Token导航 LogoToken导航

Agent Skill · 研究检索

team-lifecycle-v5(团队生命周期 v5)

team-lifecycle-v5 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

team-lifecycle-v5 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 65,612。

总安装 279周安装 12GitHub Stars 1,938下载 98核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:team-lifecycle-v5(团队生命周期 v5)
来源仓库:https://github.com/catlog22/claude-code-workflow
仓库路径:skills/team-lifecycle-v5
安装命令:
npx skills add https://github.com/catlog22/claude-code-workflow --skill team-lifecycle-v5
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/catlog22/claude-code-workflow --skill team-lifecycle-v5

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

适用于团队生命周期高级管理、智能演进或多维度评估等场景。支持多宿主环境,便于在不同 AI 工具间迁移使用。

来源仓库内路径:skills/team-lifecycle-v5

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/catlog22/claude-code-workflow --skill team-lif…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

team-lifecycle-v5 怎么安装?

在终端执行 npx skills add https://github.com/catlog22/claude-code-workflow --skill team-lifecycle-v5。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

team-lifecycle-v5 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

team-lifecycle-v5 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/catlog22/claude-code-workflow --skill team-lifecycle-v5 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

team-lifecycle-v5 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

team-lifecycle-v5 用的人多吗?

公开数据是累计安装 279 次,近一周安装 12 次,下载 98 次,GitHub 1,938 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

team-lifecycle-v5 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 来源仓库有 1,938 星,维护活跃度相对可查。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
team-lifecycle-v5

团队生命周期 v5 · 本页

2791,938执行命令未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Team Lifecycle v5

Unified team skill: specification -> implementation -> testing -> review. Built on team-worker agent architecture — all worker roles share a single agent definition with role-specific Phase 2-4 loaded from markdown specs.

Architecture

+---------------------------------------------------+
|  Skill(skill="team-lifecycle-v5")                  |
|  args="task description"                           |
+-------------------+-------------------------------+
                    |
         Orchestration Mode (auto -> coordinator)
                    |
              Coordinator (inline)
              Phase 0-5 orchestration
                    |
    +----+-----+-------+-------+-------+-------+
    v    v     v       v       v       v       v
 [team-worker agents, each loaded with a role-spec]
  analyst writer planner executor tester reviewer
                                    ^        ^
                              on-demand by coordinator
                            +---------+ +--------+
                            |architect| |fe-dev  |
                            +---------+ +--------+
                                        +--------+
                                        | fe-qa  |
                                        +--------+

  Subagents (callable by any worker, not team members):
    [discuss-subagent]  - multi-perspective critique
    [explore-subagent]  - codebase exploration with cache
    [doc-generation]    - document generation (CLI execution)

Role Router

This skill is coordinator-only. Workers do NOT invoke this skill — they are spawned as team-worker agents directly.

Input Parsing

Parse $ARGUMENTS. No --role needed — always routes to coordinator.

Role Registry

RoleSpecTask PrefixTypeInner Loop
coordinatorroles/coordinator/role.md(none)orchestrator-
analystrole-specs/analyst.mdRESEARCH-*pipelinefalse
writerrole-specs/writer.mdDRAFT-*pipelinetrue
plannerrole-specs/planner.mdPLAN-*pipelinetrue
executorrole-specs/executor.mdIMPL-*pipelinetrue
testerrole-specs/tester.mdTEST-*pipelinefalse
reviewerrole-specs/reviewer.mdREVIEW-* + QUALITY-* + IMPROVE-*pipelinefalse
architectrole-specs/architect.mdARCH-*consultingfalse
fe-developerrole-specs/fe-developer.mdDEV-FE-*frontendfalse
fe-qarole-specs/fe-qa.mdQA-FE-*frontendfalse

Subagent Registry

SubagentSpecCallable ByPurpose
discusssubagents/discuss-subagent.mdanalyst, writer, reviewerMulti-perspective critique
exploresubagents/explore-subagent.mdanalyst, planner, any roleCodebase exploration with cache
doc-generationsubagents/doc-generation-subagent.mdwriterDocument generation (CLI execution)

Dispatch

Always route to coordinator. Coordinator reads roles/coordinator/role.md and executes its phases.

Orchestration Mode

User just provides task description.

