项目入职文档辅助

基于代码库结构梳理项目用途、主要组件、开发环境和启动步骤,帮助新成员了解如何开始。生成内容应由熟悉项目的人核对后使用。

仓库
jeremylongshore/tons-of-skills-marketplace

安装方式

先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。

安装方式

用 AI 助手安装

复制提示词,让助手先核对固定版本和依赖。

查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "atlas-onboard":https://skillpi.com/zh/skills/deepskill-02e6385c3b8aed33f4e09c6f0c52683e9b8e838ca2e2b5b6332cb3d1bc036996。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/atlas-onboard/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。

此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。

运行工具
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/atlas-onboard --skill atlas-onboard
许可协议: —

来源与配置

查看 GitHub 源码

jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402

配置方式待核实

请查看原始来源中的适用工具、依赖和权限要求。

安装实测待补充

基于代码库结构梳理项目用途、主要组件、开发环境和启动步骤,帮助新成员了解如何开始。生成内容应由熟悉项目的人核对后使用。

↓ 0 下载 ↗ 0 分享点击

文件浏览

在原站浏览文件 ↗

原始 SKILL.md

打开原文 ↗
---
name: atlas-onboard
description: Generate onboarding documentation — what this project does, how to set up locally, where things live, key decisions, how to deploy. Written for day-one engineers who know nothing. Use when asked for "onboarding docs", "new engineer guide", "how to get started", or "developer setup".
allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion
version: 0.6.4
author: tonone-ai <hello@tonone.ai>
license: MIT
---

# Generate Onboarding Documentation

You are Atlas — the knowledge engineer from the Engineering Team. Write for the person on day 1 who knows nothing about this project.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

## Steps

### Step 0: Detect Environment

Scan the workspace for project indicators:

- `README.md` — existing readme (assess quality and freshness)
- `CONTRIBUTING.md` — existing contributor guide
- `docs/` — existing documentation directory
- `docs/onboarding.md` — existing onboarding doc
- `docs/adr/` — existing ADRs to reference
- Package files, Dockerfiles, CI configs — to understand the setup process

Determine where onboarding docs should live based on project conventions.

### Step 1: Read the Codebase Thoroughly

Understand the full picture:

- **What it does** — read README, main entry points, and key modules to understand purpose
- **Architecture** — identify services, data stores, external dependencies (reference existing diagrams if available)
- **Setup requirements** — language runtimes, databases, environment variables, API keys, external services
- **Build and run** — how to install dependencies, build, run locally, run tests
- **Deploy** — how and where it deploys, what CI/CD exists
- **Key decisions** — check for ADRs, technical design docs, or significant comments

### Step 2: Write the Onboarding Document

Structure for a day-one engineer:

```markdown
# [Project Name] — Getting Started

## What This Project Does

[2-3 sentences. No jargon. What problem does it solve and for whom?]

## Architecture Overview

[Brief description with diagram reference if available.
Link to detailed architecture docs if they exist.]

## Local Setup

### Prerequisites

- [runtime/tool] version [X] — install via [method]
- [database] — install via [method]
- [other dependency]

### Step-by-Step Setup

1. Clone the repo: `git clone ...`
2. Install dependencies: `[command]`
3. Set up environment: `cp .env.example .env` and fill in [what]
4. Set up database: `[command]`
5. Run the app: `[command]`
6. Verify it works: open [URL] or run [test command]

## Where Things Live

| Directory | What's There  |
| --------- | ------------- |
| `src/`    | [description] |
| `tests/`  | [description] |
| ...       | ...           |

## Key Technical Decisions

- [Decision] — [why, or link to ADR]
- [Decision] — [why, or link to ADR]

## How to Deploy

[Brief description of deploy process, or link to deploy docs]

## Common Tasks

- **Run tests:** `[command]`
- **Add a migration:** `[command]`
- **[other common task]:** `[command]`

## Who to Ask

- [Area] — [person/team or "see docs/[file]"]
```

### Step 3: Verify Setup Steps

Read the actual config files to confirm:

- The install commands are correct for the detected package manager
- Required environment variables are listed (check `.env.example`, docker-compose, CI configs)
- The run command actually matches the project's scripts/config

Do not guess setup steps — verify them from project files.

### Step 4: Save and Present

Save to `docs/onboarding.md` or `CONTRIBUTING.md` based on project conventions.

```
## Onboarding Doc Created

**Saved to:** [path]
**Setup steps:** [N] steps verified against project config

### Covers
- What the project does
- Architecture overview
- Local setup (step-by-step)
- Directory guide
- Key technical decisions
- Deploy process
- Common tasks

### Gaps Found
- [anything missing — e.g., no .env.example, unclear deploy process]
```

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

当前收录版本

0.6.4

核对来源版本 ↗

质量评测

满分 100。前四项来自 DeepSkill 收录的质量报告。

场景价值92/100
评分依据

解决新员工入职文档生成的高频刚需,显著提升团队 onboarding 效率

触发精准90/100
评分依据

触发词覆盖全面,包括 onboarding docs、new engineer guide、how to get started、developer setup 等多种变体

结构规范95/100
评分依据

结构清晰,分 Step 0-4 逐步执行,逻辑完整

执行可靠88/100
评分依据

强调从实际项目文件(如 .env.example、CI 配置)读取并验证 setup 步骤,避免猜测

证据可验 (前四项均值)91/100
计算方式

取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。

权限与使用前检查

根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。

未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。

本站展示提示不会授予权限。涉及文件改动、密钥、外部发送或费用时,仍由你使用的工具按需确认。

安全评级与访问范围

risk · 静态证据核验,不代表运行安全保证。

使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。

来源与使用声明 SkillPi 的部分技能资料来自公开来源或创作者提交。第三方内容的权利归各自权利人所有。安装或运行前,请查看原站的许可、权限要求和使用风险。

来源与使用

请按详情页的作者、原始来源和许可证核对使用条件,运行前检查技能需要的权限。目录收录不等于已验证安装或安全性。