/ 目录 / 演练场 / swing-skills
● 社区 TheStack-ai ⚡ 即开即用

swing-skills

作者 TheStack-ai · TheStack-ai/swing-skills

6 cognitive firewalls for AI agents — clarify, research, options, review, trace, mortem — each targeting a named bias: premature closure, hallucination, anchoring, confirmation, black-box reasoning, optimism.

A skill pack of 6 self-contained cognitive tools that plug specific biases. swing-clarify forces 5W1H on ambiguous requests. swing-research runs a 4-stage verified pipeline with S/A/B/C source grading. swing-options generates 5 probability-weighted alternatives including unconventional ones. swing-review does structured devil's advocacy (steel-man first, then 3-vector attack). swing-trace inventories assumptions and surfaces weakest links. swing-mortem does prospective failure analysis.

为什么要用

核心特性

实时演示

实际使用效果

swing-skill.replay ▶ 就绪
0/0

安装

选择你的客户端

~/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
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.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 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

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
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标,然后选 "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
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

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

Continue 使用服务器对象数组,而非映射。

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

加入 context_servers。Zed 保存后热重载。

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

一行命令搞定。用 claude mcp list 验证,claude mcp remove 卸载。

使用场景

实战用法: 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

何时使用: A stakeholder dropped a short, ambiguous request.

前置条件
  • Skill installed — git clone https://github.com/TheStack-ai/swing-skills ~/.claude/skills/swing-skills
步骤
  1. Run swing-clarify
    Use swing-clarify. Request: 'make the dashboard better'. Decompose 5W1H.✓ 已复制
    → What/who/when/where/why/how decomposition + clarifying questions

结果: A concrete scope you can actually execute against.

搭配使用: agent-skill-tdd-skill

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

👤 Analysts, researchers ⏱ ~45 min intermediate

何时使用: You want a defensible brief, not hallucinated bullet points.

步骤
  1. 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.✓ 已复制
    → Claim table with tier + source

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

注意事项
  • B/C-tier claims treated as fact — The grade is there to weight; read them as weaker
搭配使用: firecrawl · brave-search

Break anchoring by generating five weighted alternatives

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

何时使用: You've got a favorite solution and want a sanity check.

步骤
  1. Run swing-options
    Use swing-options. Decision: which DB for our new service? Give 5 probability-weighted options including unconventional.✓ 已复制
    → 5 options with weights + rationale

结果: 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

何时使用: Before committing to a plan or design.

步骤
  1. Run swing-review
    Use swing-review on design.md. Steel-man it first, then attack from correctness, operability, and cost.✓ 已复制
    → Strong version of the design, then 3 attack surfaces

结果: 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

何时使用: Right before kickoff on risky work.

步骤
  1. Run swing-mortem
    Use swing-mortem. Assume plan.md failed in 6 months. List 5 failure scenarios with leading indicators.✓ 已复制
    → 5 scenarios + early-warning signals

结果: 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

何时使用: A decision feels off but you can't articulate why.

步骤
  1. Run swing-trace
    Use swing-trace on this decision: 'we'll use Kafka'. Inventory assumptions; call out the weakest.✓ 已复制
    → Assumption list ranked by risk

结果: The weakest link exposed before it breaks.

组合

与其他 MCP 搭配,撬动十倍杠杆

swing-skill + skills-skill-6

Layer Swing's firewalls with InfraNodus graph analysis

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

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
swing-clarify ambiguous request Any vague task 0
swing-research question Research with defensibility 0
swing-options decision Anchoring risk 0
swing-review plan/design Pre-commit review 0
swing-trace decision Reasoning audit 0
swing-mortem plan Before kickoff 0

成本与限制

运行它的成本

API 配额
None
每次调用 Token 数
Moderate per skill (research is highest)
费用
Free
提示
Use swing-clarify by default; others on-demand

安全

权限、密钥、影响范围

凭据存储: None
数据出站: None beyond your LLM calls

故障排查

常见错误与修复

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?'

替代方案

swing-skills 对比其他方案

替代方案何时用它替代权衡
InfraNodus skillsYou want graph-based thinking augmentationNo bias-specific firewalls
Manual reviewOne-off trivial decisionsNo structure

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills