Add document standards, quality gates, and templates for team lifecycle phases

- Introduced `document-standards.md` to define YAML frontmatter schema, naming conventions, and content structure for spec-generator outputs.
- Created `quality-gates.md` outlining per-phase quality gate criteria and scoring dimensions for spec-generator outputs.
- Added templates for architecture documents, epics and stories, product briefs, and requirements PRD to streamline documentation in respective phases.

.claude/skills/team-tech-debt/SKILL.md

@@ -224,7 +224,7 @@ TDSCAN-001 内部并行架构:
          ┌────────────────────────────────────────────────────┐
          │                  Scanner Worker                     │
          │                                                     │
-         │  Fan-out A: Subagent Exploration (并行 cli-explore) │
+         │  Fan-out A: CLI Exploration (parallel CLI explore)    │
          │  ┌──────────┐ ┌──────────┐ ┌──────────┐            │
          │  │structure  │ │patterns  │ │deps      │            │
          │  │角度       │ │角度      │ │角度      │             │

.claude/skills/team-tech-debt/role-specs/executor.md

@@ -9,7 +9,7 @@ message_types:
 
 # Tech Debt Executor
 
-Debt cleanup executor. Apply remediation plan actions in worktree: refactor code, update dependencies, add tests, add documentation. Batch-delegate to code-developer subagent, self-validate after each batch.
+Debt cleanup executor. Apply remediation plan actions in worktree: refactor code, update dependencies, add tests, add documentation. Batch-delegate to CLI tools, self-validate after each batch.
 
 ## Phase 2: Load Remediation Plan
 
@@ -32,14 +32,24 @@ Debt cleanup executor. Apply remediation plan actions in worktree: refactor code
 
 ## Phase 3: Execute Fixes
 
-For each batch, delegate to `code-developer` subagent (synchronous, `run_in_background: false`):
+For each batch, use CLI tool for implementation:
 
 **Worktree constraint**: ALL file operations and commands must execute within worktree path. Use `cd "<worktree-path>" && ...` prefix for all Bash commands.
 
 **Per-batch delegation**:
-- Provide batch type prompt (refactor/update-deps/add-tests/add-docs/restructure)
-- List all items with file paths, descriptions, and fix steps
-- Enforce: read files before modifying, minimal changes, backward compatibility, no new features, no suppressions
+
+```bash
+ccw cli -p "PURPOSE: Apply tech debt fixes in batch; success = all items fixed without breaking changes
+TASK: <batch-type-specific-tasks>
+MODE: write
+CONTEXT: @<worktree-path>/**/* | Memory: Remediation plan context
+EXPECTED: Code changes that fix debt items, maintain backward compatibility, pass existing tests
+CONSTRAINTS: Minimal changes only | No new features | No suppressions | Read files before modifying
+Batch type: <refactor|update-deps|add-tests|add-docs|restructure>
+Items: <list-of-items-with-file-paths-and-descriptions>" --tool gemini --mode write --cd "<worktree-path>"
+```
+
+Wait for CLI completion before proceeding to next batch.
 
 **Fix Results Tracking**:
 

.claude/skills/team-tech-debt/role-specs/scanner.md

@@ -1,7 +1,6 @@
 ---
 prefix: TDSCAN
 inner_loop: false
-subagents: []
 message_types:
   success: scan_complete
   error: error
@@ -47,8 +46,8 @@ Multi-dimension tech debt scanner. Scan codebase across 5 dimensions (code, arch
 
 | Score | Complexity | Strategy |
 |-------|------------|----------|
-| >= 4 | High | Triple Fan-out: subagent explore + CLI 5 dimensions + multi-perspective Gemini |
-| 2-3 | Medium | Dual Fan-out: subagent explore + CLI 3 dimensions |
+| >= 4 | High | Triple Fan-out: CLI explore + CLI 5 dimensions + multi-perspective Gemini |
+| 2-3 | Medium | Dual Fan-out: CLI explore + CLI 3 dimensions |
 | 0-1 | Low | Inline: ACE search + Grep |
 
 ## Phase 3: Multi-Dimension Scan
@@ -58,7 +57,7 @@ Multi-dimension tech debt scanner. Scan codebase across 5 dimensions (code, arch
 - Classify findings into dimensions
 
 **Medium/High Complexity** (Fan-out):
-- Fan-out A: Subagent exploration (structure, patterns, dependencies angles) via `cli-explore-agent`
+- Fan-out A: CLI exploration (structure, patterns, dependencies angles) via `ccw cli --tool gemini --mode analysis`
 - Fan-out B: CLI dimension analysis (parallel gemini per dimension -- code, architecture, testing, dependency, documentation)
 - Fan-out C (High only): Multi-perspective Gemini analysis (security, performance, code-quality, architecture)
 - Fan-in: Merge results, cross-deduplicate by file:line, boost severity for multi-source findings

.claude/skills/team-tech-debt/role-specs/validator.md

@@ -58,8 +58,18 @@ Execute 4-layer validation (all commands in worktree):
 - improvement_percentage = ((before - after) / before) * 100
 
 **Auto-fix attempt** (when total_regressions <= 3):
-- Spawn code-developer subagent to fix regressions in worktree
-- Constraints: fix only regressions, preserve debt cleanup changes, no suppressions
+- Use CLI tool to fix regressions in worktree:
+  ```
+  Bash({
+    command: `cd "${worktreePath}" && ccw cli -p "PURPOSE: Fix regressions found in validation
+  TASK: ${regressionDetails}
+  MODE: write
+  CONTEXT: @${modifiedFiles.join(' @')}
+  EXPECTED: Fixed regressions
+  CONSTRAINTS: Fix only regressions | Preserve debt cleanup changes | No suppressions" --tool gemini --mode write`,
+    run_in_background: false
+  })
+  ```
 - Re-run checks after fix attempt
 
 ## Phase 4: Compare & Report

.claude/skills/team-tech-debt/roles/coordinator/role.md

@@ -19,7 +19,7 @@
 ### MUST NOT
 - Execute tech debt work directly (delegate to workers)
 - Modify task outputs (workers own their deliverables)
-- Call implementation subagents directly (cli-explore-agent, code-developer, etc.)
+- Call CLI tools for analysis, exploration, or code generation
 - Modify source code or generate artifact files directly
 - Bypass worker roles to complete delegated work
 - Skip dependency validation when creating task chains
@@ -100,7 +100,7 @@ For callback/check/resume/complete: load `commands/monitor.md` and execute match
 | `Task` | Tool | Phase 4 | Worker spawning |
 | `AskUserQuestion` | Tool | Phase 1 | Requirement clarification |
 
-> Coordinator does not directly use CLI analysis tools or implementation subagents
+> Coordinator does not directly use CLI analysis tools or CLI code generation
 
 ---
 

.claude/skills/team-tech-debt/specs/team-config.json

@@ -23,8 +23,7 @@
       "message_types_sent": ["scan_complete", "debt_items_found", "error"],
       "message_types_received": [],
       "commands": ["scan-debt"],
-      "cli_tools": ["gemini"],
-      "subagents": ["cli-explore-agent"]
+      "cli_tools": ["gemini"]
     },
     "assessor": {
       "name": "assessor",
@@ -44,8 +43,7 @@
       "message_types_sent": ["plan_ready", "plan_revision", "error"],
       "message_types_received": [],
       "commands": ["create-plan"],
-      "cli_tools": ["gemini"],
-      "subagents": ["cli-explore-agent"]
+      "cli_tools": ["gemini"]
     },
     "executor": {
       "name": "executor",
@@ -55,7 +53,7 @@
       "message_types_sent": ["fix_complete", "fix_progress", "error"],
       "message_types_received": [],
       "commands": ["remediate"],
-      "subagents": ["code-developer"]
+      "cli_tools": [{"tool": "gemini", "mode": "write"}]
     },
     "validator": {
       "name": "validator",
@@ -65,8 +63,7 @@
       "message_types_sent": ["validation_complete", "regression_found", "error"],
       "message_types_received": [],
       "commands": ["verify"],
-      "subagents": ["code-developer"],
-      "cli_tools": ["gemini"]
+      "cli_tools": [{"tool": "gemini", "mode": "write"}]
     }
   },