Report:
  61. - Overall NFR status
  62. - Critical blockers or waivers needed
  63. - Next recommended workflow (`trace` or release gate)
  64. ## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
  65. ### ✅ SUCCESS:
  66. - Step completed in full with required outputs
  67. ### ❌ SYSTEM FAILURE:
  68. - Skipped sequence steps or missing outputs
  69. **Master Rule:** Skipping steps is FORBIDDEN.
  70. ## On Complete
  71. Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
  72. If the resolver succeeds and returns a non-empty `workflow.on_complete`, execute that value as the final terminal instruction before exiting.
  73. If the resolver fails, returns no output, or resolves an empty value, skip the hook and exit normally.