Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

unstuckunstuck 搜索

Agent Skill

unstuck 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

259

周安装

11

GitHub Stars

2,799

下载量

91
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:unstuck(unstuck 搜索)
来源仓库:https://github.com/q00/ouroboros
仓库路径:skills/unstuck
安装命令:
npx skills add https://github.com/q00/ouroboros --skill unstuck
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/q00/ouroboros --skill unstuck

简介

用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景快速定位候选结果。
  • 通过 npx skills add 命令从指定仓库安装并使用。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • unstuck 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

/ouroboros:unstuck

Break through stagnation with lateral thinking personas.

Usage

/ouroboros:unstuck [persona]

Trigger keywords: "I'm stuck", "think sideways"

Available Personas

PersonaStyleWhen to Use
hacker"Make it work first, elegance later"When overthinking blocks progress
researcher"What information are we missing?"When the problem is unclear
simplifier"Cut scope, return to MVP"When complexity is overwhelming
architect"Restructure the approach entirely"When the current design is wrong
contrarian"What if we're solving the wrong problem?"When assumptions need challenging

Instructions

When the user invokes this skill:

Load MCP Tools (Required first)

The Ouroboros MCP tools are often registered as deferred tools that must be explicitly loaded before use. You MUST perform this step before proceeding.

  1. Use the ToolSearch tool to find and load the lateral thinking MCP tool: ToolSearch query: "+ouroboros lateral"
  2. The tool will typically be named mcp__plugin_ouroboros_ouroboros__ouroboros_lateral_think (with a plugin prefix). After ToolSearch returns, the tool becomes callable.
  3. If ToolSearch finds the tool → use MCP mode below. If not → skip to Fallback section.

IMPORTANT: Do NOT skip this step. Do NOT assume MCP tools are unavailable just because they don't appear in your immediate tool list. They are almost always available as deferred tools that need to be loaded first.

Unstuck Steps

  1. Determine the context:

- What is the user stuck on? (Check recent conversation) - What approaches have been tried? - Which persona would help most?

  1. If a specific persona is requested, use it. Otherwise, choose based on context:

- Repeated similar failures → contrarian (challenge assumptions) - Too many options → simplifier (reduce scope) - Missing information → researcher (seek data) - Analysis paralysis → hacker (just make it work) - Structural issues → architect (redesign)

  1. Call the ouroboros_lateral_think MCP tool: Tool: ouroboros_lateral_think Arguments: problem_context: <description of the stuck situation> current_approach: <what has been tried> persona: "contrarian" (or chosen persona) failed_attempts: ["attempt1", "attempt2"] (previous failures)
  2. Present the lateral thinking result:

- Show the persona's approach summary - Present the reframing prompt - List the questions to consider - Suggest concrete next steps with a 📍 Next: action routing back to the workflow

Fallback (No MCP Server)

If the MCP server is not available, delegate to the matching agent:

  • ouroboros:contrarian - "What if we're solving the wrong problem?"
  • ouroboros:hacker - "Make it work, elegance comes later"
  • ouroboros:simplifier - "Cut scope to the absolute minimum"
  • ouroboros:researcher - "Stop coding. Read the docs."
  • ouroboros:architect - "Question the foundation. Rebuild if needed."

These agents use prompt-based lateral thinking without numerical analysis.

Example

User: I'm stuck on the database schema design

/ouroboros:unstuck simplifier

# Lateral Thinking: Reduce to Minimum Viable Schema

Start with exactly 2 tables. If you can't build the core feature
with 2 tables, you haven't found the core feature yet.

## Questions to Consider
- What is the ONE query your users will run most?
- Can you use a single JSON column instead of normalized tables?
- What if you started with flat files and added a DB later?

📍 Next: Try the approach above, then `ooo run` to execute — or `ooo interview` to re-examine the problem

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.54%
按下载量换算35

Claude

29.43%
按下载量换算27

Cursor

19.6%
按下载量换算18

Gemini CLI

9.82%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills