agentleFS
KirKruglovKirKruglov/claude-project-manager/skills/generate-stakeholder-map/SKILL.md

generate-stakeholder-map

Skill6 starsChanged 7 months agoMITView on GitHub

Generates a structured stakeholder map for IT project management (Phase 1 —

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. About 0 are common, 17 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the request is in Russian → use templates with the -ru suffix

    line 29
  2. Distinctive:

    All output (headings, labels, agent messages) must match the detected language.

    line 31
  3. Distinctive:

    If none of the files is available — ask a clarifying question (see Step 1).

    line 44
  4. Distinctive:

    Before checking files: if the request includes tasks outside this skill's scope (generating a communications plan, contacting stakeholders, …

    line 60
  5. Distinctive:

    Do not attempt to perform out-of-scope tasks.

    line 64
  6. Distinctive:

    Check for files in the following order:

    line 66
  7. Distinctive:

    If the user's message already contains stakeholder data (names, roles, influence/interest levels) — skip the A/B prompt and proceed …

    line 71
  8. Distinctive:

    If none of the files exist AND no inline data is provided — show in chat:

    line 74
  9. Distinctive:

    Wait for user response. Do not proceed without data.

    line 83
  10. Distinctive:

    Read available files and extract the following per stakeholder:

    line 89
  11. Distinctive:

    If data for a field is insufficient:

    line 124
  12. Distinctive:

    Add a row to Section 5 (Open Questions) with: the missing field description, the stakeholder name, Status = Open.

    line 126
  13. Distinctive:

    If there are more than 15 stakeholders — group minor ones (Monitor quadrant) into a single entry "Other Interested Parties".

    line 144
  14. Distinctive:

    If Section 5 has rows — list them: "Open questions requiring clarification: [list]."

    line 154
  15. Distinctive:

    If the original request included out-of-scope tasks — note each one explicitly: "[Task X] is outside this skill's scope.

    line 156
  16. Distinctive:

    Does not send communications to stakeholders — that is the task of generate-comm-plan and send-email

    line 187
  17. Distinctive:

    Does not generate a communications plan — only the stakeholder map

    line 188
  18. Distinctive:

    No Miro integration (MCP does not exist as of April 2026)

    line 189
  19. Very specific:

    If stakeholder data is insufficient — marks [clarify], does not fabricate

    line 191

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Skill: generate-stakeholder-map

Generates a stakeholder map for IT projects (Phase 1 — Initiation). Reads available project files, extracts stakeholder data, and produces a structured stakeholder-map.md with a summary table and narrative blocks per stakeholder.


Triggers

Russian: «создай карту стейкхолдеров», «сформируй карту стейкхолдеров», «идентифицируй стейкхолдеров», «подготовь карту заинтересованных сторон», «кто стейкхолдеры проекта», «нужна карта стейкхолдеров» English: "generate stakeholder map", "create stakeholder map", "identify stakeholders", "stakeholder analysis", "map project stakeholders", "who are the stakeholders"


Language Detection

Determine the language of the user's request:

  • If the request is in Russian → use templates with the -ru suffix
  • Otherwise → use templates with the -en suffix
  • All output (headings, labels, agent messages) must match the detected language.

Input

DataRequiredSourceNotes
Client answersno01-initiation/questionnaire-client.mdPrimary source: Block 5 + stakeholder mentions throughout
Project charterno01-initiation/project-charter.mdSecondary source (artifact from generate-charter MVP skill)
Team listnoinput/team-list.mdOrg structure, roles, contacts
Manual inputnoChatIf no files found — request data directly

If none of the files is available — ask a clarifying question (see Step 1).


Output

FileProject pathMode
stakeholder-map.md01-initiation/generate

Instructions

Step 1 — Locate Available Data Sources

Before checking files: if the request includes tasks outside this skill's scope (generating a communications plan, contacting stakeholders, creating a risk register, etc.) — complete the stakeholder map first, then explicitly note at the end of Step 4: "[Task X] is outside this skill's scope. Use [relevant skill] for that." Do not attempt to perform out-of-scope tasks.

Check for files in the following order:

  1. 01-initiation/questionnaire-client.md
  2. 01-initiation/project-charter.md
  3. input/team-list.md

If the user's message already contains stakeholder data (names, roles, influence/interest levels) — skip the A/B prompt and proceed directly to Step 2.

If none of the files exist AND no inline data is provided — show in chat:

No project input files found. Stakeholder data is needed to create the map.
Choose an option:
A) Provide a path to a file with stakeholder data
B) Enter data directly: name, role, influence level, and interest for each stakeholder

Wait for user response. Do not proceed without data.


