refactor: Major v6 epic creation improvements and documentation overhaul

## Key Changes

### 1. Epic Creation Workflow Enhancements
- Added user-value focused epic structure principles (NO technical layer breakdown)
- Implemented multi-mode detection: CONTINUE, REPLACE, or UPDATE existing epics
- Added comprehensive anti-pattern examples showing wrong vs right epic breakdown
- Epics now created AFTER architecture for technically-informed story breakdown
- Added checkpoint protocol for interactive workflow progression

### 2. Removed Deprecated Solutioning Gate Check
- Deleted entire solutioning-gate-check workflow (682 lines)
- Replaced by new implementation-readiness workflow
- Cleaner separation of concerns in solutioning phase

### 3. PRD Template Simplification
- Removed hardcoded "Implementation Planning", "References", and "Next Steps" sections
- PRD now focuses purely on requirements, not workflow orchestration
- Epics/stories created as separate step after architecture

### 4. Documentation Overhaul (15+ docs updated)
- Updated quick-start guide with v6 workflow sequence
- Clarified that epics are created AFTER architecture, not during PRD
- Updated solutioning docs to reflect implementation-readiness pattern
- Improved agents-guide, brownfield-guide, enterprise docs
- Enhanced glossary, FAQ, and workflow reference documentation

### 5. Workflow Path Adjustments
- All 4 paths updated (enterprise/method × brownfield/greenfield)
- Version bumps across BMGD, BMM, and CIS workflow YAMLs
- Minor instruction file updates for consistency

### Files Changed
- 65 files total: 468 insertions, 978 deletions (net reduction of 510 lines)
- 4 files deleted (entire solutioning-gate-check workflow)
- 1 new directory added (implementation-readiness placeholder)
This commit is contained in:
Brian Madison
2025-11-16 00:23:47 -06:00
parent 5980e41a28
commit 6f7e9f0653
65 changed files with 562 additions and 352 deletions

View File

@@ -3,6 +3,7 @@
<critical>Communicate all responses in {communication_language}</critical>
<critical>This is a meta-workflow that orchestrates the CIS brainstorming workflow with game-specific context and additional game design techniques</critical>
<critical>⚠️ ABSOLUTELY NO TIME ESTIMATES - NEVER mention hours, days, weeks, months, or ANY time-based predictions. AI has fundamentally changed development speed - what once took teams weeks/months can now be done by one person in hours. DO NOT give ANY time estimates whatsoever.</critical>
<critical>⚠️ CHECKPOINT PROTOCOL: After EVERY <template-output> tag, you MUST follow workflow.xml substep 2c: SAVE content to file immediately → SHOW checkpoint separator (━━━━━━━━━━━━━━━━━━━━━━━) → DISPLAY generated content → PRESENT options [a]Advanced Elicitation/[c]Continue/[p]Party-Mode/[y]YOLO → WAIT for user response. Never batch saves or skip checkpoints.</critical>
<workflow>

View File

@@ -7,6 +7,7 @@
<critical>⚠️ ABSOLUTELY NO TIME ESTIMATES - NEVER mention hours, days, weeks, months, or ANY time-based predictions. AI has fundamentally changed development speed - what once took teams weeks/months can now be done by one person in hours. DO NOT give ANY time estimates whatsoever.</critical>
<critical>DOCUMENT OUTPUT: Concise, professional, game-design focused. Use tables/lists over prose. User skill level ({user_skill_level}) affects conversation style ONLY, not document content.</critical>
<critical>⚠️ CHECKPOINT PROTOCOL: After EVERY <template-output> tag, you MUST follow workflow.xml substep 2c: SAVE content to file immediately → SHOW checkpoint separator (━━━━━━━━━━━━━━━━━━━━━━━) → DISPLAY generated content → PRESENT options [a]Advanced Elicitation/[c]Continue/[p]Party-Mode/[y]YOLO → WAIT for user response. Never batch saves or skip checkpoints.</critical>
<workflow>

View File

@@ -13,6 +13,7 @@
<critical>If users mention technical details, append to technical_preferences with timestamp</critical>
<critical>DOCUMENT OUTPUT: Concise, clear, actionable game design specs. Use tables/lists over prose. User skill level ({user_skill_level}) affects conversation style ONLY, not document content.</critical>
<critical>⚠️ CHECKPOINT PROTOCOL: After EVERY <template-output> tag, you MUST follow workflow.xml substep 2c: SAVE content to file immediately → SHOW checkpoint separator (━━━━━━━━━━━━━━━━━━━━━━━) → DISPLAY generated content → PRESENT options [a]Advanced Elicitation/[c]Continue/[p]Party-Mode/[y]YOLO → WAIT for user response. Never batch saves or skip checkpoints.</critical>
## Input Document Discovery
@@ -26,7 +27,7 @@ This workflow requires: game brief, and may reference market research or brownfi
- Read `index.md` to understand the document structure
- Read ALL section files listed in the index
- Treat the combined content as if it were a single document
4. **Brownfield projects**: The `document-project` workflow always creates `{output_folder}/docs/index.md`
4. **Brownfield projects**: The `document-project` workflow always creates `{output_folder}/index.md`
**Priority**: If both whole and sharded versions exist, use the whole document.

