agentleFS
CSPulseCSPulse/customer-success-skills/skills/stakeholder-map/SKILL.md

stakeholder-map

Skill2 starsChanged 3 months agoMITView on GitHub

Use when the user says "stakeholder map", "who actually decides", "who signs this", "map the account", "we are single-threaded", "who do I need to know". Produces a map sorted by what each person can do to the outcome, not title, with a met / not met column, a single-threading count and a dated route to close each gap. Not for a champion who just left (use champion-loss) or for the renewal call itself (use renewal-risk).

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brainstorm-experiments-existing, brainstorm-ideas-new and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • skytiger6724Skill

    brainstorm-experiments-existing

    Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments.

    Also in 6 projects that use this

  • skytiger6724Skill

    brainstorm-ideas-new

    Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives. Use when starting product discovery for a new product, exploring features for a startup idea, or doing initial ideation.

    Also in 6 projects that use this

  • 45ckSkill

    pestle-analysis

    Also in 6 projects that use this

  • About-IntelligenceSkill

    positioning-ideas

    Brainstorm product positioning ideas differentiated from competitors.

    Also in 6 projects that use this

  • About-IntelligenceSkill

    product-name

    Brainstorm 5 unique, memorable product names with rationale aligned to brand values and target audience.

    Also in 6 projects that use this

  • launchapp-devSkill

    interview-script

    Create a structured user interview script with warm-up, core exploration, and wrap-up sections. Use when preparing for user research interviews to ensure consistent, insightful conversations.

    Also in 7 projects that use this

  • +5 more from skytiger6724
  • +1 more from About-Intelligence

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user gave names and roughly what they do, go straight to "Do this".

    line 13
  2. Distinctive:

    Say who decides first: If the economic buyer is aware-of or assumed, that is the account's largest risk and goes at the top of the output.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Stakeholder Map

An org chart says what people are called. This says what each person can do to the account, who the user has really met, and what to do about the gaps.

Start here

If the user gave names and roughly what they do, go straight to "Do this". If an "Account context" block exists in the conversation, use it for who signs in this business.

Otherwise ask for these in ONE message, then proceed with whatever comes back (do not wait for all three):

  1. The people the user knows on the account, with role and last contact date
  2. Who the user thinks signs, and whether they have ever spoken to them
  3. Anything that changed lately: new executive, someone gone quiet, someone left

Gaps are the output here, not a blocker.

Do this

  1. Sort by position, not title. Economic buyer (controls the budget), champion (spends their own credibility for you), sceptic (argued against it or would), user, coach (explains how the org works, may not like the product), gatekeeper (procurement, security, legal; can block, cannot approve). One person can hold two.
  2. Add the met column. Met means a real conversation, not a group call they attended. Aware of means known, never spoken to. Assumed means the role exists but cannot be named.
  3. Say who decides first. If the economic buyer is aware-of or assumed, that is the account's largest risk and goes at the top of the output.
  4. Count the threads. One relationship is no recovery path. Two in the same team is single-threading in disguise. Three or more across functions is coverage. Then ask: if the champion left this month, who inside the customer could explain why they bought?
  5. Track movement. New arrivals, departures, remit changes, and anyone who used to reply in a day and now takes a week.
  6. Give each gap a route and a date: an introduction from the champion, a review with the sponsor invited, an exec-to-exec ask, or a piece of value worth their fifteen minutes. Say honestly which gaps may not close.

Output

WHO DECIDES: [Name, role] | Met: yes / no / only through [person]
Threads: [n] relationships, [single / disguised single / multi] threaded
Sceptic: [name or "not identified, map incomplete"]

Map
| Person | Position | Met | Last contact | Stance (said/seen/inferred) |

Changed since last look
- [arrival / departure / quiet / remit change, with date]

Gaps and routes
- [gap] | Route: [how] | Owner: [who] | By: [date]

What I could not check
- [gap]

A filled example is in examples/sample.md. Match its length and specificity: real dates, real counts, no placeholders in the final output.

Rules

  • Every account has a sceptic. A map without one is incomplete, not lucky, because the person nobody thought about is the one who surfaces at signature.
  • Seniority is not influence. The signer is often not the most senior name, so ask what happens to the renewal if this person says no.
  • A group call is not a relationship. Someone who sat on a webinar-style call has not been met, and counting them hides the real gap.
  • A champion's optimism is evidence about the champion. Tag it said and name whose mouth it came from.
  • Sponsor silence while the working team stays engaged usually means the decision moved above the user's line of sight.
  • A gap without a route is only a description. The gap was already obvious; the route and date are the work.
  • The map goes stale. An organization that reorganized last quarter is not the one on the page, so date the map and re-check it at every renewal checkpoint.

Related (only if installed)

champion-loss when the sponsor left. exec-conversation to prepare the meeting once it is granted. renewal-risk to turn the map into a call.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.