strategic-partner MCP — Use Cases, Install & Live Demo

Why use it

Key features

Premise challenge against 4 trigger conditions before any work starts
Forced 'Path A/B/C' alternatives with tradeoffs — no single-option proposals
Confidence labels: [SAFE] vs [RISK] on recommendations
Advisory Completion Gate — 5 conditions must hold before executor prompt is crafted
14 named cognitive heuristics applied to specific decision types

Live Demo

What it looks like in practice

strategic-partner-skill.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "strategic-partner-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/strategic-partner",
        "~/.claude/skills/strategic-partner"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "strategic-partner-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/strategic-partner",
        "~/.claude/skills/strategic-partner"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "strategic-partner-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/strategic-partner",
        "~/.claude/skills/strategic-partner"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "strategic-partner-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/strategic-partner",
        "~/.claude/skills/strategic-partner"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "strategic-partner-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/strategic-partner",
        "~/.claude/skills/strategic-partner"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "strategic-partner-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/JimmySadek/strategic-partner",
          "~/.claude/skills/strategic-partner"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add strategic-partner-skill -- git clone https://github.com/JimmySadek/strategic-partner ~/.claude/skills/strategic-partner

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use strategic-partner

Run a decision through the advisor before touching code

👤 Tech leads and founders who suspect they'd regret building too soon ⏱ ~30 min intermediate

When to use: You're about to ask Claude Code to build something substantial. Pause and consult the advisor first.

Prerequisites

Skill cloned — git clone https://github.com/JimmySadek/strategic-partner ~/.claude/skills/strategic-partner

Flow

Open the advisory session

Using strategic-partner — I'm about to add a queue system to handle email sends. Challenge my premise first.✓ Copied

→ Claude probes whether a queue is actually needed vs simpler alternatives
Receive Path A/B/C

Give me three paths with tradeoffs.✓ Copied

→ Three distinct paths, each labeled [SAFE] or [RISK], with honest downsides
Cross Completion Gate

I pick Path B. Prepare the executor prompt.✓ Copied

→ Gate check runs; if conditions aren't met, you're pushed back to advisory
Hand off to executor

Open a fresh Claude Code session and paste the executor prompt.✓ Copied

→ Execution session works with clean context

Outcome: Work that's been decided deliberately rather than drifted into.

Pitfalls

Using the advisor as a rubber stamp — If you're always picking 'Path A — do what I said', the premise challenge isn't working — provide real context

Combine with: github

Run a weekly strategy review with the persistent advisor

👤 Solo operators without a real chief-of-staff ⏱ ~30 min beginner

When to use: Friday afternoon, closing out the week.

Flow

Review decisions made this week

strategic-partner — review this week's advisory log. Which decisions do I now have evidence to revise?✓ Copied

→ Specific call-outs of decisions where execution revealed something new
Plan next week

What's the one decision next week that most deserves premise challenge?✓ Copied

→ Pinpoint rather than a to-do list

Outcome: A weekly audit that compounds across months.

Combine with: planning-with-files

Combinations

Pair with other MCPs for X10 leverage

strategic-partner-skill + planning-with-files

Persist the advisor's decision log across sessions in findings.md / progress.md

Use planning-with-files — keep decisions.md updated every advisory session.✓ Copied

strategic-partner-skill + github

When executor session commits, reference the decision from advisor log in the PR body

After executor finishes, link the advisor decision ID in the PR description.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call
premise_challenge	intended work + context	Before any substantial build
forced_alternatives	problem statement	Once premise passes; before committing to one path
completion_gate	chosen path + context	Before crafting executor prompt
executor_prompt_craft	decision + context	Handoff to execution
decision_log	current session state	Throughout advisory session

Cost & Limits

What this costs to run

API quota: None
Tokens per call: Advisor sessions carry persistent context — can grow
Monetary: Free — skills are local files
Tip: Trim the decision log periodically; stale decisions bloat context.

Security

Permissions, secrets, blast radius

Credential storage: No credentials — pure prompts

Data egress: None

This skill deliberately slows you down on important decisions. That's the feature — don't work around it.

Troubleshooting

Common errors and fixes

Skill not invoked — Claude jumps to building

Say 'use strategic-partner' explicitly; the skill is the brake.

Verify: ls ~/.claude/skills/strategic-partner/SKILL.md

SKILL.md frontmatter wrong

Re-clone; description drives activation.

Verify: head ~/.claude/skills/strategic-partner/SKILL.md

Wrong trigger keywords — no premise challenge happens

Phrase as 'challenge my premise' or 'advisor mode' explicitly; 'help me build X' skips advisory.

Alternatives

strategic-partner vs others

Alternative	When to use it instead	Tradeoff
planning-with-files	You want disk-based progress memory rather than decision gating	Complementary — different purposes
Carmack Council	You want multi-expert review rather than chief-of-staff persona	Different phase — Council reviews, SP decides upstream

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills