Yuan Chen

Swelist

ビジネス運営v1.0.13
作者:Yuan Chen✓ SkillHub 認証済み更新日 2026-05-21全 14 バージョン · 最新版の公開日 2026-05-21swelist@user_159cc044/swelist
ユーザー運営#Sqlite#Career#Job Tracker#New Grad#Software Engineering

AlphaMoatによると、2026-10時点でSwelistのダウンロード数は14,650、スター数は2で、累計ダウンロード数で今回のランキング対象AIスキル10,914件中1,910位、ビジネス運営では873件中161位です。

一覧の初期表示は累計ダウンロード数順で、スター数順にも並べ替えできます。詳細ページの順位は累計ダウンロード数で計算しています。

ダウンロード数
1.5万
スター数
2
累計ダウンロード順位
#1,910
全体の上位 18% · ビジネス運営の上位 19%
プラットフォームダウンロード数スター数コメント
ClawHub ↗34902-
SkillHub ↗1.5万2—

プラットフォームごとに集計方法と集計時点が異なります。

このスキルでできること

swelist は SimplifyJobs の公開求人を実行時に取得し、インターンシップか新卒かの区分、掲載期間、勤務地で絞り込みます。swelist tracker は企業名、職種、ステータス、メモをローカルの SQLite データベースへ書き込み、更新、照会、CSV や JSON への書き出しに対応します。同梱の jobgpt は OPENAI_API_KEY を使って OpenAI を呼び出し、行動面接の回答、志望動機、キャリア相談の文章を生成します。 tracker コマンドの前に ~/.claude/profile.md を読み、バックエンドとデータベースの場所を確認します。jobgpt の面接準備プロンプトは履歴書や個人情報を OpenAI に送信する場合があるため、機密情報を伏せてください。

資料公開日 2026-10-27

できること

  • 勤務地と掲載期間で在募のインターン求人を絞り込む
  • 応募記録をローカルのデータベースにまとめ、定期的に書き出す

使う場面

  • アカウント不要の応募管理台帳が欲しいとき
  • 面接回答の下書きがまず欲しいとき

プロンプト例

スキルのドキュメントをもとに生成した例であり、実際の実行結果ではありません。

サンフランシスコとリモートで最近掲載されたインターン求人を探してください。
この企業への応募を完了にして、メモを追加してください。

月次の推移

ダウンロード数1.5万
65491.1万1.5万2026-03 · ダウンロード数 71492026-05 · ダウンロード数 89602026-06 · ダウンロード数 93612026-07 · ダウンロード数 97912026-08 · ダウンロード数 1万2026-09 · ダウンロード数 1.1万2026-10 · ダウンロード数 1.5万26-0326-0926-10
スター数2
1232026-03 · スター数 22026-05 · スター数 22026-06 · スター数 22026-07 · スター数 22026-08 · スター数 22026-09 · スター数 22026-10 · スター数 226-0326-0926-10

2026-09 から集計方法を変更し、同名スキルを作者ごとに分けて集計し、全スキルを対象にしました。破線は変更前の月で、変更後のデータとは直接比較せず、変更をまたぐ増減も計算していません。

月ダウンロード数前月比スター数
2026-101.5万—2
2026-091.1万—2
2026-081万+2.4%2
2026-079791+4.6%2
2026-069361+4.5%2
2026-058960—2
2026-037149—2

SKILL.md 原文

作者が公開した元のファイルをテキストのまま表示しています。AlphaMoat による編集や審査はしていません。リンクはクリックできません。コマンドは内容を確認してから実行してください。取得日 2026-10-23。

21 KB・ClawHub v1.0.13
---
name: Swelist — Tech Internship & Job Tracker
description: Helps you find tech internships and new-grad jobs, track every application locally, and prep for interviews — no sign-up needed
summary: >
  Use swelist to browse software engineering internships and new-graduate
  positions sourced live from SimplifyJobs, filtered by location and
  timeframe. Track every job application you have submitted in a local
  SQLite database — add entries, mark statuses as in progress, rejected,
  or done, add notes, and export your full pipeline as JSON or CSV.
  Includes an AI writing assistant (jobgpt) for generating behavioral
すべて表示(全 654 行)
  interview answers in STAR format, compelling "why this company"
  responses, and general career advice. Works offline for tracking;
  no account, API key, or subscription required.
version: 0.1.9
homepage: https://pypi.org/project/swelist/
author: Yuan Chen
repository: https://github.com/chenyuan99/swelist
keywords:
  - internship
  - new-grad
  - job-search
  - job-tracker
  - tech-jobs
  - software-engineering
  - application-tracker
  - sqlite
  - career
  - job-listings
  - simplify-jobs
  - job-finder
  - swe-jobs
  - cs-internship
tags:
  - career
  - productivity
  - job-search
category: career
metadata:
  openclaw:
    emoji: "💼"
    requires:
      bins: ["swelist"]
    install:
      - id: uv
        kind: uv
        package: swelist
        bins: ["swelist"]
        label: "Install swelist (uv)"
---

# swelist

`swelist` is a job-seeker CLI for finding software engineering internships and new-grad positions in real time, plus a local SQLite tracker for every application — no account, no API key, no subscription required. It pulls live data from SimplifyJobs, filters by role, location, and timeframe, and pairs with an AI writing assistant (`jobgpt`) for interview prep.

------------------------------------------------------------------------

## When to Use This Skill

Trigger when the user asks to:

- Find or browse internship openings ("show me tech internships this week", "any CS internships remote?")
- Search for new-grad software engineering jobs ("new grad SWE jobs in NYC", "entry-level software engineer positions")
- Filter job listings by location, company, or recency ("jobs in Seattle last 7 days", "remote internships last month")
- Track a job application locally ("add Amazon SDE intern to my tracker", "log this application")
- Update or check an application status ("mark Stripe offer as done", "set Google to rejected")
- List or export tracked applications ("show all my applications", "export tracker as JSON")
- Get AI interview prep answers ("why do you want to work at Meta?", "STAR answer for conflict question")
- Get general career advice via jobgpt ("how do I negotiate salary?", "tips for my first internship")

Keywords: `find internships`, `new grad jobs`, `job listings`, `job search`, `application tracker`, `track my application`, `update application status`, `swelist`, `job search CLI`, `software engineer jobs`, `tech internship`, `interview prep`, `STAR answer`, `why this company`

------------------------------------------------------------------------

## Tool Identity

-   **Name:** swelist
-   **Type:** Command-Line Interface (CLI)
-   **Language:** Python
-   **Distribution:** PyPI
-   **Execution Model:**
    -   `swelist run` — stateless, read-only (fetches live data, no local state)
    -   `swelist jobgpt` — stateless (calls OpenAI API, no local state)
    -   `swelist tracker` — stateful (reads/writes local SQLite at `~/.offerplus/applications.db`)

------------------------------------------------------------------------

## Purpose

`swelist` is a job-seeker CLI with three subcommand groups:

-   **`swelist run`** — retrieves recently added technology internship and
    new‑graduate job postings from curated public GitHub repositories and
    renders them in a predictable, text-based format.
-   **`swelist jobgpt`** — AI-powered writing assistant for interview prep
    (behavioral answers, "why this company", general career Q&A).
-   **`swelist tracker`** — local SQLite application tracker; add, update,
    query, list, and export job applications without any external account.

It is optimized for: automation pipelines, periodic polling agents, and
human-in-the-loop job search workflows.

------------------------------------------------------------------------

## Data Sources

-   SimplifyJobs / Summer2025-Internships
-   SimplifyJobs / New-Grad-Positions

Data is fetched live at runtime.

------------------------------------------------------------------------

## Installation

``` bash
pip install swelist
```

------------------------------------------------------------------------

## Invocation Contract

``` bash
swelist [--role ROLE] [--timeframe TIMEFRAME] [--location LOCATION]
```

The tool accepts only CLI flags. No stdin is consumed.

------------------------------------------------------------------------

## Parameters

### --role

Controls which category of jobs to retrieve.

  Value        Meaning
  ------------ ----------------------------
  internship   Internship roles (default)
  newgrad      New‑graduate roles

Example:

``` bash
swelist --role newgrad
swelist --role internship --timeframe lastweek --location "Seattle, Remote"
```

------------------------------------------------------------------------

### --timeframe

Controls recency filtering.

  Value       Time Window
  ----------- ---------------
  lastday     Last 24 hours
  lastweek    Last 7 days
  lastmonth   Last 30 days

Example:

``` bash
swelist --timeframe lastweek
swelist --role newgrad --timeframe lastmonth --location "New York, Boston"
```

------------------------------------------------------------------------

### --location

Filters job postings by geographic location.

