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.

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475
  1. ---
  2. name: bmad-create-ux-design
  3. description: 'Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX"'
  4. ---
  5. # Create UX Design Workflow
  6. **Goal:** Create comprehensive UX design specifications through collaborative visual exploration and informed decision-making where you act as a UX facilitator working with a product stakeholder.
  7. ## Conventions
  8. - Bare paths (e.g. `steps/step-01-init.md`) resolve from the skill root.
  9. - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
  10. - `{project-root}`-prefixed paths resolve from the project working directory.
  11. - `{skill-name}` resolves to the skill directory's basename.
  12. ## WORKFLOW ARCHITECTURE
  13. This uses **micro-file architecture** for disciplined execution:
  14. - Each step is a self-contained file with embedded rules
  15. - Sequential progression with user control at each step
  16. - Document state tracked in frontmatter
  17. - Append-only document building through conversation
  18. ## On Activation
  19. ### Step 1: Resolve the Workflow Block
  20. Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`
  21. **If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
  22. 1. `{skill-root}/customize.toml` — defaults
  23. 2. `{project-root}/_bmad/custom/{skill-name}.toml` — team overrides
  24. 3. `{project-root}/_bmad/custom/{skill-name}.user.toml` — personal overrides
  25. Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
  26. ### Step 2: Execute Prepend Steps
  27. Execute each entry in `{workflow.activation_steps_prepend}` in order before proceeding.
  28. ### Step 3: Load Persistent Facts
  29. Treat every entry in `{workflow.persistent_facts}` as foundational context you carry for the rest of the workflow run. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.
  30. ### Step 4: Load Config
  31. Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
  32. - Use `{user_name}` for greeting
  33. - Use `{communication_language}` for all communications
  34. - Use `{document_output_language}` for output documents
  35. - Use `{planning_artifacts}` for output location and artifact scanning
  36. - Use `{project_knowledge}` for additional context scanning
  37. ### Step 5: Greet the User
  38. Greet `{user_name}`, speaking in `{communication_language}`.
  39. ### Step 6: Execute Append Steps
  40. Execute each entry in `{workflow.activation_steps_append}` in order.
  41. Activation is complete. Begin the workflow below.
  42. ## Paths
  43. - `default_output_file` = `{planning_artifacts}/ux-design-specification.md`
  44. ## EXECUTION
  45. - ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
  46. - ✅ YOU MUST ALWAYS WRITE all artifact and document content in `{document_output_language}`
  47. - Read fully and follow: `./steps/step-01-init.md` to begin the UX design workflow.