Step 2 — Extract Stakeholder Data

Read available files and extract the following per stakeholder:

FieldSourcesPriority
Namequestionnaire-client.md Block 5, project-charter.mdquestionnaire > charter
Role / Titlequestionnaire-client.md, team-list.mdquestionnaire > team-list
Organizationquestionnaire-client.md—
CategoryDetermine independently (see list below)—
Influence levelInfer from context—
Interest levelInfer from context—
Contact / Emailquestionnaire-client.md, team-list.md—
Interests and expectationsquestionnaire-client.md Block 5, Block 2—
Concerns and risksquestionnaire-client.md Block 4—
Communication frequencyquestionnaire-client.md Q20 equivalent—

Stakeholder categories:

  • Sponsor
  • Client
  • Project Team
  • Decision Maker
  • External User
  • Pilot Client
  • Consultant / Regulator

Influence and interest levels: High / Medium / Low.

Power/Interest quadrant — determine automatically:

  • High Power + High Interest → Manage Closely
  • High Power + Low Interest → Keep Satisfied
  • Low Power + High Interest → Keep Informed
  • Low Power + Low Interest → Monitor
  • Medium Power + High Interest → Keep Informed
  • Medium Power + Low Interest → Monitor (Treat Medium as the lower tier for quadrant assignment.)

If data for a field is insufficient:

  • Mark [clarify] in the corresponding table cell (e.g., the Contact column) AND in the narrative block.
  • Add a row to Section 5 (Open Questions) with: the missing field description, the stakeholder name, Status = Open.

Step 3 — Generate the Stakeholder Map

  1. Determine language → select template stakeholder-map-{lang}.md.
  2. Fill in metadata:
PlaceholderSource
{{project_name}}Project CLAUDE.md or user request
{{pm_name}}CLAUDE.md (if available)
{{date}}Current date (YYYY-MM-DD)
{{version}}1.0
  1. Fill in the summary stakeholder table — one row per stakeholder.
  2. Fill in the narrative block per stakeholder (role, expectations, concerns, strategy, frequency).
  3. If there are more than 15 stakeholders — group minor ones (Monitor quadrant) into a single entry "Other Interested Parties".

Step 4 — Save and Report

  1. Save file: 01-initiation/stakeholder-map.md.
  2. Show in chat:
    • What was created: "Stakeholder map saved as [filename] in [path]."
    • Number of stakeholders, quadrant distribution
    • If Section 5 has rows — list them: "Open questions requiring clarification: [list]."
    • Next step: "Stakeholder map ready. Suggested next steps: generate-risk-register (risk register) or generate-comm-plan (communications plan — after project plan is approved)."
    • If the original request included out-of-scope tasks — note each one explicitly: "[Task X] is outside this skill's scope. Use [relevant skill] for that."
  3. Log to logs/log.md: date, skill, created file, number of stakeholders.

Templates

FilePurpose
templates/stakeholder-map-ru.mdArtifact template (RU)
templates/stakeholder-map-en.mdArtifact template (EN)

Dependencies

Reads:

  • 01-initiation/questionnaire-client.md — primary source (from generate-questionnaire)
  • 01-initiation/project-charter.md — secondary source (from generate-charter, MVP)
  • input/team-list.md — org structure

Passes data to:

  • generate-comm-plan — communications plan is built on the stakeholder map
  • coordinate-meeting — attendee lists for meetings
  • generate-approval-letter — approval addressees

Constraints

  • Mode B: agent prepares a draft, human reviews and approves
  • Does not send communications to stakeholders — that is the task of generate-comm-plan and send-email
  • Does not generate a communications plan — only the stakeholder map
  • No Miro integration (MCP does not exist as of April 2026)
  • Handles one project per invocation
  • If stakeholder data is insufficient — marks [clarify], does not fabricate
  • Maximum 15 stakeholders in detailed blocks; additional ones grouped as "Other Interested Parties"

Changelog

DateVersionChange
2026-04-061.0Skill created. Three data sources: questionnaire-client, project-charter, team-list. Template: table + narrative blocks. No Miro.
2026-04-061.1Post-eval fixes (3/6 → 6/6 expected): added inline-data detection in Step 1 (skip A/B when data provided); added Medium Power quadrant rules; added [clarify] to Contact column + Section 5 auto-fill; added out-of-scope guard rail in Steps 1 and 4; added Section 5 open questions reporting.

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.