Invocation: Skill(skill="team-lifecycle-v5", args="task description")

Lifecycle:

User provides task description
  -> coordinator Phase 1-3: requirement clarification -> TeamCreate -> create task chain
  -> coordinator Phase 4: spawn first batch workers (background) -> STOP
  -> Worker executes -> SendMessage callback -> coordinator advances next step
  -> Loop until pipeline complete -> Phase 5 report

User Commands (wake paused coordinator):

CommandAction
check / statusOutput execution status graph, no advancement
resume / continueCheck worker states, advance next step
revise <TASK-ID> [feedback]Create revision task + cascade downstream
feedback <text>Analyze feedback impact, create targeted revision chain
recheckRe-run QUALITY-001 quality check
improve [dimension]Auto-improve weakest dimension from readiness-report

Coordinator Spawn Template

v5 Worker Spawn (all roles)

When coordinator spawns workers, use team-worker agent with role-spec path:

Task({
  subagent_type: "team-worker",
  description: "Spawn <role> worker",
  team_name: <team-name>,
  name: "<role>",
  run_in_background: true,
  prompt: `## Role Assignment
role: <role>
role_spec: .claude/skills/team-lifecycle-v5/role-specs/<role>.md
session: <session-folder>
session_id: <session-id>
team_name: <team-name>
requirement: <task-description>
inner_loop: <true|false>

Read role_spec file to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role-spec Phase 2-4 -> built-in Phase 5 (report).`
})

Inner Loop roles (writer, planner, executor): Set inner_loop: true. The team-worker agent handles the loop internally.

Single-task roles (analyst, tester, reviewer, architect, fe-developer, fe-qa): Set inner_loop: false.


Pipeline Definitions

Spec-only (6 tasks)

RESEARCH-001(+D1) -> DRAFT-001(+D2) -> DRAFT-002(+D3) -> DRAFT-003(+D4) -> DRAFT-004(+D5) -> QUALITY-001(+D6)

Impl-only (4 tasks)

PLAN-001 -> IMPL-001 -> TEST-001 + REVIEW-001

Full-lifecycle (10 tasks)

[Spec pipeline] -> PLAN-001(blockedBy: QUALITY-001) -> IMPL-001 -> TEST-001 + REVIEW-001

Frontend Pipelines

FE-only:       PLAN-001 -> DEV-FE-001 -> QA-FE-001
               (GC loop: QA-FE verdict=NEEDS_FIX -> DEV-FE-002 -> QA-FE-002, max 2 rounds)

Fullstack:     PLAN-001 -> IMPL-001 || DEV-FE-001 -> TEST-001 || QA-FE-001 -> REVIEW-001

Full + FE:     [Spec pipeline] -> PLAN-001 -> IMPL-001 || DEV-FE-001 -> TEST-001 || QA-FE-001 -> REVIEW-001

Cadence Control

Beat model: Event-driven, each beat = coordinator wake -> process -> spawn -> STOP.

Beat Cycle (single beat)
======================================================================
  Event                   Coordinator              Workers
----------------------------------------------------------------------
  callback/resume --> +- handleCallback -+
                      |  mark completed   |
                      |  check pipeline   |
                      +- handleSpawnNext -+
                      |  find ready tasks |
                      |  spawn workers ---+--> [team-worker A] Phase 1-5
                      |  (parallel OK)  --+--> [team-worker B] Phase 1-5
                      +- STOP (idle) -----+         |
                                                     |
  callback <-----------------------------------------+
  (next beat)              SendMessage + TaskUpdate(completed)
======================================================================

  Fast-Advance (skips coordinator for simple linear successors)
======================================================================
  [Worker A] Phase 5 complete
    +- 1 ready task? simple successor?
    |   --> spawn team-worker B directly
    |   --> log fast_advance to message bus (coordinator syncs on next wake)
    +- complex case? --> SendMessage to coordinator
======================================================================

Checkpoints

TriggerPositionBehavior
Spec->Impl transitionQUALITY-001 completedRead readiness-report.md, display checkpoint, pause for user action
GC loop maxQA-FE max 2 roundsStop iteration, report current state
Pipeline stallNo ready + no runningCheck missing tasks, report to user

Checkpoint Output Template (QUALITY-001 completion):

[coordinator] ══════════════════════════════════════════
[coordinator] SPEC PHASE COMPLETE
[coordinator] Quality Gate: <PASS|REVIEW|FAIL> (<score>%)
[coordinator]
[coordinator] Dimension Scores:
[coordinator]   Completeness:  <bar> <n>%
[coordinator]   Consistency:   <bar> <n>%
[coordinator]   Traceability:  <bar> <n>%
[coordinator]   Depth:         <bar> <n>%
[coordinator]   Coverage:      <bar> <n>%
[coordinator]
[coordinator] Available Actions:
[coordinator]   resume              -> Proceed to implementation
[coordinator]   improve             -> Auto-improve weakest dimension
[coordinator]   improve <dimension> -> Improve specific dimension
[coordinator]   revise <TASK-ID>    -> Revise specific document
[coordinator]   recheck             -> Re-run quality check
[coordinator]   feedback <text>     -> Inject feedback, create revision
[coordinator] ══════════════════════════════════════════

Task Metadata Registry

Task IDRolePhaseDependenciesInline Discuss
RESEARCH-001analystspec(none)DISCUSS-001
DRAFT-001writerspecRESEARCH-001DISCUSS-002
DRAFT-002writerspecDRAFT-001DISCUSS-003
DRAFT-003writerspecDRAFT-002DISCUSS-004
DRAFT-004writerspecDRAFT-003DISCUSS-005
QUALITY-001reviewerspecDRAFT-004DISCUSS-006
PLAN-001plannerimpl(none or QUALITY-001)-
IMPL-001executorimplPLAN-001-
TEST-001testerimplIMPL-001-
REVIEW-001reviewerimplIMPL-001-
DEV-FE-001fe-developerimplPLAN-001-
QA-FE-001fe-qaimplDEV-FE-001-

Session Directory

.workflow/.team/TLS-<slug>-<date>/
+-- team-session.json
+-- spec/
|   +-- spec-config.json
|   +-- discovery-context.json
|   +-- product-brief.md
|   +-- requirements/
|   +-- architecture/
|   +-- epics/
|   +-- readiness-report.md
|   +-- spec-summary.md
+-- discussions/
+-- plan/
|   +-- plan.json
|   +-- .task/TASK-*.json
+-- explorations/
|   +-- cache-index.json
|   +-- explore-<angle>.json
+-- architecture/
+-- analysis/
+-- qa/
+-- wisdom/
|   +-- learnings.md
|   +-- decisions.md
|   +-- conventions.md
|   +-- issues.md
+-- .msg/
+-- shared-memory.json

Session Resume

Coordinator supports --resume / --continue for interrupted sessions:

  1. Scan .workflow/.team/TLS-*/team-session.json for active/paused sessions
  2. Multiple matches -> AskUserQuestion for selection
  3. Audit TaskList -> reconcile session state <-> task status
  4. Reset in_progress -> pending (interrupted tasks)
  5. Rebuild team and spawn needed workers only
  6. Create missing tasks with correct blockedBy
  7. Kick first executable task -> Phase 4 coordination loop

Shared Resources

ResourcePathUsage
Document Standardsspecs/document-standards.mdYAML frontmatter, naming, structure
Quality Gatesspecs/quality-gates.mdPer-phase quality gates
Team Configspecs/team-config.jsonRole registry, pipeline definitions
Product Brief Templatetemplates/product-brief.mdDRAFT-001
Requirements Templatetemplates/requirements-prd.mdDRAFT-002
Architecture Templatetemplates/architecture-doc.mdDRAFT-003
Epics Templatetemplates/epics-template.mdDRAFT-004
Discuss Subagentsubagents/discuss-subagent.mdInline discuss protocol
Explore Subagentsubagents/explore-subagent.mdShared exploration utility
Doc-Gen Subagentsubagents/doc-generation-subagent.mdDocument generation engine

Error Handling

ScenarioResolution
Unknown commandError with available command list
Role spec file not foundError with expected path
Command file not foundFallback to inline execution
Discuss subagent failsWorker proceeds without discuss, logs warning
Explore cache corruptClear cache, re-explore
Fast-advance spawns wrong taskCoordinator reconciles on next callback

平台分布

Codex

35.96%
按下载量换算35

Claude

30.41%
按下载量换算30

Cursor

18.23%
按下载量换算18

Gemini CLI

8.81%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/catlog22/claude-code-workflow --skill team-lifecycle-v5 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills