Token导航 LogoToken导航TokenDH.com
待分类只读github未标认证来源可访问许可证需确认审计通过

ralphRalph 助手

Agent Skill

ralph 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

291

周安装

12

GitHub Stars

公开资料未说明

下载量

95
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:ralph(Ralph 助手)
来源仓库:https://github.com/scando1993/sugar
仓库路径:skills/ralph
安装命令:
npx skills add https://github.com/scando1993/sugar --skill ralph
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/scando1993/sugar --skill ralph

简介

ralph 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合围绕仓库状态、代码变更或协作事项进行整理。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装使用。
  • 建议确认权限范围和维护状态,避免触发联网或文件读写操作。
  • ralph 属于待分类类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Ralph PRD Converter

Converts existing PRDs to prd.json — the format that drives Ralph-style autonomous agent loops.


Output Format

{
  "project": "[Project Name]",
  "branchName": "phase-a-[scope-kebab-case]",
  "description": "[Feature description]",
  "userStories": [
    {
      "id": "US-001",
      "title": "[Story title]",
      "description": "As a [user], I want [feature] so that [benefit]",
      "acceptanceCriteria": [
        "Criterion 1",
        "Criterion 2",
        "Typecheck passes"
      ],
      "priority": 1,
      "status": "pending",
      "term": 0,
      "votes": [],
      "notes": ""
    }
  ]
}

The Number One Rule: Story Size

Each story must be completable in ONE agent pass (one context window).

Right-sized:

  • Add a database column and migration
  • Add a UI component to an existing page
  • Update a server action with new logic
  • Write tests for one module

Too big (split these):

  • "Build the entire dashboard" → split into schema, queries, components, filters
  • "Add authentication" → split into schema, middleware, login UI, session handling

Rule of thumb: If you cannot describe the change in 2-3 sentences, split it.


Story Ordering: Dependencies First

Stories execute in priority order. Earlier stories must not depend on later ones.

Correct order:

  1. Schema / database changes (migrations)
  2. Server actions / backend logic
  3. UI components that use the backend
  4. Dashboard / summary views that aggregate data

Acceptance Criteria: Must Be Verifiable

Each criterion must be something an agent can CHECK.

Good: "Add status column to tasks table with default 'pending'" Bad: "Works correctly"

Always include as final criterion: "Typecheck passes" For testable logic: also include "Tests pass"


Conversion Rules

  1. Each user story becomes one JSON entry
  2. IDs: Sequential (US-001, US-002, etc.)
  3. Priority: Based on dependency order, then document order
  4. All stories start with status: "pending", term: 0, votes: [], and empty notes
  5. branchName: Derive from feature name, kebab-case
  6. Always add "Typecheck passes" to every story

Red Flags — If You Catch Yourself Thinking:

ThoughtReality
"This story is small enough to combine with the next one"If it has its own acceptance criteria, it's its own story.
"I don't need Typecheck passes for this one"EVERY story includes "Typecheck passes". No exceptions.
"This description is obvious, no need for detail"An agent with ZERO context will read this. Be explicit.

Consensus Format Example

For consensus mode, add a consensus config to the prd.json root and set initial story fields:

{
  "project": "my-app",
  "branchName": "phase-a-feature",
  "description": "Feature with consensus verification",
  "consensus": {
    "quorumSize": 3,
    "requiredMajority": 2,
    "implementModel": "sonnet",
    "verifyModel": "sonnet",
    "escalationModel": "opus",
    "maxTerms": 5
  },
  "userStories": [
    {
      "id": "US-001",
      "title": "Example story",
      "description": "As a developer, I need...",
      "acceptanceCriteria": ["Criterion 1", "Typecheck passes"],
      "priority": 1,
      "status": "pending",
      "term": 0,
      "votes": [],
      "notes": ""
    }
  ]
}

Splitting Large PRDs

Original: "Add user notification system"

Split into:

  1. US-001: Add notifications table to database
  2. US-002: Create notification service
  3. US-003: Add notification bell icon to header
  4. US-004: Create notification dropdown panel
  5. US-005: Add mark-as-read functionality

Each is one focused change that can be completed and verified independently.

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

36.95%
按下载量换算35

Claude

28.05%
按下载量换算27

Cursor

20.95%
按下载量换算20

Gemini CLI

10.4%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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