View File

@@ -41,7 +41,7 @@ input_file_patterns:
document_project:
description: "Brownfield project documentation (optional)"
sharded: "{output_folder}/docs/index.md"
sharded: "{output_folder}/index.md"
load_strategy: "INDEX_GUIDED"
standalone: true

View File

@@ -9,6 +9,7 @@
<critical>Uses narrative_template for output</critical>
<critical>If users mention gameplay mechanics, note them but keep focus on narrative</critical>
<critical>Facilitate good brainstorming techniques throughout with the user, pushing them to come up with much of the narrative you will help weave together. The goal is for the user to feel that they crafted the narrative and story arc unless they push you to do it all or indicate YOLO</critical>
<critical>⚠️ CHECKPOINT PROTOCOL: After EVERY <template-output> tag, you MUST follow workflow.xml substep 2c: SAVE content to file immediately → SHOW checkpoint separator (━━━━━━━━━━━━━━━━━━━━━━━) → DISPLAY generated content → PRESENT options [a]Advanced Elicitation/[c]Continue/[p]Party-Mode/[y]YOLO → WAIT for user response. Never batch saves or skip checkpoints.</critical>
<step n="0" goal="Check for workflow status" tag="workflow-status">
<action>Check if {output_folder}/bmm-workflow-status.yaml exists</action>

View File

@@ -2,7 +2,7 @@
**Purpose**: Validate the architecture document itself is complete, implementable, and provides clear guidance for AI agents.
**Note**: This checklist validates the ARCHITECTURE DOCUMENT only. For cross-workflow validation (PRD → Architecture → Stories alignment), use the solutioning-gate-check workflow.
**Note**: This checklist validates the ARCHITECTURE DOCUMENT only. For cross-workflow validation (PRD → Architecture → Stories alignment), use the implementation-readiness workflow.
---
@@ -233,8 +233,8 @@
---
**Next Step**: Run the **solutioning-gate-check** workflow to validate alignment between PRD, Architecture, and Stories before beginning implementation.
**Next Step**: Run the **implementation-readiness** workflow to validate alignment between PRD, Architecture, and Stories before beginning implementation.
---
_This checklist validates architecture document quality only. Use solutioning-gate-check for comprehensive readiness validation._
_This checklist validates architecture document quality only. Use implementation-readiness for comprehensive readiness validation._

View File

@@ -12,6 +12,7 @@
<critical>Input documents specified in workflow.yaml input_file_patterns - workflow engine handles fuzzy matching, whole vs sharded document discovery automatically</critical>
<critical>ELICITATION POINTS: After completing each major architectural decision area (identified by template-output tags for decision_record, project_structure, novel_pattern_designs, implementation_patterns, and architecture_document), invoke advanced elicitation to refine decisions before proceeding</critical>
<critical>⚠️ ABSOLUTELY NO TIME ESTIMATES - NEVER mention hours, days, weeks, months, or ANY time-based predictions. AI has fundamentally changed development speed - what once took teams weeks/months can now be done by one person in hours. DO NOT give ANY time estimates whatsoever.</critical>
<critical>⚠️ CHECKPOINT PROTOCOL: After EVERY <template-output> tag, you MUST follow workflow.xml substep 2c: SAVE content to file immediately → SHOW checkpoint separator (━━━━━━━━━━━━━━━━━━━━━━━) → DISPLAY generated content → PRESENT options [a]Advanced Elicitation/[c]Continue/[p]Party-Mode/[y]YOLO → WAIT for user response. Never batch saves or skip checkpoints.</critical>
<step n="0" goal="Validate workflow readiness" tag="workflow-status">
<action>Check if {output_folder}/bmm-workflow-status.yaml exists</action>

View File

@@ -35,7 +35,7 @@ input_file_patterns:
document_project:
description: "Brownfield project documentation (optional)"
sharded: "{output_folder}/docs/index.md"
sharded: "{output_folder}/index.md"
load_strategy: "INDEX_GUIDED"
# Module path and component files

View File

@@ -54,7 +54,7 @@ input_file_patterns:
load_strategy: "SELECTIVE_LOAD"
document_project:
description: "Brownfield project documentation (optional)"
sharded: "{output_folder}/docs/index.md"
sharded: "{output_folder}/index.md"
load_strategy: "INDEX_GUIDED"
standalone: true

View File

@@ -43,7 +43,7 @@ input_file_patterns:
load_strategy: "FULL_LOAD"
document_project:
description: "Brownfield project documentation (optional)"
sharded: "{output_folder}/docs/index.md"
sharded: "{output_folder}/index.md"
load_strategy: "INDEX_GUIDED"
installed_path: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/correct-course"

View File

@@ -45,7 +45,7 @@ input_file_patterns:
load_strategy: "SELECTIVE_LOAD"
document_project:
description: "Brownfield project documentation (optional)"
sharded: "{output_folder}/docs/index.md"
sharded: "{output_folder}/index.md"
load_strategy: "INDEX_GUIDED"
# Workflow components

View File

@@ -51,7 +51,7 @@ input_file_patterns:
load_strategy: "SELECTIVE_LOAD"
document_project:
description: "Brownfield project documentation (optional)"
sharded: "{output_folder}/docs/index.md"
sharded: "{output_folder}/index.md"
load_strategy: "INDEX_GUIDED"
# Output configuration