SKILL·F0ED43

stakeholder-identification

deanpeters
更新于 26 days ago
1 次查看
5,795
713
5,795
在 GitHub 上查看
design

关于

This skill systematically identifies all stakeholders before project engagement, using structured categorization and an equity check. It's designed for launching new initiatives or scoping discovery sprints when the stakeholder landscape is unknown. The output is a prioritized list, narrowing focus to the 2-3 most critical stakeholders to understand first.

快速安装

Claude Code

推荐
主要方式
npx skills add deanpeters/Product-Manager-Skills -a claude-code
插件命令备选方式
/plugin add https://github.com/deanpeters/Product-Manager-Skills
Git 克隆备选方式
git clone https://github.com/deanpeters/Product-Manager-Skills.git ~/.claude/skills/stakeholder-identification

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Stakeholder Identification

Purpose

Map every stakeholder before engaging anyone. This skill produces a comprehensive, equity-aware stakeholder set — not just the obvious sponsors and users, but the gatekeepers, the impacted communities, and the voices your team defaults to overlooking.

Most PM stakeholder lists are written from memory in five minutes. They reliably capture executives, product peers, and the most vocal users. They reliably miss the marginalized user groups who bear the product's consequences without having the organizational power to shape its decisions. This skill forces a slower, more structured brainstorm that builds the foundation for every engagement decision that follows.

Use this before stakeholder-mapping (which prioritizes) and before stakeholder-engagement-advisor (which plans per-stakeholder outreach). Identification comes first — you cannot prioritize people you haven't named.

Key Concepts

Allies, Audiences, Influencers — The three categories that clarify stakeholder relationship to your work. Allies actively support the initiative; audiences are impacted by it; influencers shape opinion or decisions without being directly affected. Sorting stakeholders this way reveals who to recruit, who to inform, and who to persuade — three different engagement jobs.

R/P/D Marking — Tagging each stakeholder as a provider of Resources (budget, headcount, access), Permission (approval to proceed, regulatory clearance), or Decision-making authority (final say). This quickly surfaces who can fund, block, or green-light your initiative versus who is merely interested. One stakeholder can hold multiple tags.

Equity Lens — Deliberately stretching the list to include stakeholders who are often excluded: marginalized user populations, frontline employees, downstream communities, people who bear the product's consequences but lack organizational power to influence its design. Without this step, teams optimize for loud, well-resourced voices and build products that fail the quieter majority.

Primary, Secondary, Tertiary Effects — Tracing ripple effects of your product outward from direct users to indirectly affected groups. A feature that changes how support agents work (primary) affects how customers experience service (secondary), which affects the company's reputation and churn (tertiary). Following the chain surfaces stakeholders that single-level thinking misses.

Notice Bias & Assumptions — An explicit team check: who did we default to naming? Who is absent from the list? Whose perspective are we treating as universal? This step names the blind spots before they become requirements gaps.

Identification vs. Prioritization — The discipline of separating who exists from who matters most. The goal of this skill is a complete list, not a prioritized one. Collapsing these two steps causes teams to prematurely cut stakeholders they haven't yet understood. Prioritization happens in stakeholder-mapping.

Application

Step 1 — Brainstorm without filtering

Generate a fast, unconstrained list of potential stakeholders: individuals, teams, organizations, and communities connected to this initiative. Do not self-edit. Write down anyone who could plausibly have a stake — even if their involvement seems unlikely.

If working in a group, run this silently for 4-6 minutes before sharing.

Step 2 — Categorize

Sort each stakeholder into one or more of these categories:

  • Allies — who actively supports this work or would benefit from its success?
  • Audiences — who is impacted by the outcome, directly or indirectly?
  • Influencers — who shapes decisions, opinion, or adoption without being a direct participant?

Note: a stakeholder can appear in more than one category. Those overlaps — an ally who is also a key influencer — often mark your highest-leverage relationships.

Step 3 — Apply R/P/D marking

For each stakeholder, mark whether they provide:

  • R — Resources (budget, people, data, access)
  • P — Permission (approval, legal clearance, sign-off)
  • D — Decision authority (final say on scope, prioritization, or launch)

Any stakeholder holding P or D who is missing from your list is a gap that will surface later as a blocker.

