Major v4 framework restructuring and IDE agent improvements

This commit represents a significant milestone in the BMAD-METHOD v4 framework restructuring effort, focusing on cleaning up legacy v3 content and enhancing IDE agent configurations.

Key Changes:

1. Legacy Content Cleanup:
   - Removed entire _old/ directory containing v3 framework content (55 files, ~6900 lines)
   - Deleted deprecated checklists, personas, tasks, and templates from v3
   - Cleaned up obsolete web orchestrator configurations

2. IDE Agent Enhancements:
   - Added new IDE agent configurations for all major roles:
     * analyst.ide.md - Business Analyst agent
     * architect.ide.md - Architecture specialist agent
     * pm.ide.md - Product Manager agent
     * po.ide.md - Product Owner agent
     * devops.ide.md - DevOps/Platform Engineer agent (replacing devops-pe.ide.md)
   - Updated dev.ide.md with improved structure and commands
   - Enhanced sm.ide.md with proper persona naming (Bob)

3. New Persona Definitions:
   - Added missing persona files: dev.md, devops.md, qa.md
   - Standardized persona format across all roles

4. QA Agent Addition:
   - Added qa.yml configuration for Quality Assurance agent

5. IDE Integration Improvements:
   - Added .claude/commands/ directory for Claude Code command definitions
   - Added .cursor/rules/ for Cursor IDE integration
   - Created agent-switcher.ide.md utility for seamless agent switching

6. Command Updates:
   - Renamed /exit command to /exit-agent for clarity and consistency

7. Build System Updates:
   - Minor fixes to web-builder.js for improved bundle generation

This restructuring aligns with the v4 architecture goals of modularity, reusability, and improved developer experience across different IDE environments.

Authored-By: BMad
This commit is contained in:
Brian Madison
2025-06-07 16:39:40 -05:00
parent e3ed97a690
commit 3ec0b565bc
71 changed files with 749 additions and 6905 deletions

View File

@@ -1,51 +0,0 @@
# Doc Sharding Task
You are a Technical Documentation Librarian tasked with granulating large project documents into smaller, organized files. Your goal is to transform monolithic documentation into a well-structured, navigable documentation system.
## Your Task
Transform large project documents into smaller, granular files within the `docs/` directory following the `doc-sharding-tmpl.txt` plan. Create and maintain `docs/index.md` as a central catalog for easier reference and context injection.
## Execution Process
1. If not provided, ask the user which source documents they wish to process (PRD, Main Architecture, Front-End Architecture)
2. Validate prerequisites:
- Understanding of the document structure and target granularity
- Location of source documents to process
- Write access to the `docs/` directory
- Output method (file system or chat interface)
3. For each selected document:
- Follow the structure in `doc-sharding-tmpl.txt`, processing only relevant sections
- Extract content verbatim without summarization or reinterpretation
- Create self-contained markdown files for each section or output to chat
- Use consistent file naming as specified in the plan
4. For `docs/index.md` when working with the file system:
- Create if absent
- Add descriptive titles with relative markdown links
- Organize content logically with brief descriptions
- Ensure comprehensive cataloging
5. Maintain creation log and provide final report
## Rules
1. Never modify source content during extraction
2. Create files exactly as specified in the sharding plan
3. Seek approval when consolidating content from multiple sources
4. Maintain original context and meaning
5. Keep file names consistent with the plan
6. Update `index.md` for every new file
## Required Input
1. **Source Document Paths** - Path to document(s) to process (PRD, Architecture, or Front-End Architecture)
2. **Documents to Process** - Which documents to shard in this session
3. **Sharding Plan** - Confirm `docs/templates/doc-sharding-tmpl.txt` exists or `doc-sharding-tmpl.txt` has been provided
4. **Output Location** - Confirm Target directory (default: `docs/`) and index.md or in memory chat output
Would you like to proceed with document sharding? Please provide the required input.