Token导航 LogoToken导航

Agent Skill · 开发

stakeholder-alignment(利益相关者协调)

stakeholder-alignment 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。

stakeholder-alignment 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 14,151。

总安装 745周安装 32GitHub Stars 3下载 261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:stakeholder-alignment(利益相关者协调)
来源仓库:https://github.com/oldwinter/skills
仓库路径:skills/stakeholder-alignment
安装命令:
npx skills add https://github.com/oldwinter/skills --skill stakeholder-alignment
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 stakeholder-alignment

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

用于处理 GitHub 仓库、Issue 和 Pull Request 协作信息整理。适合在团队协作、项目管理中使用,围绕代码变更进行信息归纳。通过 GitHub 安装并使用 npx skills add 命令集成到开发流程。建议在安装前确认仓库访问权限和维护状态,避免误操作影响协作流程。

stakeholder-alignment 属于开发类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/stakeholder-alignment

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/oldwinter/skills --skill stakeholder-alignment;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

stakeholder-alignment 怎么安装?

在终端执行 npx skills add https://github.com/oldwinter/skills --skill stakeholder-alignment。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

stakeholder-alignment 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。

stakeholder-alignment 需要什么权限?

权限级别是只读。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。

stakeholder-alignment 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。

stakeholder-alignment 用的人多吗?

公开数据是累计安装 745 次,近一周安装 32 次,下载 261 次,GitHub 3 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。

stakeholder-alignment 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 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。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 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。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
stakeholder-alignment

利益相关者协调 · 本页

7453只读未明确通过

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

Stakeholder Alignment

Scope

Covers

  • Getting to shared understanding on goal, decision, and success criteria
  • Mapping stakeholders (deciders/influencers/blockers) and tailoring messaging to what they care about
  • Turning “opinions” into decision principles + evaluation criteria
  • Running a no-surprises pre-brief loop to surface objections early
  • Facilitating an alignment/decision meeting and locking follow-through with clear comms

When to use

  • “Help me get exec buy-in for this roadmap change.”
  • “We keep leaving meetings ‘aligned’ and then un-aligning—fix the process.”
  • “Map stakeholders and create a plan to align them on a proposal.”
  • “I need cross-functional alignment (Eng/Design/Sales/Legal) before we commit.”
  • “Draft an alignment pre-read + meeting plan + follow-up comms.”

When NOT to use

  • You don’t yet have a clear problem to solve (use problem definition first).
  • You mainly need a decision framework/roles for a complex choice (use a decision-process skill; this skill assumes you can name the decision and stakeholders).
  • You only need a polished deck (use a presentation skill; this focuses on alignment mechanics and artifacts).
  • The request is interpersonal/HR/legal or requires specialist counsel.

Inputs

Minimum required

  • Alignment goal: inform / align / decide (and by when)
  • The proposal (or decision) in one sentence + why now
  • Stakeholder list (or org context to infer it)
  • Constraints/non-negotiables (timeline, budget, policy, compliance, customer commitments)
  • Current state: what’s already been discussed, and where alignment breaks down

Missing-info strategy

  • Ask 3–5 questions from references/INTAKE.md at a time.
  • If key info is unavailable, proceed with explicit assumptions and label unknowns.

Outputs (deliverables)

Produce a Stakeholder Alignment Pack (Markdown in-chat; or files if requested) in this order:

  1. Alignment Brief (1-pager) (goal, decision/ask, why now, user value, success criteria, constraints, tradeoffs)
  2. Stakeholder Map + “How They Think” notes (roles, incentives, likely objections, decision principles)
  3. Alignment Plan (pre-brief sequence, artifacts, timeline, and “no surprises” plan)
  4. Alignment Pre-read + Meeting Plan (agenda, vital questions, options/tradeoffs, decision capture)
  5. Decision Summary + Comms Draft (what we decided, why, what changes, owners, next steps)
  6. Risks / Open questions / Next steps (always)

Templates: references/TEMPLATES.md Expanded guidance: references/WORKFLOW.md

Workflow (8 steps)

1) Define the alignment target (what does “aligned” mean?)

  • Inputs: user context; references/INTAKE.md.
  • Actions: Classify the goal (inform/align/decide) and name the decision/commitment (or the output of alignment). Set a date and what “done” looks like.
  • Outputs: Alignment Brief sections: Goal, Decision/Ask, Deadline, Scope boundaries.
  • Checks: You can finish the sentence: “After alignment, stakeholders will commit to _____ by _____.“

2) Map stakeholders and decision rights (who matters, and why)

  • Inputs: org context; prior meeting notes; known stakeholders.
  • Actions: Build a stakeholder map: decider(s), approvers, influencers, implementers, blockers, and “silent veto” risks. Identify who must not be surprised.
  • Outputs: Stakeholder Map (table) + “pre-brief required” list.
  • Checks: Every critical function affected (e.g., Eng, Design, Sales, Support, Legal/Compliance, Finance) is either included or explicitly out of scope.

3) Decode “how they think” (principles, not just opinions)

  • Inputs: prior feedback; exec writings/talks; observed patterns.
  • Actions: Convert stakeholder feedback into 3–7 decision principles (e.g., “must feel like the future”, “minimize enterprise risk”). Note what evidence persuades them.
  • Outputs: “How They Think” notes (per key stakeholder) + principles list.
  • Checks: For each key stakeholder, you can explain: “In what world does their viewpoint make sense?”

4) Anchor on user value + business constraints (cut through noise)

  • Inputs: proposal; user/customer context; constraints.
  • Actions: Draft the narrative spine: user value (the “vital question”), why now, and the unavoidable tradeoffs. Make constraints explicit (compliance, monetization, go-to-market, reliability).
  • Outputs: Alignment Brief sections: User value, Why now, Constraints, Tradeoffs.
  • Checks: A skeptical stakeholder can’t dismiss the proposal as “nice to have” without disputing a stated assumption.

5) Define evaluation criteria and “what good looks like”

  • Inputs: goals, constraints, stakeholder principles.
  • Actions: Create evaluation criteria (and weights if helpful). Set expectations that agreement may feel uncomfortable at first; focus stakeholders on criteria over gut feel.
  • Outputs: Criteria list (and optional criteria table) + “discomfort is normal” expectation-setting line for meetings.
  • Checks: Criteria are few (3–7), mutually meaningful (real tradeoffs), and tied to stakeholder principles.

6) Run the pre-brief loop (no surprises; watch reactions)

  • Inputs: draft pack; pre-brief list.
  • Actions: Meet key stakeholders 1:1 (or small groups). Observe what lands (and what causes “dead eyes”), capture objections, and update the pack. Keep a change log.
  • Outputs: Pre-brief notes + objections log + updated pack + change log.
  • Checks: No major stakeholder sees the core ask for the first time in the live meeting.

7) Facilitate the alignment/decision meeting (commitments, not vibes)

  • Inputs: final pre-read; agenda; decision capture plan.
  • Actions: Open with the alignment target and vital question. Walk through options/tradeoffs against criteria. Confirm the decision and commitments (owner + due dates). Record dissent and follow-ups.
  • Outputs: Meeting notes + decision capture + action list.
  • Checks: Everyone leaves knowing: what we decided, why, what changes tomorrow, and who owns what.

8) Communicate and lock alignment (prevent re-litigation)

  • Inputs: decision capture; action list; stakeholder map.
  • Actions: Send a crisp summary to all stakeholders (including those not in the room). Document rationale and tradeoffs. Set a review/checkpoint date.
  • Outputs: Decision Summary + Comms Draft + review checkpoint.
  • Checks: Follow-up comms contains: decision, rationale, tradeoffs, owners, dates, and what would trigger a revisit.

Quality gate (required)

Examples

Example 1: “We need exec alignment on a 6-week pause of Feature A to address reliability. Draft the alignment brief, stakeholder map, pre-brief plan, and the decision meeting plan.” Expected: Alignment Brief, Stakeholder Map, pre-brief plan + notes template, meeting plan + comms draft.

Example 2: “Sales and Legal are blocking a self-serve launch. Create a cross-functional alignment plan that surfaces constraints early and lands on a committed path.” Expected: explicit constraints, evaluation criteria, no-surprises pre-brief loop, decision capture, and follow-up comms.

Boundary example: “Make them agree with me; they’re irrational.” Response: refuse to ‘win politics’; reframe to an evidence-based alignment process (principles, criteria, tradeoffs). If the user can’t name a decision/goal, do problem definition first.

平台分布

Codex

36.03%
按下载量换算94

Claude

30.85%
按下载量换算81

Cursor

18.59%
按下载量换算49

Gemini CLI

8.92%
按下载量换算23

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。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