Refactor Chinese documentation for team skills and commands

- Removed outdated table of contents from commands-skills.md - Updated skills overview in claude-collaboration.md with new skill names and descriptions - Enhanced clarity and structure of skills details, including roles and pipelines - Added new team skills: team-arch-opt, team-perf-opt, team-brainstorm, team-frontend, team-uidesign, team-issue, team-iterdev, team-quality-assurance, team-roadmap-dev, team-tech-debt, team-ultra-analyze - Improved user command section for better usability - Streamlined best practices for team skills usage
2026-03-03 15:43:11 +08:00 · 2026-03-02 22:49:52 +08:00
parent 99d6438303
commit 1bf9006d65
13 changed files with 1872 additions and 1173 deletions
--- a/docs/skills/claude-collaboration.md
+++ b/docs/skills/claude-collaboration.md
@@ -1,11 +1,6 @@
---
-适用CLI: claude
-分类: team
---
-
 # Claude Skills - Team Collaboration

-## One-Liner
+## One-Line Positioning

 **Team Collaboration Skills is a multi-role collaborative work orchestration system** — Through coordinator, worker roles, and message bus, it enables parallel processing and state synchronization for complex tasks.

@@ -13,32 +8,83 @@

 | Pain Point | Current State | Claude Code Workflow Solution |
 |------------|---------------|----------------------|
-| **Single model limitation** | Can only call one AI model | Multi-role parallel collaboration, leveraging各自专长 |
+| **Single model limitation** | Can only call one AI model | Multi-role parallel collaboration, leveraging respective strengths |
 | **Chaotic task orchestration** | Manual task dependency and state management | Automatic task discovery, dependency resolution, pipeline orchestration |
 | **Fragmented collaboration** | Team members work independently | Unified message bus, shared state, progress sync |
 | **Resource waste** | Repeated context loading | Wisdom accumulation, exploration cache, artifact reuse |

-## Skills List
+---

-| Skill | Function | Trigger |
-|-------|----------|---------|
-| `team-coordinate` | Universal team coordinator (dynamic role generation) | `/team-coordinate` |
-| `team-lifecycle` | Full lifecycle team (spec→impl→test→review) | `/team-lifecycle` |
-| `team-planex` | Plan-execute pipeline (plan while executing) | `/team-planex` |
-| `team-review` | Code review team (scan→review→fix) | `/team-review` |
-| `team-testing` | Testing team (strategy→generate→execute→analyze) | `/team-testing` |
+## Skills Overview
+
+| Skill | Function | Use Case |
+| --- | --- | --- |
+| `team-coordinate-v2` | Universal team coordinator (dynamic role generation) | Any complex task |
+| `team-lifecycle-v5` | Full lifecycle team (spec→impl→test) | Complete feature development |
+| `team-planex` | Plan-execute pipeline | Issue batch processing |
+| `team-review` | Code review team | Code review, vulnerability scanning |
+| `team-testing` | Testing team | Test coverage, test case generation |
+| `team-arch-opt` | Architecture optimization team | Refactoring, architecture analysis |
+| `team-perf-opt` | Performance optimization team | Performance tuning, bottleneck analysis |
+| `team-brainstorm` | Brainstorming team | Multi-angle analysis, idea generation |
+| `team-frontend` | Frontend development team | UI development, design system |
+| `team-uidesign` | UI design team | Design system, component specs |
+| `team-issue` | Issue processing team | Issue analysis, implementation |
+| `team-iterdev` | Iterative development team | Incremental delivery, agile development |
+| `team-quality-assurance` | Quality assurance team | Quality scanning, defect management |
+| `team-roadmap-dev` | Roadmap development team | Phased development, milestones |
+| `team-tech-debt` | Tech debt team | Debt cleanup, code governance |
+| `team-ultra-analyze` | Deep analysis team | Complex problem analysis, collaborative exploration |
+| `team-executor-v2` | Lightweight executor | Session resume, pure execution |
+
+---
+
+## Core Architecture
+
+All Team Skills share a unified **team-worker agent architecture**:
+
+```
+┌──────────────────────────────────────────────────────────┐
+│  Skill(skill="team-xxx", args="task description")         │
+└────────────────────────┬─────────────────────────────────┘
+                         │ Role Router
+              ┌──── --role present? ────┐
+              │ NO                      │ YES
+              ↓                         ↓
+       Orchestration Mode         Role Dispatch
+       (auto → coordinator)      (route to role.md)
+              │
+    ┌─────────┴─────────┬───────────────┬──────────────┐
+    ↓                   ↓               ↓              ↓
+┌────────┐         ┌────────┐      ┌────────┐     ┌────────┐
+│ coord  │         │worker 1│      │worker 2│     │worker N│
+│(orchestrate)│    │(execute)│     │(execute)│    │(execute)│
+└────────┘         └────────┘      └────────┘     └────────┘
+    │                   │               │              │
+    └───────────────────┴───────────────┴──────────────┘
+                         │
+              Message Bus (message bus)
+```
+
+**Core Components**:
+- **Coordinator**: Built-in orchestrator for task analysis, dispatch, monitoring
+- **Team-Worker Agent**: Unified agent, loads role-spec to execute role logic
+- **Role Router**: `--role=xxx` parameter routes to role execution
+- **Message Bus**: Inter-team member communication protocol
+- **Shared Memory**: Cross-task knowledge accumulation (Wisdom)
+
+---

 ## Skills Details

-### team-coordinate
+### team-coordinate-v2

 **One-Liner**: Universal team coordinator — Dynamically generates roles and orchestrates execution based on task analysis

 **Trigger**:
-```
-/team-coordinate <task-description>
-/team-coordinate --role=coordinator <task>
-/team-coordinate --role=<worker> --session=<path>
+```bash
+team-coordinate <task-description>
+team-coordinate --role=coordinator <task>
 ```

 **Features**:
@@ -47,17 +93,6 @@
 - Fast-Advance mechanism skips coordinator to directly spawn successor tasks
 - Wisdom accumulates cross-task knowledge

-**Role Registry**:
-| Role | File | Task Prefix | Type |
-|------|------|-------------|------|
-| coordinator | roles/coordinator/role.md | (none) | orchestrator |
-| (dynamic) | `<session>/roles/<role>.md` | (dynamic) | worker |
-
-**Pipeline**:
-```
-Task Analysis → Generate Roles → Initialize Session → Create Task Chain → Spawn First Batch Workers → Loop Progress → Completion Report
-```
-
 **Session Directory**:
 ```
 .workflow/.team/TC-<slug>-<date>/
@@ -66,20 +101,18 @@ Task Analysis → Generate Roles → Initialize Session → Create Task Chain
 ├── roles/                      # Dynamic role definitions
 ├── artifacts/                  # All MD deliverables
 ├── wisdom/                     # Cross-task knowledge
-├── explorations/               # Shared exploration cache
-├── discussions/                # Inline discussion records
 └── .msg/                       # Team message bus logs
 ```

 ---

-### team-lifecycle
+### team-lifecycle-v5

 **One-Liner**: Full lifecycle team — Complete pipeline from specification to implementation to testing to review

 **Trigger**:
-```
-/team-lifecycle <task-description>
+```bash
+team-lifecycle <task-description>
 ```

 **Features**:
@@ -97,164 +130,67 @@ Task Analysis → Generate Roles → Initialize Session → Create Task Chain
 | executor | role-specs/executor.md | IMPL-* | true |
 | tester | role-specs/tester.md | TEST-* | false |
 | reviewer | role-specs/reviewer.md | REVIEW-* | false |
-| architect | role-specs/architect.md | ARCH-* | false |
-| fe-developer | role-specs/fe-developer.md | DEV-FE-* | false |
-| fe-qa | role-specs/fe-qa.md | QA-FE-* | false |

 **Pipeline Definitions**:
 ```
-Specification Pipeline (6 tasks):
-  RESEARCH-001 → DRAFT-001 → DRAFT-002 → DRAFT-003 → DRAFT-004 → QUALITY-001
-
-Implementation Pipeline (4 tasks):
-  PLAN-001 → IMPL-001 → TEST-001 + REVIEW-001
-
-Full Lifecycle (10 tasks):
-  [Spec Pipeline] → PLAN-001 → IMPL-001 → TEST-001 + REVIEW-001
-
-Frontend Pipeline:
-  PLAN-001 → DEV-FE-001 → QA-FE-001 (GC loop, max 2 rounds)
+Specification Pipeline:  RESEARCH → DRAFT → QUALITY
+Implementation Pipeline: PLAN → IMPL → TEST + REVIEW
+Full Lifecycle:          [Spec Pipeline] → [Impl Pipeline]
 ```

-**Quality Gate** (after QUALITY-001 completion):
-```
-═════════════════════════════════════════
-SPEC PHASE COMPLETE
-Quality Gate: <PASS|REVIEW|FAIL> (<score>%)
-
-Dimension Scores:
-  Completeness:  <bar> <n>%
-  Consistency:   <bar> <n>%
-  Traceability:  <bar> <n>%
-  Depth:         <bar> <n>%
-  Coverage:      <bar> <n>%
-
-Available Actions:
-  resume              -> Proceed to implementation
-  improve             -> Auto-improve weakest dimension
-  improve <dimension> -> Improve specific dimension
-  revise <TASK-ID>    -> Revise specific document
-  recheck             -> Re-run quality check
-  feedback <text>     -> Inject feedback, create revision
-═════════════════════════════════════════
-```
-
-**User Commands** (wake paused coordinator):
-| Command | Action |
-|---------|--------|
-| `check` / `status` | Output execution status graph, no progress |
-| `resume` / `continue` | Check worker status, advance next step |
-| `revise <TASK-ID> [feedback]` | Create revision task + cascade downstream |
-| `feedback <text>` | Analyze feedback impact, create targeted revision chain |
-| `recheck` | Re-run QUALITY-001 quality check |
-| `improve [dimension]` | Auto-improve weakest dimension in readiness-report |
-
 ---

 ### team-planex

-**One-Liner**: Plan-and-execute team — Planner and executor work in parallel through per-issue beat pipeline
+**One-Liner**: Plan-and-execute team — Per-issue beat pipeline

 **Trigger**:
-```
-/team-planex <task-description>
-/team-planex --role=planner <input>
-/team-planex --role=executor --input <solution-file>
+```bash
+team-planex <task-description>
+team-planex --role=planner <input>
+team-planex --role=executor --input <solution-file>
 ```

 **Features**:
 - 2-member team (planner + executor), planner serves as lead role
- Per-issue beat: planner creates EXEC-* task immediately after completing each issue's solution
+- Per-issue beat: planner creates EXEC-* task immediately after completing each issue
 - Solution written to intermediate artifact file, executor loads from file
- Supports multiple execution backends (agent/codex/gemini)

-**Role Registry**:
-| Role | File | Task Prefix | Type |
-|------|------|-------------|------|
-| planner | roles/planner.md | PLAN-* | pipeline (lead) |
-| executor | roles/executor.md | EXEC-* | pipeline |
-
-**Input Types**:
-| Input Type | Format | Example |
-|------------|--------|---------|
-| Issue IDs | Direct ID input | `--role=planner ISS-20260215-001 ISS-20260215-002` |
-| Requirement text | `--text '...'` | `--role=planner --text 'Implement user authentication module'` |
-| Plan file | `--plan path` | `--role=planner --plan plan/2026-02-15-auth.md` |
-
-**Wave Pipeline** (per-issue beat):
+**Wave Pipeline**:
 ```
-Issue 1:  planner plans solution → write artifact → conflict check → create EXEC-* → issue_ready
-                ↓ (executor starts immediately)
-Issue 2:  planner plans solution → write artifact → conflict check → create EXEC-* → issue_ready
-                ↓ (executor consumes in parallel)
-Issue N:  ...
-Final:    planner sends all_planned → executor completes remaining EXEC-* → finish
+Issue 1:  planner plans → write artifact → create EXEC-* → executor executes
+Issue 2:  planner plans → write artifact → create EXEC-* → executor parallel consume
+Final:    planner sends all_planned → executor completes remaining → finish
 ```

-**Execution Method Selection**:
-| Executor | Backend | Use Case |
-|----------|---------|----------|
-| `agent` | code-developer subagent | Simple tasks, synchronous execution |
-| `codex` | `ccw cli --tool codex --mode write` | Complex tasks, background execution |
-| `gemini` | `ccw cli --tool gemini --mode write` | Analysis tasks, background execution |
-
-**User Commands**:
-| Command | Action |
-|---------|--------|
-| `check` / `status` | Output execution status graph, no progress |
-| `resume` / `continue` | Check worker status, advance next step |
-| `add <issue-ids or --text '...' or --plan path>` | Append new tasks to planner queue |
-
 ---

 ### team-review

-**One-Liner**: Code review team — Unified code scanning, vulnerability review, optimization suggestions, and auto-fix
+**One-Liner**: Code review team — Unified code scanning, vulnerability review, auto-fix

 **Trigger**:
+```bash
+team-review <target-path>
+team-review --full <target-path>      # scan + review + fix
+team-review --fix <review-files>      # fix only
+team-review -q <target-path>          # quick scan only
 ```
-/team-review <target-path>
-/team-review --full <target-path>      # scan + review + fix
-/team-review --fix <review-files>      # fix only
-/team-review -q <target-path>          # quick scan only
-```
-
-**Features**:
- 4-role team (coordinator, scanner, reviewer, fixer)
- Multi-dimensional review: security, correctness, performance, maintainability
- Auto-fix loop (review → fix → verify)

 **Role Registry**:
-| Role | File | Task Prefix | Type |
-|------|------|-------------|------|
-| coordinator | roles/coordinator/role.md | RC-* | orchestrator |
-| scanner | roles/scanner/role.md | SCAN-* | read-only analysis |
-| reviewer | roles/reviewer/role.md | REV-* | read-only analysis |
-| fixer | roles/fixer/role.md | FIX-* | code generation |
+| Role | Task Prefix | Type |
+|------|-------------|------|
+| coordinator | RC-* | orchestrator |
+| scanner | SCAN-* | read-only analysis |
+| reviewer | REV-* | read-only analysis |
+| fixer | FIX-* | code generation |

-**Pipeline** (CP-1 Linear):
+**Pipeline**:
 ```
-coordinator dispatch
-  → SCAN-* (scanner: toolchain + LLM scan)
-  → REV-*  (reviewer: deep analysis + report)
-  → [User confirmation]
-  → FIX-*  (fixer: plan + execute + verify)
+SCAN-* (scan) → REV-* (review) → [User confirmation] → FIX-* (fix)
 ```

-**Checkpoints**:
-| Trigger | Location | Behavior |
-|---------|----------|----------|
-| Review→Fix transition | REV-* complete | Pause, show review report, wait for user `resume` to confirm fix |
-| Quick mode (`-q`) | After SCAN-* | Pipeline ends after scan, no review/fix |
-| Fix-only mode (`--fix`) | Entry | Skip scan/review, go directly to fixer |
-
-**Review Dimensions**:
-| Dimension | Check Points |
-|-----------|--------------|
-| Security (sec) | Injection vulnerabilities, sensitive data leakage, permission control |
-| Correctness (cor) | Boundary conditions, error handling, type safety |
-| Performance (perf) | Algorithm complexity, I/O optimization, resource usage |
-| Maintainability (maint) | Code structure, naming conventions, comment quality |
+**Review Dimensions**: Security, Correctness, Performance, Maintainability

 ---

@@ -263,75 +199,318 @@ coordinator dispatch
 **One-Liner**: Testing team — Progressive test coverage through Generator-Critic loop

 **Trigger**:
+```bash
+team-testing <task-description>
 ```
-/team-testing <task-description>
-```
-
-**Features**:
- 5-role team (coordinator, strategist, generator, executor, analyst)
- Three pipelines: Targeted, Standard, Comprehensive
- Generator-Critic loop automatically improves test coverage

 **Role Registry**:
-| Role | File | Task Prefix | Type |
-|------|------|-------------|------|
-| coordinator | roles/coordinator.md | (none) | orchestrator |
-| strategist | roles/strategist.md | STRATEGY-* | pipeline |
-| generator | roles/generator.md | TESTGEN-* | pipeline |
-| executor | roles/executor.md | TESTRUN-* | pipeline |
-| analyst | roles/analyst.md | TESTANA-* | pipeline |
+| Role | Task Prefix | Type |
+|------|-------------|------|
+| coordinator | (none) | orchestrator |
+| strategist | STRATEGY-* | pipeline |
+| generator | TESTGEN-* | pipeline |
+| executor | TESTRUN-* | pipeline |
+| analyst | TESTANA-* | pipeline |

 **Three Pipelines**:
 ```
-Targeted (small scope changes):
-  STRATEGY-001 → TESTGEN-001(L1 unit) → TESTRUN-001
-
-Standard (progressive):
-  STRATEGY-001 → TESTGEN-001(L1) → TESTRUN-001(L1) → TESTGEN-002(L2) → TESTRUN-002(L2) → TESTANA-001
-
-Comprehensive (full coverage):
-  STRATEGY-001 → [TESTGEN-001(L1) + TESTGEN-002(L2)](parallel) → [TESTRUN-001(L1) + TESTRUN-002(L2)](parallel) → TESTGEN-003(L3) → TESTRUN-003(L3) → TESTANA-001
+Targeted:   STRATEGY → TESTGEN(L1) → TESTRUN
+Standard:   STRATEGY → TESTGEN(L1) → TESTRUN → TESTGEN(L2) → TESTRUN → TESTANA
+Comprehensive: STRATEGY → [TESTGEN(L1+L2) parallel] → [TESTRUN parallel] → TESTGEN(L3) → TESTRUN → TESTANA
 ```

-**Generator-Critic Loop**:
-```
-TESTGEN → TESTRUN → (if coverage < target) → TESTGEN-fix → TESTRUN-2
-                   (if coverage >= target) → next layer or TESTANA
+**Test Layers**: L1: Unit (80%) → L2: Integration (60%) → L3: E2E (40%)
+
+---
+
+### team-arch-opt
+
+**One-Liner**: Architecture optimization team — Analyze architecture issues, design refactoring strategies, implement improvements
+
+**Trigger**:
+```bash
+team-arch-opt <task-description>
 ```

-**Test Layer Definitions**:
-| Layer | Coverage Target | Example |
-|-------|-----------------|---------|
-| L1: Unit | 80% | Unit tests, function-level tests |
-| L2: Integration | 60% | Integration tests, module interaction |
-| L3: E2E | 40% | End-to-end tests, user scenarios |
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| analyzer | ANALYZE-* | architecture analysis |
+| designer | DESIGN-* | refactoring design |
+| refactorer | REFACT-* | implement refactoring |
+| validator | VALID-* | validate improvements |
+| reviewer | REVIEW-* | code review |

-**Shared Memory** (shared-memory.json):
-| Role | Field |
-|------|-------|
-| strategist | `test_strategy` |
-| generator | `generated_tests` |
-| executor | `execution_results`, `defect_patterns` |
-| analyst | `analysis_report`, `coverage_history` |
+**Detection Scope**: Dependency cycles, coupling/cohesion, layering violations, God Classes, dead code
+
+---
+
+### team-perf-opt
+
+**One-Liner**: Performance optimization team — Performance profiling, bottleneck identification, optimization implementation
+
+**Trigger**:
+```bash
+team-perf-opt <task-description>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| profiler | PROFILE-* | performance profiling |
+| strategist | STRAT-* | optimization strategy |
+| optimizer | OPT-* | implement optimization |
+| benchmarker | BENCH-* | benchmarking |
+| reviewer | REVIEW-* | code review |
+
+---
+
+### team-brainstorm
+
+**One-Liner**: Brainstorming team — Multi-angle creative analysis, Generator-Critic loop
+
+**Trigger**:
+```bash
+team-brainstorm <topic>
+team-brainstorm --role=ideator <topic>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| ideator | IDEA-* | idea generation |
+| challenger | CHALLENGE-* | critical questioning |
+| synthesizer | SYNTH-* | synthesis integration |
+| evaluator | EVAL-* | evaluation scoring |
+
+---
+
+### team-frontend
+
+**One-Liner**: Frontend development team — Built-in ui-ux-pro-max design intelligence
+
+**Trigger**:
+```bash
+team-frontend <task-description>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| analyst | ANALYZE-* | requirement analysis |
+| architect | ARCH-* | architecture design |
+| developer | DEV-* | frontend implementation |
+| qa | QA-* | quality assurance |
+
+---
+
+### team-uidesign
+
+**One-Liner**: UI design team — Design system analysis, token definition, component specs
+
+**Trigger**:
+```bash
+team-uidesign <task>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| researcher | RESEARCH-* | design research |
+| designer | DESIGN-* | design definition |
+| reviewer | AUDIT-* | accessibility audit |
+| implementer | BUILD-* | code implementation |
+
+---
+
+### team-issue
+
+**One-Liner**: Issue processing team — Issue processing pipeline
+
+**Trigger**:
+```bash
+team-issue <issue-ids>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| explorer | EXPLORE-* | code exploration |
+| planner | PLAN-* | solution planning |
+| implementer | IMPL-* | code implementation |
+| reviewer | REVIEW-* | code review |
+| integrator | INTEG-* | integration validation |
+
+---
+
+### team-iterdev
+
+**One-Liner**: Iterative development team — Generator-Critic loop, incremental delivery
+
+**Trigger**:
+```bash
+team-iterdev <task-description>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| architect | ARCH-* | architecture design |
+| developer | DEV-* | feature development |
+| tester | TEST-* | test validation |
+| reviewer | REVIEW-* | code review |
+
+**Features**: Developer-Reviewer loop (max 3 rounds), Task Ledger real-time progress
+
+---
+
+### team-quality-assurance
+
+**One-Liner**: Quality assurance team — Issue discovery + test validation closed loop
+
+**Trigger**:
+```bash
+team-quality-assurance <task-description>
+team-qa <task-description>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| scout | SCOUT-* | issue discovery |
+| strategist | QASTRAT-* | strategy formulation |
+| generator | QAGEN-* | test generation |
+| executor | QARUN-* | test execution |
+| analyst | QAANA-* | result analysis |
+
+---
+
+### team-roadmap-dev
+
+**One-Liner**: Roadmap development team — Phased development, milestone management
+
+**Trigger**:
+```bash
+team-roadmap-dev <task-description>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | human interaction |
+| planner | PLAN-* | phase planning |
+| executor | EXEC-* | phase execution |
+| verifier | VERIFY-* | phase validation |
+
+---
+
+### team-tech-debt
+
+**One-Liner**: Tech debt team — Debt scanning, assessment, cleanup, validation
+
+**Trigger**:
+```bash
+team-tech-debt <task-description>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| scanner | TDSCAN-* | debt scanning |
+| assessor | TDEVAL-* | quantitative assessment |
+| planner | TDPLAN-* | governance planning |
+| executor | TDFIX-* | cleanup execution |
+| validator | TDVAL-* | validation regression |
+
+---
+
+### team-ultra-analyze
+
+**One-Liner**: Deep analysis team — Multi-role collaborative exploration, progressive understanding
+
+**Trigger**:
+```bash
+team-ultra-analyze <topic>
+team-analyze <topic>
+```
+
+**Role Registry**:
+| Role | Task Prefix | Function |
+|------|-------------|----------|
+| coordinator | (none) | orchestrator |
+| explorer | EXPLORE-* | code exploration |
+| analyst | ANALYZE-* | deep analysis |
+| discussant | DISCUSS-* | discussion interaction |
+| synthesizer | SYNTH-* | synthesis output |
+
+**Features**: Supports Quick/Standard/Deep three depth modes
+
+---
+
+### team-executor-v2
+
+**One-Liner**: Lightweight executor — Resume session, pure execution mode
+
+**Trigger**:
+```bash
+team-executor --session=<path>
+```
+
+**Features**:
+- No analysis, no role generation — only load and execute existing session
+- Used to resume interrupted team-coordinate sessions
+
+---
+
+## User Commands
+
+All Team Skills support unified user commands (wake paused coordinator):
+
+| Command | Action |
+|---------|--------|
+| `check` / `status` | Output execution status graph, no progress |
+| `resume` / `continue` | Check worker status, advance next step |
+| `revise <TASK-ID>` | Create revision task + cascade downstream |
+| `feedback <text>` | Analyze feedback impact, create targeted revision chain |
+
+---
+
+## Best Practices
+
+1. **Choose the right team type**:
+   - General tasks → `team-coordinate-v2`
+   - Complete feature development → `team-lifecycle-v5`
+   - Issue batch processing → `team-planex`
+   - Code review → `team-review`
+   - Test coverage → `team-testing`
+   - Architecture optimization → `team-arch-opt`
+   - Performance tuning → `team-perf-opt`
+   - Brainstorming → `team-brainstorm`
+   - Frontend development → `team-frontend`
+   - UI design → `team-uidesign`
+   - Tech debt → `team-tech-debt`
+   - Deep analysis → `team-ultra-analyze`
+
+2. **Leverage inner-loop roles**: Set `inner_loop: true` to let single worker handle multiple same-prefix tasks
+
+3. **Wisdom accumulation**: All roles in team sessions accumulate knowledge to `wisdom/` directory
+
+4. **Fast-Advance**: Simple linear successor tasks automatically skip coordinator to spawn directly
+
+5. **Checkpoint recovery**: All team skills support session recovery via `--resume` or `resume` command
+
+---

 ## Related Commands

 - [Claude Commands - Workflow](../commands/claude/workflow.md)
 - [Claude Commands - Session](../commands/claude/session.md)
-
-## Best Practices
-
-1. **Choose the right team type**:
-   - General tasks → `team-coordinate`
-   - Full feature development → `team-lifecycle`
-   - Issue batch processing → `team-planex`
-   - Code review → `team-review`
-   - Test coverage → `team-testing`
-
-2. **Leverage inner-loop roles**: For roles with multiple same-prefix serial tasks, set `inner_loop: true` to let a single worker handle all tasks, avoiding repeated spawn overhead
-
-3. **Wisdom accumulation**: All roles in team sessions accumulate knowledge to `wisdom/` directory, subsequent tasks can reuse these patterns, decisions, and conventions
-
-4. **Fast-Advance**: Simple linear successor tasks automatically skip coordinator to spawn directly, reducing coordination overhead
-
-5. **Checkpoint recovery**: All team skills support session recovery, continue interrupted sessions via `--resume` or user command `resume`