Token导航 LogoToken导航TokenDH.com
前端设计只读github未标认证来源可访问许可证需确认审计通过

cross-functional-collaboration跨职能协作

Agent Skill

cross-functional-collaboration 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

总安装

717

周安装

29

GitHub Stars

3

下载量

225
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:cross-functional-collaboration(跨职能协作)
来源仓库:https://github.com/oldwinter/skills
仓库路径:skills/cross-functional-collaboration
安装命令:
npx skills add https://github.com/oldwinter/skills --skill cross-functional-collaboration
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/oldwinter/skills --skill cross-functional-collaboration

简介

cross-functional-collaboration 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。
  • 通过 npx skills add 命令从指定仓库安装并使用。
  • 使用前需确认权限范围、维护状态,避免触发联网或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Cross-functional Collaboration

Scope

Covers

  • Leading a cross-functional initiative (Product/Engineering/Design/Data/Marketing/Ops/etc.)
  • Turning “we’re misaligned” into explicit goals, roles, decisions, and operating cadence
  • Reducing rework and conflict via shared artifacts (docs/prototypes) and clear decision rights
  • Building trust through conflict norms and credit/recognition practices

When to use

  • “We keep thrashing between PM/Eng/Design—set up a better way of working.”
  • “Create a collaboration charter: roles, responsibilities, decision-making, and cadence.”
  • “We need to work better with Engineering/Design/Data on.”
  • “Our cross-functional project is slow due to unclear ownership and decisions.”

When NOT to use

  • You need to define the underlying product problem first (use problem-definition).
  • You need a full decision process for a single high-stakes decision (use running-decision-processes).
  • The issue is primarily a performance or accountability problem with an individual (use having-difficult-conversations).
  • You only need a timeline/milestone plan (use managing-timelines).

Inputs

Minimum required

  • Initiative summary: what it is, why now, desired outcomes, and timeframe
  • Functions/teams involved + key stakeholders (including any required subject matter experts)
  • Current symptoms: where collaboration is breaking down (examples help)
  • Constraints: deadlines, non-negotiables, policies/compliance, customer commitments

Missing-info strategy

  • Ask up to 5 questions from references/INTAKE.md.
  • If answers aren’t available, proceed with explicit assumptions and label unknowns.

Outputs (deliverables)

Produce a Cross-Functional Collaboration Pack (Markdown in-chat, or files if requested) in this order:

  1. Mission Charter (goals, success metrics, scope, constraints, timeline)
  2. Stakeholder & Incentives Map (owners, approvers, incentives/risks, comms needs)
  3. Roles & Expectations Contract (responsibilities, expectations matrix, decision rights, escalation triggers)
  4. Operating Cadence & Communication Plan (meetings, async updates, doc hub, comms to stakeholders)
  5. Decision Log (initial) + Decision Protocol (what decisions are needed, who decides, how captured)
  6. Collaboration Norms (conflict protocol + credit/recognition plan)
  7. Risks / Open questions / Next steps (always included)

Templates: references/TEMPLATES.md

Workflow (7 steps)

1) Define the mission (and the collaboration mode)

  • Inputs: Initiative summary; timeline; constraints.
  • Actions: Clarify the mission, success metrics, and what “done” means. Name the collaboration mode (project/sprint vs ongoing interface) and the stakes (why this matters now).
  • Outputs: Mission Charter (draft).
  • Checks: A cross-functional partner can restate the mission, success metric(s), and constraints without you in the room.

2) Map the full cross-functional system (people + incentives)

  • Inputs: Org context; teams/functions; known stakeholders.
  • Actions: Identify owners, approvers, contributors, and informed stakeholders. Capture incentives, concerns, and “hidden constraints.” Ensure required subject matter experts are included.
  • Outputs: Stakeholder & Incentives Map + “missing seats” list.
  • Checks: No surprise approvers; every team that must execute or sign off is represented.

3) Make expectations explicit (write the contract)

  • Inputs: Stakeholder map; friction examples.
  • Actions: Run an expectations exercise (each function writes expectations of the others). Convert to a clear responsibilities map, decision rights, escalation triggers, and review cadence.
  • Outputs: Roles & Expectations Contract (v1).
  • Checks: Each function can answer: “What do I own? What do I expect of others? What decisions can I make?”

4) Establish a shared language via artifacts (prototype-first when helpful)

  • Inputs: Initiative stage; ambiguity areas; tooling constraints.
  • Actions: Choose the minimum set of shared artifacts (e.g., charter, spec/PRD, prototype, metrics definitions). Add an early “prototype or working slice” milestone when it reduces ambiguity.
  • Outputs: Artifact plan + first prototype milestone (or “working slice” plan).
  • Checks: At least one artifact concretely reduces ambiguity (fewer interpretation disputes).

5) Design the operating cadence (meetings, async, and decision logging)

  • Inputs: Timeline; time zones; team size; existing rituals.
  • Actions: Define the cadence, update format, doc hub, and channels. Install a decision log and a lightweight decision protocol (who decides, how disagreements resolve, where decisions live).
  • Outputs: Operating Cadence & Communication Plan + Decision Log (seeded with first decisions).
  • Checks: Cadence is sustainable and oriented to outcomes, decisions, and risks (not “status theater”).

6) Set norms for conflict and credit (trust mechanics)

  • Inputs: Known tensions; cultural context; prior failure modes.
  • Actions: Define a conflict protocol (including a “Yes, and” approach to reconcile valid competing goals). Define credit/recognition practices (who presents, how you share credit, how you recognize partner work).
  • Outputs: Collaboration Norms (Conflict Protocol + Credit/Recognition Plan).
  • Checks: Norms are specific enough to follow in a real disagreement and in exec/customer updates.

7) Quality gate + launch (and monitoring plan)

  • Inputs: Draft pack.
  • Actions: Run the checklist and rubric. Finalize the pack. Propose the first 1–2 “health checks” to update roles/cadence based on reality.
  • Outputs: Final Pack + rubric score + Risks/Open questions/Next steps.
  • Checks: If rubric score is low, do one more intake round (max 5 questions) and revise.

Quality gate (required)

Examples

Example 1: “I’m leading a cross-functional onboarding revamp across Product/Eng/Design/Data. Create a Collaboration Pack with roles, cadence, and a decision log.” Expected: mission charter, stakeholder map, expectations contract, operating cadence, decision protocol/log, conflict + credit norms.

Example 2: “I’m an Engineering Manager partnering with PM+Design on a platform migration. Our decisions are slow and we keep re-litigating scope—create a Collaboration Pack.” Expected: decision rights/escalation triggers, seeded decision log, prototype/working-slice plan, and a lightweight cadence.

Boundary example: “Help me convince another team to do what I want.” Response: this skill aligns on shared goals/constraints and decision rights; if you need a one-way persuasion narrative or exec escalation, clarify the decision and use running-decision-processes or managing-up.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.8%
按下载量换算83

Claude

28.76%
按下载量换算65

Cursor

18.88%
按下载量换算42

Gemini CLI

8.75%
按下载量换算20

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills