Add quality gates, role library, and templates for team lifecycle v3

- Introduced quality gates documentation outlining scoring dimensions and per-phase criteria.
- Created a dynamic role library with definitions for core and specialist roles, including data engineer, devops engineer, ml engineer, orchestrator, performance optimizer, and security expert.
- Added templates for architecture documents, epics and stories, product briefs, and requirements PRD to standardize outputs across phases.

Author: catlog22

.claude/skills/team-coordinate/roles/coordinator/role.md

@@ -130,7 +130,7 @@ For callback/check/resume/adapt/complete: load `commands/monitor.md` and execute
    - Dependency graph: build DAG of work streams
    - Complexity scoring: count capabilities, cross-domain factor, parallel tracks
    - Role minimization: merge overlapping, absorb trivial, cap at 5
-   - **Role-spec metadata**: Generate frontmatter fields (prefix, inner_loop, subagents, message_types)
+   - **Role-spec metadata**: Generate frontmatter fields (prefix, inner_loop, additional_members, message_types)
 
 4. **Output**: Write `<session>/task-analysis.json`
 
@@ -185,10 +185,10 @@ Regardless of complexity score or role count, coordinator MUST:
 5. **Read `specs/role-spec-template.md`** for Behavioral Traits + Reference Patterns
 
 6. **For each role in task-analysis.json#roles**:
-   - Fill YAML frontmatter: role, prefix, inner_loop, subagents, message_types
+   - Fill YAML frontmatter: role, prefix, inner_loop, additional_members, message_types
    - **Compose Phase 2-4 content** (NOT copy from template):
      - Phase 2: Derive input sources and context loading steps from **task description + upstream dependencies**
-     - Phase 3: Describe **execution goal** (WHAT to achieve) from task description — do NOT prescribe specific subagent or tool
+     - Phase 3: Describe **execution goal** (WHAT to achieve) from task description — do NOT prescribe specific CLI tool or approach
      - Phase 4: Combine **Behavioral Traits** (from template) + **output_type** (from task analysis) to compose verification steps
      - Reference Patterns may guide phase structure, but task description determines specific content
    - Write generated role-spec to `<session>/role-specs/<role-name>.md`

.claude/skills/team-frontend/role-specs/analyst.md

@@ -1,7 +1,6 @@
 ---
 prefix: ANALYZE
 inner_loop: false
-additional_members: []
 message_types:
   success: analyze_ready
   error: error

.claude/skills/team-frontend/role-specs/architect.md

@@ -1,7 +1,6 @@
 ---
 prefix: ARCH
 inner_loop: false
-additional_members: []
 message_types:
   success: arch_ready
   error: error

.claude/skills/team-frontend/role-specs/developer.md

@@ -1,7 +1,6 @@
 ---
 prefix: DEV
 inner_loop: true
-additional_members: []
 message_types:
   success: dev_complete
   error: error

.claude/skills/team-frontend/role-specs/qa.md

@@ -1,7 +1,6 @@
 ---
 prefix: QA
 inner_loop: false
-additional_members: []
 message_types:
   success: qa_passed
   error: error

.claude/skills/team-issue/role-specs/explorer.md

@@ -1,7 +1,6 @@
 ---
 prefix: EXPLORE
 inner_loop: false
-additional_members: []
 message_types:
   success: context_ready
   error: error

.claude/skills/team-issue/role-specs/integrator.md

@@ -1,7 +1,6 @@
 ---
 prefix: MARSHAL
 inner_loop: false
-additional_members: []
 message_types:
   success: queue_ready
   conflict: conflict_found

.claude/skills/team-issue/role-specs/planner.md

@@ -2,7 +2,6 @@
 prefix: SOLVE
 inner_loop: false
 additional_prefixes: [SOLVE-fix]
-additional_members: []
 message_types:
   success: solution_ready
   multi: multi_solution

.claude/skills/team-lifecycle-v2/CHANGELOG.md

@@ -0,0 +1,46 @@
+# Changelog
+
+## v2.1 - Architecture Fix (2026-03-05)
+
+### Fixed
+- **Critical**: Removed subagent calls from worker role-specs
+- Workers now correctly use CLI tools instead of attempting Agent() spawn
+- Removed subagents directory (workers cannot use it)
+- Updated SKILL.md to clarify architectural constraints
+
+### Changed
+- Multi-perspective critique: Now uses parallel CLI calls
+- Codebase exploration: Now uses `ccw cli --tool gemini`
+- Document generation: Now uses `ccw cli --tool gemini --mode write`
+
+### Impact
+- No functional change for users
+- Implementation now architecturally correct
+- Workers will no longer fail with "Unknown skill: Agent"
+
+### Files Modified
+- `SKILL.md`: Replaced "Subagent Registry" with "CLI Tool Usage in Workers"
+- `role-specs/analyst.md`: Removed `subagents: [discuss]`, replaced discuss subagent call with parallel CLI calls
+- `role-specs/writer.md`: Removed `subagents: [discuss]`, replaced discuss subagent call with parallel CLI calls
+- `role-specs/reviewer.md`: Removed `subagents: [discuss]`, replaced discuss subagent call with parallel CLI calls
+- `role-specs/planner.md`: Updated complexity routing table to reference CLI exploration
+- `role-specs/architect.md`: Removed `subagents: [explore]`
+- `subagents/`: Directory removed
+
+### Technical Details
+
+**Why Workers Cannot Spawn Subagents**:
+When a worker attempts `Agent()`, it fails with "Unknown skill: Agent". Only the Coordinator (main conversation context) can spawn agents.
+
+**Worker Capabilities**:
+- ✅ Built-in tools: Read, Write, Edit, Bash, Grep, Glob
+- ✅ CLI tools: `ccw cli --tool gemini/codex/qwen`
+- ❌ Agent spawn: Cannot call `Agent()` to spawn subagents
+
+**Multi-Perspective Critique Implementation**:
+Workers now use parallel CLI calls with `run_in_background: true`:
+```bash
+Bash(`ccw cli -p "..." --tool gemini --mode analysis`, { run_in_background: true })
+Bash(`ccw cli -p "..." --tool codex --mode analysis`, { run_in_background: true })
+Bash(`ccw cli -p "..." --tool claude --mode analysis`, { run_in_background: true })
+```