Strategy Skills

io.github.eterdisPublished by GitHub account eterdisv1.0.1Updated Oct 24, 2026

11 open strategy frameworks as AI-guided prompts for any MCP client.

Overview

AI-generated overview

Local MCP server that exposes 11 open strategy frameworks as AI-guided prompts, plus a company-context template resource.

What you can do
  • Run strategy frameworks as guided prompts: an orchestrator entry point, strategic diagnostic, causal chain mapping, VRIO advantage test, PESTEL scan, market positioning, Wardley mapping, culture assessment, first-principles strategy, Playing to Win cascade, pre-mortem and a Track Two innovation setup
  • Choose a mode for each skill prompt: diagnostic, review or alert
  • Read a company-context template resource for a living document that accumulates strategic intelligence across sessions
When to use it
Useful when you want an assistant to walk through structured business-strategy analysis — assessing a market position, testing whether an advantage is durable, or stress-testing a plan — instead of improvising a framework from scratch.
Requirements
Runs as a local process over stdio, installed via npx from the npm package @eterdis/strategy-skills-mcp; Node.js and network access for the package download are needed. No authentication, environment variables or headers are declared. Desktop clients only.
Before you install
The prompts guide analysis but the output is AI-generated advice, not consulting; verify conclusions before acting on them. The company-context document may hold sensitive strategic information, so review what you paste into sessions.

Installation

In SourceWeft

  1. Open Strategy Skills in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@eterdis/strategy-skills-mcp

MCP server that exposes 11 open strategy frameworks as AI-guided prompts. Built on 20 years of consulting practice.

Install

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "strategy-skills": {      "command": "npx",      "args": ["-y", "@eterdis/strategy-skills-mcp"]    }  }}

Claude Code

bash
claude mcp add strategy-skills -- npx -y @eterdis/strategy-skills-mcp

Cursor / VS Code

Add to MCP settings:

json
{  "mcpServers": {    "strategy-skills": {      "command": "npx",      "args": ["-y", "@eterdis/strategy-skills-mcp"]    }  }}

What you get

12 prompts:

PromptWhat it does
strategyEntry point — orchestrator that coordinates all skills
strategy-diagnosticAI-guided strategic assessment
strategy-mapTwo-directional causal chain analysis
vrio-analysisTest whether competitive advantages are real and durable
environmental-radarContinuous PESTEL environmental scan
market-positionCompetitive positioning diagnostic
wardley-mapComponent evolution mapping
culture-assessmentSurface real culture vs. stated culture
first-principles-strategyFind the theoretical maximum
playing-to-winLafley/Martin five-choice strategy cascade
pre-mortemIdentify how the plan will fail before it does
protoloop-setupTrack Two innovation system

Each skill prompt accepts an optional mode argument: diagnostic, review, or alert.

1 resource:

ResourceWhat it is
company-context-templateTemplate for the living document that accumulates strategic intelligence across sessions

License

CC BY 4.0 — use freely, including commercially. Attribution to Eterdis AS required.

Links

Source: mcp-server/README.md at commit 8bd22e9

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.