docs: Enhance Main Claude coordination rules with new capabilities

Updated AGENT_COORDINATION_RULES.md to document Main Claude's enhanced role:

New Capabilities Section:
- Automatic skill invocation (frontend-design for ANY UI change)
- Sequential Thinking recognition (when to use ST MCP)
- Dual checkpoint system (git + database via /checkpoint)
- Skills vs Agents distinction (when to use each)

Main Claude Responsibilities Enhanced:
- Auto-invoke frontend-design skill when UI affected
- Recognize when Sequential Thinking is appropriate
- Execute dual checkpoints (git + database)
- Coordinate agents and skills intelligently

Quick Reference Updated:
- Added UI validation (Frontend Design Skill)
- Added complex problem analysis (Sequential Thinking MCP)
- Added dual checkpoints (/checkpoint command)
- Added skill invocation (Main Claude)

Summary Section Added:
- Orchestra conductor metaphor for Main Claude's role
- Clear list of what Main Claude does NOT do
- Clear list of what Main Claude DOES automatically
- Comprehensive coordinator responsibilities

Files: .claude/AGENT_COORDINATION_RULES.md (+129 lines)

Decision Rationale:
Main Claude needed comprehensive documentation of enhanced
capabilities added today. The coordination rules now clearly
define automatic skill invocation triggers, Sequential Thinking
usage patterns, and dual checkpoint workflow.

Total: 130 lines added documenting Main Claude's intelligent
coordination capabilities.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-01-17 16:31:45 -07:00
parent 75ce1c2fd5
commit 1ae2562626

View File

@@ -233,6 +233,9 @@ curl ... -d '{"context_type": "session_summary", ...}'
- ✅ Launch appropriate agents
- ✅ Synthesize agent results for user
- ✅ Plan and design solutions
- ✅ **Automatically invoke skills when triggered** (NEW)
- ✅ **Recognize when Sequential Thinking is needed** (NEW)
- ✅ **Execute dual checkpoints (git + database)** (NEW)
**Main Claude Does NOT:**
- ❌ Query database directly
@@ -240,6 +243,101 @@ curl ... -d '{"context_type": "session_summary", ...}'
- ❌ Execute code (unless simple demonstration)
- ❌ Run tests (use Testing Agent)
- ❌ Commit to git (use Gitea Agent)
- ❌ Review code (use Code Review Agent)
- ❌ Write production code (use Coding Agent)
---
## New Capabilities (Added 2026-01-17)
### 1. Automatic Skill Invocation
**Main Claude automatically invokes skills when triggered by specific actions:**
**Frontend Design Skill:**
- **Trigger:** ANY action that affects a UI element
- **When:** After modifying HTML/CSS/JSX, styling, layouts, components
- **Purpose:** Validate visual correctness, functionality, UX, accessibility
- **Workflow:**
```
User: "Add a submit button"
Main Claude: [Writes button code]
Main Claude: [AUTO-INVOKE frontend-design skill]
Frontend Skill: [Validates appearance, behavior, accessibility]
Frontend Skill: [Returns PASS/WARNING/ERROR]
Main Claude: [Proceeds or fixes based on validation]
```
**Rule:** If the change appears in a browser, invoke frontend-design skill to validate it.
### 2. Sequential Thinking Recognition
**Main Claude recognizes when agents should use Sequential Thinking MCP:**
**For Code Review Agent:**
- Knows to use ST when code rejected 2+ times
- Knows to use ST when 3+ critical issues found
- Knows to use ST for complex architectural decisions
- Doesn't use ST for simple fixes (wastes tokens)
**For Other Complex Tasks:**
- Multi-step debugging with unclear root cause
- Architectural trade-off decisions
- Complex problem-solving where approach might change
- Investigation tasks where each finding affects next step
**Rule:** Use ST for genuinely complex, ambiguous problems where structured reasoning adds value.
### 3. Dual Checkpoint System
**Main Claude executes dual checkpoints via /checkpoint command:**
**Part 1: Git Checkpoint**
- Stages all changes (git add -A)
- Creates detailed commit message
- Follows existing commit conventions
- Includes co-author attribution
**Part 2: Database Context**
- Saves session summary to ClaudeTools API
- Includes git metadata (commit, branch, files)
- Tags for searchability
- Relevance score 8.0 (important milestone)
**Workflow:**
```
User: /checkpoint
Main Claude: [Analyzes changes]
Main Claude: [Creates git commit]
Main Claude: [Saves context to database via API/script]
Main Claude: [Verifies both succeeded]
Main Claude: [Reports to user]
```
**Benefits:**
- Git: Code versioning and rollback
- Database: Cross-machine context recall
- Together: Complete project memory
### 4. Skills vs Agents
**Main Claude understands the difference:**
**Skills** (invoked via Skill tool):
- Frontend design/validation
- User-invocable with `/skill-name`
- Specialized capabilities
- Return enhanced output
**Agents** (invoked via Task tool):
- Database operations
- Code writing
- Testing
- Code review
- Git operations
- Backup/restore
**Rule:** Skills are for specialized enhancements (frontend, design patterns). Agents are for core operations (database, coding, testing).
---
@@ -255,18 +353,48 @@ curl ... -d '{"context_type": "session_summary", ...}'
| Review code | Code Review Agent |
| Git operations | Gitea Agent |
| Backups | Backup Agent |
| **UI validation** | **Frontend Design Skill (auto-invoked)** |
| **Complex problem analysis** | **Sequential Thinking MCP** |
| **Dual checkpoints** | **/checkpoint command (Main Claude)** |
| **User interaction** | **Main Claude** |
| **Coordination** | **Main Claude** |
| **Decision making** | **Main Claude** |
| **Skill invocation** | **Main Claude** |
---
**Remember: Main Claude = Coordinator, not Executor**
**When in doubt, use an agent!**
**When in doubt, use an agent or skill!**
---
## Summary of Main Claude's Role
**Main Claude is the conductor of an orchestra:**
- Receives user requests
- Decides which agents/skills to invoke
- Coordinates workflow between agents
- Automatically triggers skills when appropriate
- Synthesizes results for user
- Maintains conversation context
**Main Claude does NOT:**
- Execute database operations directly
- Write production code (delegates to Coding Agent)
- Run tests directly (delegates to Testing Agent)
- Review code directly (delegates to Code Review Agent)
- Perform git operations directly (delegates to Gitea Agent)
**Main Claude DOES automatically:**
- Invoke frontend-design skill for ANY UI change
- Recognize when Sequential Thinking is appropriate
- Execute dual checkpoints (git + database) via /checkpoint
- Coordinate agents and skills intelligently
---
**Created:** 2026-01-17
**Last Updated:** 2026-01-17 (added new capabilities)
**Purpose:** Ensure proper agent-based architecture
**Status:** Mandatory guideline for all future operations