swing-skills MCP — Use Cases, Install & Live Demo

Why use it

Key features

6 skills, each tied to a specific cognitive failure mode
Chainable or standalone
swing-research uses S/A/B/C claim tiering
swing-review does steel-manning before attacking (no straw-men)
swing-mortem assumes your plan already failed and diagnoses why

Live Demo

What it looks like in practice

swing-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": {
    "swing-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/TheStack-ai/swing-skills",
        "~/.claude/skills/swing-skills"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

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

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

VS Code → Cline → MCP Servers → Edit

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

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

~/.codeium/windsurf/mcp_config.json

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

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "swing-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/TheStack-ai/swing-skills",
        "~/.claude/skills/swing-skills"
      ]
    }
  ]
}

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

~/.config/zed/settings.json

{
  "context_servers": {
    "swing-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/TheStack-ai/swing-skills",
          "~/.claude/skills/swing-skills"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add swing-skill -- git clone https://github.com/TheStack-ai/swing-skills ~/.claude/skills/swing-skills

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

Use Cases

Real-world ways to use swing-skills

Force clarification before an ambiguous task is executed

👤 Anyone who's seen AI agents gallop off in the wrong direction ⏱ ~10 min beginner

When to use: A stakeholder dropped a short, ambiguous request.

Prerequisites

Skill installed — git clone https://github.com/TheStack-ai/swing-skills ~/.claude/skills/swing-skills

Flow

Run swing-clarify

Use swing-clarify. Request: 'make the dashboard better'. Decompose 5W1H.✓ Copied

→ What/who/when/where/why/how decomposition + clarifying questions

Outcome: A concrete scope you can actually execute against.

Combine with: agent-skill-tdd-skill

Research a topic with graded sources, not a wall of links

👤 Analysts, researchers ⏱ ~45 min intermediate

When to use: You want a defensible brief, not hallucinated bullet points.

Flow

Run swing-research

Use swing-research. Question: 'what's the state of Rust in web backends (2025)?' Output claims with S/A/B/C grades.✓ Copied

→ Claim table with tier + source

Outcome: A brief you could defend to a skeptical stakeholder.

Pitfalls

B/C-tier claims treated as fact — The grade is there to weight; read them as weaker

Combine with: firecrawl · brave-search

Break anchoring by generating five weighted alternatives

👤 Decision-makers who notice they're anchoring ⏱ ~20 min beginner

When to use: You've got a favorite solution and want a sanity check.

Flow

Run swing-options

Use swing-options. Decision: which DB for our new service? Give 5 probability-weighted options including unconventional.✓ Copied

→ 5 options with weights + rationale

Outcome: A decision made from options, not one default.

Structured review: steel-man then attack from 3 vectors

👤 Teams wanting a real review, not rubber-stamps ⏱ ~30 min intermediate

When to use: Before committing to a plan or design.

Flow

Run swing-review

Use swing-review on design.md. Steel-man it first, then attack from correctness, operability, and cost.✓ Copied

→ Strong version of the design, then 3 attack surfaces

Outcome: A design that either holds or gets better.

Run a pre-mortem on a plan before execution

👤 PMs and leads about to green-light something important ⏱ ~30 min intermediate

When to use: Right before kickoff on risky work.

Flow

Run swing-mortem

Use swing-mortem. Assume plan.md failed in 6 months. List 5 failure scenarios with leading indicators.✓ Copied

→ 5 scenarios + early-warning signals

Outcome: Early-warning instrumentation built in from day one.

Expose the weakest assumption in a decision tree

👤 Engineers debugging reasoning, not just code ⏱ ~20 min intermediate

When to use: A decision feels off but you can't articulate why.

Flow

Run swing-trace

Use swing-trace on this decision: 'we'll use Kafka'. Inventory assumptions; call out the weakest.✓ Copied

→ Assumption list ranked by risk

Outcome: The weakest link exposed before it breaks.

Combinations

Pair with other MCPs for X10 leverage

swing-skill + skills-skill-6

Layer Swing's firewalls with InfraNodus graph analysis

After swing-review, run InfraNodus critical-perspective for graph-based critique.✓ Copied

swing-skill + agent-skill-tdd-skill

Clarify + research before the TDD flow

Start with swing-clarify + swing-research, then hand off to agent-skill-tdd.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call
swing-clarify	ambiguous request	Any vague task
swing-research	question	Research with defensibility
swing-options	decision	Anchoring risk
swing-review	plan/design	Pre-commit review
swing-trace	decision	Reasoning audit
swing-mortem	plan	Before kickoff

Cost & Limits

What this costs to run

API quota: None
Tokens per call: Moderate per skill (research is highest)
Monetary: Free
Tip: Use swing-clarify by default; others on-demand

Security

Permissions, secrets, blast radius

Credential storage: None

Data egress: None beyond your LLM calls

Troubleshooting

Common errors and fixes

swing-research cites sources that don't check out

Cross-check S-tier sources manually; lower grades are weaker by design

swing-review feels like a formality

Force adversarial framing: 'what would an angry senior engineer say?'

Alternatives

swing-skills vs others

Alternative	When to use it instead	Tradeoff
InfraNodus skills	You want graph-based thinking augmentation	No bias-specific firewalls
Manual review	One-off trivial decisions	No structure

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills