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-lifecycle/role-specs/analyst.md

@@ -3,7 +3,7 @@ role: analyst
 prefix: RESEARCH
 inner_loop: false
 discuss_rounds: [DISCUSS-001]
-subagents: [discuss]
+cli_tools: [discuss]
 message_types:
   success: research_ready
   progress: research_progress
@@ -76,7 +76,7 @@ Parse CLI output to build codebase context: tech_stack, architecture_patterns, c
 
 ### 4b: Inline Discuss (DISCUSS-001)
 
-Call discuss subagent with:
+Invoke multi-perspective discussion using CLI tools:
 - Artifact: `<session-folder>/spec/discovery-context.json`
 - Round: DISCUSS-001
 - Perspectives: product, risk, coverage
@@ -93,4 +93,4 @@ Handle discuss verdict per team-worker consensus handling protocol.
 | Codebase detection failed | Continue as new project |
 | Topic too vague | Report with clarification questions |
 | CLI exploration fails | Continue without codebase context |
-| Discuss subagent fails | Proceed without discuss, log warning |
+| Multi-perspective discussion fails | Proceed without discuss, log warning |

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

@@ -3,7 +3,7 @@ role: architect
 prefix: ARCH
 inner_loop: false
 discuss_rounds: []
-subagents: [explore]
+cli_tools: [explore]
 message_types:
   success: arch_ready
   concern: arch_concern

.claude/skills/team-lifecycle/role-specs/executor.md

@@ -3,7 +3,7 @@ role: executor
 prefix: IMPL
 inner_loop: true
 discuss_rounds: []
-subagents: []
+cli_tools: []
 message_types:
   success: impl_complete
   progress: impl_progress

.claude/skills/team-lifecycle/role-specs/fe-developer.md

@@ -3,7 +3,7 @@ role: fe-developer
 prefix: DEV-FE
 inner_loop: false
 discuss_rounds: []
-subagents: []
+cli_tools: []
 message_types:
   success: dev_fe_complete
   progress: dev_fe_progress

.claude/skills/team-lifecycle/role-specs/fe-qa.md

@@ -3,7 +3,7 @@ role: fe-qa
 prefix: QA-FE
 inner_loop: false
 discuss_rounds: []
-subagents: []
+cli_tools: []
 message_types:
   success: qa_fe_passed
   result: qa_fe_result

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

@@ -3,7 +3,7 @@ role: planner
 prefix: PLAN
 inner_loop: true
 discuss_rounds: []
-subagents: []
+cli_tools: [explore]
 message_types:
   success: plan_ready
   revision: plan_revision
@@ -27,8 +27,8 @@ If `<session-folder>/spec/` exists → load requirements/_index.md, architecture
 | Complexity | Criteria | Strategy |
 |------------|----------|----------|
 | Low | < 200 chars, no refactor/architecture keywords | ACE semantic search only |
-| Medium | 200-500 chars or moderate scope | 2-3 angle explore subagent |
-| High | > 500 chars, refactor/architecture, multi-module | 3-5 angle explore subagent |
+| Medium | 200-500 chars or moderate scope | 2-3 angle CLI explore |
+| High | > 500 chars, refactor/architecture, multi-module | 3-5 angle CLI explore |
 
 For each angle, use CLI exploration (cache-aware — check cache-index.json before each call):
 

.claude/skills/team-lifecycle/role-specs/reviewer.md

@@ -4,7 +4,7 @@ prefix: REVIEW
 additional_prefixes: [QUALITY, IMPROVE]
 inner_loop: false
 discuss_rounds: [DISCUSS-006]
-subagents: [discuss]
+cli_tools: [discuss]
 message_types:
   success_review: review_result
   success_quality: quality_result
@@ -73,11 +73,19 @@ message_types:
 
 ### Spec Quality Inline Discuss (DISCUSS-006)
 
-After generating readiness-report.md, call discuss subagent:
+After generating readiness-report.md, call CLI discuss tool:
 - Artifact: `<session-folder>/spec/readiness-report.md`
 - Round: DISCUSS-006
 - Perspectives: product, technical, quality, risk, coverage (all 5)
 
+```bash
+ccw cli -p "PURPOSE: Multi-perspective critique of spec readiness
+TASK: Review from product, technical, quality, risk, coverage perspectives
+ARTIFACT: @<session-folder>/spec/readiness-report.md
+MODE: analysis
+EXPECTED: JSON with perspectives[], consensus, severity, recommendations[]" --tool gemini --mode analysis
+```
+
 Handle discuss verdict per team-worker consensus handling protocol.
 
 > **Note**: DISCUSS-006 HIGH always triggers user pause (final sign-off gate), regardless of revision count.
@@ -91,4 +99,4 @@ Handle discuss verdict per team-worker consensus handling protocol.
 | Missing context | Request from coordinator |
 | Invalid mode | Abort with error |
 | Analysis failure | Retry, then fallback template |
-| Discuss subagent fails | Proceed without final discuss, log warning |
+| CLI discuss fails | Proceed without final discuss, log warning |

.claude/skills/team-lifecycle/role-specs/tester.md

@@ -3,7 +3,7 @@ role: tester
 prefix: TEST
 inner_loop: false
 discuss_rounds: []
-subagents: []
+cli_tools: []
 message_types:
   success: test_result
   fix: fix_required

.claude/skills/team-lifecycle/role-specs/writer.md

@@ -3,7 +3,7 @@ role: writer
 prefix: DRAFT
 inner_loop: true
 discuss_rounds: [DISCUSS-002, DISCUSS-003, DISCUSS-004, DISCUSS-005]
-subagents: [discuss]
+cli_tools: [discuss]
 message_types:
   success: draft_ready
   revision: draft_revision
@@ -54,7 +54,7 @@ message_types:
 | Discussion feedback | `<session-folder>/discussions/<discuss-file>` | If exists |
 | Prior decisions | context_accumulator (in-memory) | If prior tasks exist |
 
-## Phase 3: Subagent Document Generation
+## Phase 3: CLI Document Generation
 
 **Objective**: Generate document using CLI tool.
 
@@ -87,11 +87,19 @@ Parse CLI output for artifact path and summary. Document is written to disk by C
 
 ### 4b: Inline Discuss
 
-Call discuss subagent for this task's discuss round:
+Call CLI discuss tool for this task's discuss round:
 - Artifact: `<output-path>` (the generated document)
 - Round: `<DISCUSS-NNN>` from mapping table
 - Perspectives: from mapping table
 
+```bash
+ccw cli -p "PURPOSE: Multi-perspective critique of <doc-type>
+TASK: Review from <perspectives>
+ARTIFACT: @<output-path>
+MODE: analysis
+EXPECTED: JSON with perspectives[], consensus, severity, recommendations[]" --tool gemini --mode analysis
+```
+
 Handle discuss verdict per team-worker consensus handling protocol.
 
 **Report**: doc type, validation status, discuss verdict + severity, average rating, summary, output path.
@@ -101,7 +109,7 @@ Handle discuss verdict per team-worker consensus handling protocol.
 | Scenario | Resolution |
 |----------|------------|
 | CLI failure | Retry once with alternative tool. Still fails → log error, continue next task |
-| Discuss subagent fails | Skip discuss, log warning |
+| CLI discuss fails | Skip discuss, log warning |
 | Cumulative 3 task failures | SendMessage to coordinator, STOP |
 | Prior doc not found | Notify coordinator, request prerequisite |
 | Discussion contradicts prior docs | Note conflict, flag for coordinator |