Step 4 — Apply the equity lens

Ask the following questions about your list:

  • Who experiences a significant difference or consequence from this product — financially, professionally, or in their daily experience?
  • Who bears the product's costs or risks without having the power to shape its design?
  • Whose perspective is missing because we assumed someone else represents them?
  • Who are the primary users? Who are the secondary users? Who is affected in the third degree?

Add anyone the equity lens surfaces. These stakeholders are likely to end up in Q1 of your stakeholder-mapping (high impact, low power) — the voices most important to elevate.

Step 5 — Notice bias and assumptions

As a group, answer explicitly:

  • Who did we default to naming in Step 1?
  • Who is absent? Why?
  • What assumptions did we make about who counts as a stakeholder?

Record the answers. These shape your research plan and recruitment strategy.

Step 6 — Narrow to priority targets

With the full list visible, identify the 2-3 stakeholders you need to understand most deeply before proceeding. These are typically:

  • The highest-power decision-makers whose buy-in is required
  • The highest-impact users whose needs are least understood
  • The most likely blockers or skeptics

For each priority stakeholder, capture: name, category, R/P/D tag, and a one-line "what we need to learn from them." These outputs feed directly into stakeholder-mapping and stakeholder-engagement-advisor.

Examples

Situation: A product team is scoping a new intake workflow that replaces manual email-based requests with a self-service portal. Initial stakeholder list: VP of Operations, Engineering Lead, PMO Director, enterprise customers.

Underdeveloped (common default): The list captures obvious sponsors and the customer segment that asked loudest for the feature. Missing: the customer support agents who currently process every manual request (primary daily users of the current workflow), IT security team (P — must approve data handling), compliance officer (P — regulatory implications), small business customers who lack technical staff to use a self-service portal (high-impact, low-power audience).

Stronger list after applying equity lens and R/P/D marking:

  • VP of Operations (D, Ally) — final scope authority
  • Engineering Lead (R, Ally) — capacity and technical feasibility
  • PMO Director (P, Influencer) — must approve process change
  • Enterprise customers (Audience) — primary users of new portal
  • Customer support agents (Audience, R) — process every intake today; adoption risk if not consulted
  • IT Security (P) — data handling approval required
  • Compliance Officer (P) — regulatory review
  • Small business customers (Audience) — impacted differently; may need a non-self-service path

The second list produces a PRD with different requirements, a different rollout plan, and a different definition of success.

Common Pitfalls

Treating the first brainstorm as the final list. The initial pass reliably captures 60% of stakeholders and systematically misses the 40% who are less visible. The categorization and equity steps exist to close that gap — skipping them defeats the exercise.

Listing roles or org units instead of people. "Engineering" is not a stakeholder. The engineering lead who controls sprint capacity is. Vague category names prevent you from booking the conversation you actually need.

Conflating identification with prioritization. Cutting stakeholders during the brainstorm phase, before you've understood their actual influence or impact, is how high-impact, low-power voices get silently dropped. Complete the list first. Prioritize in stakeholder-mapping.

Skipping the bias and assumptions check. Teams that skip this step feel confident in their completeness. Teams that run it discover they've assumed a well-resourced user proxy speaks for everyone. Name the blind spot explicitly.

Running it solo without external validation. A single person's stakeholder map reflects a single person's network and assumptions. If working solo, use the bias check to identify who is absent from your mental model, then validate with a cross-functional colleague before proceeding.

Generating a complete list but capturing no next steps. The canvas ends with priority targets and actions for a reason. A comprehensive stakeholder list with no "who talks to whom, by when" attached is a document, not a plan.

References

GitHub 仓库

deanpeters/Product-Manager-Skills
路径: skills/stakeholder-identification
0
ai-agentsai-product-managementclaude-skillspm-frameworksproduct-management
FAQ

Frequently asked questions

What is the stakeholder-identification skill?

stakeholder-identification is a Claude Skill by deanpeters. Skills package instructions and resources that Claude loads on demand, so Claude can perform stakeholder-identification-related tasks without extra prompting.

How do I install stakeholder-identification?

Use the install commands on this page: add stakeholder-identification to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.

What category does stakeholder-identification belong to?

stakeholder-identification is in the Meta category, tagged design.

Is stakeholder-identification free to use?

Yes. stakeholder-identification is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能
polymarket

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能
creating-opencode-plugins

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能
sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能