Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问许可证需确认审计通过

eurekaeureka 搜索

Agent Skill

eureka 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

1,211

周安装

52

GitHub Stars

1,470

下载量

424
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:eureka(eureka 搜索)
来源仓库:https://github.com/feiskyer/claude-code-settings
仓库路径:skills/eureka
安装命令:
npx skills add https://github.com/feiskyer/claude-code-settings --skill eureka
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/feiskyer/claude-code-settings --skill eureka

简介

eureka 捕获技术突破点并转化为可复用的知识资产,强调时效性。

  • 适用于研发团队在解决关键问题后快速沉淀经验与方法论。
  • 自动提取问题背景、洞察要点与前后对比,请求最小可运行示例。
  • 建议立即执行以避免上下文丢失,必要时主动澄清模糊细节。
  • eureka 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Eureka

Capture technical breakthroughs and transform them into actionable, reusable knowledge assets while context is fresh.

Process

1. Capture the Breakthrough

When invoked, immediately gather the essential details:

  • What was the problem? The specific challenge or blocker faced.
  • What was the insight? The key realization that unlocked the solution.
  • What changed? Concrete before/after differences (metrics, behavior, code).
  • Is there a minimal working example? Request one if not provided.

Ask clarifying questions if any of these are unclear, but act fast — capture while context is fresh.

2. Create the Breakthrough File

Create a structured markdown file at breakthroughs/YYYY-MM-DD-[brief-name].md using today's date and a concise kebab-case name derived from the breakthrough.

Use this template:

# [Descriptive Title]

**Date**: YYYY-MM-DD
**Tags**: [relevant, searchable, tags]

## One-Line Summary

A single sentence capturing the core insight.

## The Problem

What was the challenge? What wasn't working? Include specific error messages, performance numbers, or behavioral descriptions.

## The Insight

The key realization or discovery. What made this non-obvious? Why did previous approaches fail?

## Implementation

Minimal working code demonstrating the solution:

\`\`\`[language]
# concrete code example
\`\`\`

## Impact

| Metric | Before | After |
|--------|--------|-------|
| [relevant metric] | [value] | [value] |

## Reusable Pattern

Abstract the specific solution into a general principle that can be applied elsewhere:

- **When you see**: [symptom or situation]
- **Consider**: [the general approach]
- **Because**: [why it works]

## Related Resources

- Links to relevant documentation, issues, or discussions

3. Update the Index

Update breakthroughs/INDEX.md with a new entry. If the index file does not exist, create it with this structure:

# Breakthrough Index

| Date | Title | Tags | Link |
|------|-------|------|------|
| YYYY-MM-DD | [Title] | [tags] | [link to file] |

Append the new entry to the table, keeping entries in reverse chronological order (newest first).

4. Extract Reusable Patterns

After documenting, help the user identify:

  • Is this pattern applicable to other parts of the codebase?
  • Could this become a lint rule, test, or automated check?
  • Should this be shared with the team?

Key Principles

  • Act fast: Capture insights while context is fresh — don't over-polish on first pass.
  • Be specific: Include concrete metrics, error messages, and code. Vague breakthroughs are not reusable.
  • Think reusable: Always extract the generalizable pattern from the specific solution.
  • Stay searchable: Use consistent tags and clear titles so breakthroughs can be found later.

Your Task

Document the breakthrough based on what the user describes:

  1. If the description is clear, proceed directly to creating the breakthrough file
  2. If details are missing, ask focused clarifying questions first
  3. Create the file, update the index, and highlight the reusable pattern

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

36.97%
按下载量换算157

Claude

28.98%
按下载量换算123

Cursor

17.33%
按下载量换算73

Gemini CLI

8.26%
按下载量换算35

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

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