Agent skill

Stakeholder Map

by sruthir28 in sruthir28/enterprise-ai-skills

Map the people who can make or break a decision onto a Power/Interest grid, with each named stakeholder's stance (champion / skeptic / blocker / unknown), what they care about, and the single…

MITAuto-check passed

Install Stakeholder Map

skills CLI
$ npx skills add sruthir28/enterprise-ai-skills --skill stakeholder-map -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sruthir28/enterprise-ai-skills stakeholder-map --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sruthir28/enterprise-ai-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/stakeholder-map .claude/skills/stakeholder-map && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
stakeholder-map
GitHub stars
148
Token cost
~2.4k tokens
SKILL.md length
1,230 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Map the people who can make or break a decision onto a Power/Interest grid, with each named stakeholder's stance (champion / skeptic / blocker / unknown), what they care about, and the single…

  • Works in 4 steps: The decision. "Migrate to Linear."… → Decision moment. When does this need to… → The full cast. Everyone who has an… → …
  • SKILL.md covers Design choices, The grid, Inputs needed (interview if… and Output format, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Stakeholder Map is an agent skill from sruthir28/enterprise-ai-skills. Map the people who can make or break a decision onto a Power/Interest grid, with each named stakeholder's stance (champion / skeptic / blocker / unknown), what they care about, and the single influence move you'll make for them. Use before any cross-functional decision, big launch, reorg, or executive ask — anywhere the politics will decide the outcome more than the merits.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Open-source AI skills for enterprise professionals. McKinsey consulting frameworks, PM workflows, and practical tools. Currently for Claude, expanding to other LLMs. The licence is MIT.

Example prompts

  • “/stakeholder-map”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. The decision. "Migrate to Linear." "Sunset legacy product." "Reorg sales by vertical." Specific.
  2. Decision moment. When does this need to be approved? By whom?
  3. The full cast. Everyone who has an opinion, a budget, a team affected, or a meeting on this. Names + roles.
  4. What you already know about each. Stated stance, recent comments, past behavior on similar decisions. (If you don't know — that's the…

What it can do on your machine

Read from SKILL.md and the folder at commit ae8fe60. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Stakeholder Map loads about 2.4k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 1,230 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sruthir28/enterprise-ai-skills at commit ae8fe60, republished under its MIT licence (© sruthir28). 1,230 words, ~2,403 tokens.

Download SKILL.mdSave it as .claude/skills/stakeholder-map/SKILL.md (or your agent's skills folder).
name
stakeholder-map
description
Map the people who can make or break a decision onto a Power/Interest grid, with each named stakeholder's stance (champion / skeptic / blocker / unknown), what they care about, and the single influence move you'll make for them. Use before any cross-functional decision, big launch, reorg, or executive ask — anywhere the politics will decide the outcome more than the merits.

Stakeholder Map

Most decisions don't fail because the analysis was wrong. They fail because the person who could kill it wasn't bought in, or the person who could champion it wasn't asked. This skill makes the politics visible so you can plan around them — without pretending strategy and people are separate problems.

The output is a 2x2 grid + a per-stakeholder action plan. You walk away knowing exactly who you talk to first, what you say, and who you can ignore.


Design choices

  • Real names, not roles. "Head of Eng" hides the fact that this Head of Eng has been here 3 months and has political capital below the team they inherited. Use names.
  • Power × Interest, not Influence × Impact. Power = can they kill the decision. Interest = do they care about the outcome. The right axes for politics, not for delivery management.
  • One move per stakeholder. Not a 5-step engagement plan. The one thing you'll do this week.
  • Stance is honest. Champions get celebrated, blockers get named. If everyone is "supportive," you haven't mapped honestly.
  • Skip the unmappable. If you have <2 minutes of real information on a stakeholder, mark them "unknown" and make finding out their #1 action.

The grid

                       HIGH INTEREST                 LOW INTEREST
                  ┌──────────────────────────┬──────────────────────────┐
                  │                          │                          │
   HIGH           │   MANAGE CLOSELY         │   KEEP SATISFIED         │
   POWER          │   (the actual deciders)  │   (don't surprise them)  │
                  │                          │                          │
                  ├──────────────────────────┼──────────────────────────┤
                  │                          │                          │
   LOW            │   KEEP INFORMED          │   MONITOR                │
   POWER          │   (your loud allies)     │   (don't waste cycles)   │
                  │                          │                          │
                  └──────────────────────────┴──────────────────────────┘
Manage closely — High Power, High Interest

The deciders. They will say yes or no. Most of your time goes here. 1:1 alignment before the decision moment. Never let them be surprised in a group meeting.

Keep satisfied — High Power, Low Interest

Senior people whose space you're stepping into but who don't care about this specific decision yet. The risk: they hear about it secondhand and feel disrespected, then start caring (and blocking). Pre-brief them on what you're doing and why. Don't ask for input you won't use.

Keep informed — Low Power, High Interest

The team. The folks doing the work. They can't kill it but they can slow it. Visibility + giving them a role kills 80% of friction. Channel them into the decision via the deciders, not as a parallel campaign.

Monitor — Low Power, Low Interest

Don't ignore — monitor. Quarterly update is plenty. The risk is they shift into one of the other quadrants (someone gets promoted, scope expands) and you're caught off guard.


Inputs needed (interview if missing)

  1. The decision. "Migrate to Linear." "Sunset legacy product." "Reorg sales by vertical." Specific.
  2. Decision moment. When does this need to be approved? By whom?
  3. The full cast. Everyone who has an opinion, a budget, a team affected, or a meeting on this. Names + roles.
  4. What you already know about each. Stated stance, recent comments, past behavior on similar decisions. (If you don't know — that's the action.)

Output format

2x2 placement table
StakeholderRoleQuadrantStanceWhat they care aboutYour move this week
Sarah ChenCTOManage closelySkepticReliability + team retention1:1 Tuesday, lead with retention data, ask for her objections before the all-hands
..................
Stance legend
  • Champion — already advocating; ask them to advocate publicly
  • Supporter — quietly in favor; ask them to speak up at the decision moment
  • Neutral — no strong view; lowest priority (don't burn cycles converting)
  • Skeptic — has reservations but persuadable; get the objection on the table
  • Blocker — will actively oppose; decide whether to convert, route around, or escalate
  • Unknown — find out, then update
Coalition sketch (3–5 lines)

Who needs to be aligned, in what order, before the decision moment. Example:

"Win Sarah by EOW (she's the blocker). Once Sarah's neutral, Mark (champion) will close Priya. Don't engage Tom — he won't care unless Sarah escalates."


Process

  1. List everyone. Cast the net wide first. Don't pre-filter.
  2. Place each on the grid. Be honest about power — title isn't always power.
  3. Assign stance. If you don't know, mark "unknown" — that's a data point.
  4. For each Manage Closely person: what do they care about (their KPI, recent stress, public commitments), and the one move this week.
  5. Sequence the coalition. Who must align first to unlock the next. Usually = blockers and high-power skeptics, before champions.
  6. Reality-check. Ask: "If I do nothing else, would this decision still pass?" If yes, you over-mapped — simplify. If no, your top 3 actions are obvious.

Show full SKILL.md (545 more words)Show less

Worked example

Decision: Migrate engineering + product from Jira to Linear by 5/30. Decision moment: EOD Friday (today is Tuesday) — Mark approves or denies the budget swap.

StakeholderRoleQuadrantStanceWhat they care aboutMove this week
Mark ChenVP Eng (decider)Manage closelyNeutral → SkepticTeam retention, no rollout drama30-min 1:1 Weds. Lead with NPS data (4/10) + 2 pilot teams' productivity wins. Pre-empt his "what about 6 yrs of history" objection.
Priya PatelPM Lead (pilot)Manage closelyChampionFaster ship velocityAsk her to write a 1-pg "what we learned in pilot" by Thurs AM. Mark reads it before our 1:1.
Alex KimEng Director (Platform)Manage closelySkepticMigration of custom workflowsLoop in by Weds. Offer Platform team as the 3rd pilot. Convert from skeptic by giving them control.
Tom ReillyCFOKeep satisfiedUnknownCost, contract riskDrop a 3-line note Tues PM: "Net savings $18K/yr, decision Fri, no surprises." Don't ask for input.
Sarah WuHead of PeopleKeep satisfiedUnknownAnything that affects team moraleSame as Tom — short pre-brief Wed AM.
Eng Team (60ppl)IC engineersKeep informedMixed (mostly Supporters per pilot data)Less tooling frictionMark posts in #eng-all after Friday decision. Don't run a parallel campaign — let Mark own the comms.
Jira AE (vendor)ExternalMonitorBlockerRenewalIgnore until decision is made. Then 1 email to cancel.
Coalition sketch

Tuesday PM: pre-brief Tom + Sarah (kills the "I didn't know" risk). Wednesday: 1:1 with Mark (the actual decision). Bring Priya's pilot write-up. Wednesday PM: convert Alex by offering Platform as pilot #3. Thursday: Mark + Priya + Alex 30-min sync to lock the migration plan. Friday: Mark says yes. Decision goes out.

If Mark is still skeptical Wednesday, escalate to CTO with the pilot data. Don't let it drift to Monday — the renewal auto-renews 5/30.


Common mistakes to avoid

  • Mapping by title, not by power. The CTO might not care about this; the staff eng who's been there 8 years might be the actual blocker.
  • Skipping the "unknown" stance. Unknown is honest. "I think they're supportive" without evidence is wishful.
  • Over-engaging Monitor quadrant. Don't burn cycles converting people who don't care and can't block.
  • Treating champions as a finish line. Champions need fuel (data, talking points, public moments). Map what you give them, not just that they exist.
  • No coalition sequence. Knowing who matters isn't enough. You need the order.
  • Conflating loud with powerful. The person who tweets the most opinions often has the least decision power. Map carefully.

When to use

  • Cross-functional decisions with 3+ stakeholders
  • Reorgs, launches, sunsets, vendor changes
  • Any "we need exec buy-in" moment
  • Before a board meeting where you're presenting
  • When a project is stuck and you suspect the blocker is political, not technical

When NOT to use

  • Solo decisions (just decide)
  • Decisions inside your own team where you control the outcome
  • Reversible / low-stakes calls (don't formalize the politics if the worst case is "we change our mind")

Pairs well with

  • Meeting Prep Kit — once you've mapped the room, prep each 1:1 with the right talking points + objections
  • Decision Memo Builder — the memo is the artifact that aligns the coalition; build the map first, the memo second
  • SCPR Framework — the Situation/Complication framing should reflect what the key stakeholders already believe

© sruthir28, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in stakeholder-map of sruthir28/enterprise-ai-skills.

Open the folder on GitHubat commit ae8fe60

Compare with similar skills

Stakeholder Map next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Stakeholder Map compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Stakeholder Map this skillsruthir28/enterprise-ai-skills148—~2.4kAutomated safety check: PassMIT
Stakeholder Mapphuryn/pm-skills27k—~625Automated safety check: PassMIT
Stakeholder Mappingdeanpeters/Product-Manager-Skills7.2k—~3.5kAutomated safety check: PassCustom licence
Stakeholder Mapborghei/Claude-Skills881—~2kAutomated safety check: PassMIT
Feature Maponyx-dot-app/onyx32k—~459Automated safety check: PassCustom licence
Token Mapnexu-io/open-design100k—~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Stakeholder Map

    phuryn/pm-skills

    Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan.

    27k GitHub stars~625 tokensUpdated 23 days ago
    Auto-check passed
  • Stakeholder Mapping

    deanpeters/Product-Manager-Skills

    Prioritize stakeholders using two complementary grids. An agent skill from deanpeters/Product-Manager-Skills.

    7.2k GitHub stars~3.5k tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Stakeholder Map

    borghei/Claude-Skills

    Map stakeholders by power × interest and design a communication plan that prevents surprise objections.

    881 GitHub stars~2k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Feature Map

    onyx-dot-app/onyx

    Use the Onyx feature map (.agents/feature-map/) to learn what a product surface does, the code behind it, and what a change can break.

    32k GitHub stars~459 tokensUpdated today
    Auto-check passed
  • Token Map

    nexu-io/open-design

    Map an extracted Figma / source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.

    100k GitHub stars~1.4k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Maps Geography

    asgeirtj/system_prompts_leaks

    Accurate maps from real geo data — use for any map, or whenever geography would make a good graphic for a deliverable

    69k GitHub stars~717 tokensUpdated today
    Auto-check passed

More from sruthir28/enterprise-ai-skills

All 14 skills in this repo
  • Storyline Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style storyline framework for building presentation decks.

    148 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • AI Use Case Scorer

    sruthir28/enterprise-ai-skills

    Score and prioritize AI use cases for your own job. An agent skill from sruthir28/enterprise-ai-skills.

    148 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Decision Memo Builder

    sruthir28/enterprise-ai-skills

    Builds a 1-page decision memo (context → options → recommendation → risks → ask) enforcing McKinsey memo DNA — brutal brevity, SCP storyline clarity, decision-forcing output, evidence density.

    148 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Deck Pipeline

    sruthir28/enterprise-ai-skills

    Multi-agent pipeline that builds a polished presentation deck from a single topic.

    148 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Issue Tree Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style issue tree framework for breaking down complex problems into MECE (Mutually Exclusive, Collectively Exhaustive) components.

    148 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Mckinsey Charts

    sruthir28/enterprise-ai-skills

    Generate McKinsey-style consulting charts as native python-pptx objects (editable inside PowerPoint).

    148 GitHub stars~999 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Stakeholder Map

What does Stakeholder Map do?

Map the people who can make or break a decision onto a Power/Interest grid, with each named stakeholder's stance (champion / skeptic / blocker / unknown), what they care about, and the single…. Stakeholder Map is an agent skill from sruthir28/enterprise-ai-skills. Map the people who can make or break a decision onto a Power/Interest grid, with each named stakeholder's stance (champion / skeptic / blocker / unknown), what they care about, and the single influence move you'll make for them.

How do I install Stakeholder Map in Claude Code?

Run `npx skills add sruthir28/enterprise-ai-skills --skill stakeholder-map -a claude-code`. Or copy the skill folder (stakeholder-map in sruthir28/enterprise-ai-skills) into .claude/skills/stakeholder-map in your project. Claude Code loads it when a task matches its description.

How do I install Stakeholder Map in Codex?

Run `npx skills add sruthir28/enterprise-ai-skills --skill stakeholder-map -a codex`. Or copy the skill folder (stakeholder-map in sruthir28/enterprise-ai-skills) into .agents/skills/stakeholder-map in your project. Codex loads it when a task matches its description.

Can I use Stakeholder Map in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sruthir28/enterprise-ai-skills --skill stakeholder-map -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stakeholder-map, .gemini/skills/stakeholder-map, .github/skills/stakeholder-map and .opencode/skills/stakeholder-map in your project.

What does Stakeholder Map need to run?

SKILL.md names no scripts, command-line tools or credentials: Stakeholder Map is instructions for the agent only.

Does Stakeholder Map access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Stakeholder Map safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Stakeholder Map use?

Stakeholder Map is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Stakeholder Map use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Stakeholder Map?

Skills that share tags, products or a category with Stakeholder Map: Stakeholder Map (phuryn/pm-skills, 27k stars), Stakeholder Mapping (deanpeters/Product-Manager-Skills, 7.2k stars), Stakeholder Map (borghei/Claude-Skills, 881 stars) and Feature Map (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Stakeholder Map?

sruthir28 (a GitHub user) maintains it in sruthir28/enterprise-ai-skills, which has 148 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 1, 2026.

Source: sruthir28/enterprise-ai-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.