  Input                            Meaning
  -------------------------------- --------------------------------------------------
  Single location                  `Canada` or `Toronto`
  Multiple locations (comma-separated) `"Boston, New York, Remote"`
  State code (2-letter)            `CA` matches "San Francisco, CA"

Example:

``` bash
swelist --location Toronto
swelist --location "Boston, New York, Remote"
swelist --role newgrad --timeframe lastweek --location "San Francisco, Remote"
swelist --role internship --timeframe lastmonth --location CA
```

------------------------------------------------------------------------

## tracker subcommand

Local SQLite tracker for job applications synced from Gmail.

**Before invoking any tracker command, read `~/.claude/profile.md`:**

1. Check `Integrations > Tracker Backend` — if `tracker_backend` is `notion`,
   the tracker subcommand is not applicable; use the `application-manager` skill instead.
2. If `tracker_backend` is `sqlite` (or blank, defaulting to sqlite for local use),
   read `SQLite DB path` from profile.md. Use that value as `--db PATH`.
   Fall back to `~/.offerplus/applications.db` only if the field is blank.

``` bash
# Resolve DB_PATH from profile.md first, then:
swelist tracker init   [--db DB_PATH]
swelist tracker add    "<Company — Role>" --status <S> [--job-id <id>] [--applied-on YYYY-MM-DD] [--db DB_PATH]
swelist tracker update "<Company — Role>" --status <S> [--notes <text>] [--db DB_PATH]
swelist tracker get    "<Company — Role>" [--db DB_PATH]     # JSON; exit 1 + null if not found
swelist tracker list   [--status S] [--company C] [--db DB_PATH]
swelist tracker export [--format csv|json] [--db DB_PATH]
```

If the DB does not exist yet, run `tracker init` before any other tracker command.

### tracker add output sample

Input: `swelist tracker add "Stripe — Backend Engineer" --status "In progress" --job-id S789 --applied-on 2026-05-18`

```
Added: Stripe — Backend Engineer → In progress
```

Input (duplicate):

```
Skipped (already exists): Stripe — Backend Engineer
```

### tracker update output sample

Input: `swelist tracker update "Amazon — SDE, AWS" --status "Rejected"`

```
Updated: Amazon — SDE, AWS → Rejected
```

Input (not found):

```
Not found: Acme — Engineer
```

### tracker get output sample

Input: `swelist tracker get "Amazon — SDE, AWS"`

```json
{"name": "Amazon — SDE, AWS", "status": "Rejected", "job_id": "10414382", "applied_on": "2026-05-17", "notes": null, "updated_at": "2026-05-18 01:10:00"}
```

Input (not found) — exits with code 1:

```json
null
```

### tracker list output sample

Input: `swelist tracker list`

```
 Application                                    Status        Job ID      Applied       Updated
 Amazon — Software Development Engineer, AWS    In progress   10414382    2026-05-17    2026-05-17 18:30:00
 Amazon — Software Development Engineer         In progress   3146673     2026-04-21    2026-04-21 20:50:00
 Amazon — Software Development Engineer, Playback Team  Rejected  3083065  2025-12-02  2025-12-02 17:20:00

3 application(s)
```

Input: `swelist tracker list --status "In progress" --company amazon`

```
 Application                                    Status        Job ID      Applied       Updated
 Amazon — Software Development Engineer, AWS    In progress   10414382    2026-05-17    2026-05-17 18:30:00
 Amazon — Software Development Engineer         In progress   3146673     2026-04-21    2026-04-21 20:50:00

2 application(s)
```

### tracker export output sample

Input: `swelist tracker export --format json`

```json
[
  {
    "name": "Amazon — Software Development Engineer, AWS",
    "status": "In progress",
    "job_id": "10414382",
    "applied_on": "2026-05-17",
    "notes": null,
    "updated_at": "2026-05-17 18:30:00"
  },
  {
    "name": "Amazon — Software Development Engineer, Playback Team",
    "status": "Rejected",
    "job_id": "3083065",
    "applied_on": "2025-12-02",
    "notes": null,
    "updated_at": "2025-12-02 17:20:00"
  }
]
```

Input: `swelist tracker export --format csv`

```
name,status,job_id,applied_on,notes,updated_at
Amazon — Software Development Engineer,In progress,3146673,2026-04-21,,2026-04-21 20:50:00
Amazon — Software Development Engineer Playback Team,Rejected,3083065,2025-12-02,,2025-12-02 17:20:00
```

------------------------------------------------------------------------

## Output Contract

-   Output is written to **STDOUT**
-   Format is **human- and agent-readable plain text**
-   No JSON or structured serialization

### Job Posting Fields

Each job entry contains:

-   Company (string)
-   Title (string)
-   Location (string) — may be a single string or a list
-   Link (URL)

### Realistic output sample

Input: `swelist --role internship --timeframe lastweek --location "Seattle, Remote"`

```
Welcome to swelist.com
Last updated: Sun May 17 18:42:01 2026
Found 1284 tech internships from 2025Summer-Internships
Found 892 new-grad tech jobs from New-Grad-Positions
Sign-up below to receive updates when new internships/jobs are added

Found 3 postings for location 'Seattle, Remote' in TimeFilter.lastweek

Company: Amazon
Title: Software Development Engineer Intern
locations: ['Seattle, WA', 'Remote']
Link: https://www.amazon.jobs/en/jobs/2345678

Company: Microsoft
Title: Software Engineering Intern
locations: ['Redmond, WA', 'Remote']
Link: https://jobs.careers.microsoft.com/us/en/job/1234567

Company: Stripe
Title: Software Engineer, Intern
locations: ['Remote']
Link: https://stripe.com/jobs/listing/software-engineer-intern/9876543
```

### Empty-result output

When no postings match the filters:

```
# No jobs in the selected timeframe:
No postings found in TimeFilter.lastday

# Jobs exist but none match the location:
No postings found for location 'Austin' in TimeFilter.lastday
```

Agents should treat either message as a zero-result signal and not retry with the same flags.

------------------------------------------------------------------------

## Execution Guarantees

-   No side effects
-   No persistent storage
-   Safe for repeated execution
-   Deterministic given identical upstream data
-   No authentication required

------------------------------------------------------------------------

## Error Behavior

-   Network issues may raise runtime errors or result in empty output
-   Invalid flags produce CLI usage errors
-   Zero matching jobs produces valid empty result output

------------------------------------------------------------------------

## Environment Requirements

-   Python 3.8+
-   Internet access
-   Supported on macOS, Linux, Windows

------------------------------------------------------------------------

## Agent-Oriented Use Cases

-   Daily polling for new internship postings
-   Weekly new‑grad job aggregation
-   Feeding results into ranking, scoring, or alerting agents
-   Execution via cron, CI pipelines, or autonomous agents
-   Parsing job postings into structured JSON for downstream processing
-   Integration with AI agents for automated job application workflows

------------------------------------------------------------------------

## Known Limitations

-   No built‑in alerting
-   No local caching
-   No deduplication beyond source data
-   No JSON output format

------------------------------------------------------------------------

## Safety & Compliance

-   Uses only public data
-   No user tracking
-   No credential usage
-   No scraping of private systems

------------------------------------------------------------------------

## Versioning

Behavior may evolve with upstream data sources. CLI flags are considered
stable within a major version.

------------------------------------------------------------------------

# jobgpt

This document defines the operational capabilities, invocation contract,
and usage semantics of the `jobgpt` command for AI-powered job application
assistance.

------------------------------------------------------------------------

## Tool Identity

-   **Name:** jobgpt
-   **Type:** Command-Line Interface (CLI)
-   **Language:** Python
-   **Distribution:** Part of swelist package
-   **Execution Model:** Stateless, AI-powered writing assistant

------------------------------------------------------------------------

## Purpose

`jobgpt` is an AI writing assistant that helps job seekers prepare for
interviews and job applications by generating compelling answers and career
advice.

It is optimized for: - Interview preparation - Application materials - Career
guidance

------------------------------------------------------------------------

## Subcommands

### ask

Ask any career or job-search question.

``` bash
jobgpt ask "Your question here"
```

**Parameters:**

-   **question** (positional, required): Any job-search or career question

**Options:**

-   `--model`: OpenAI model to use (default: `gpt-4o`)
-   `--copy`: Copy output to clipboard (flag)

**Example:**

``` bash
jobgpt ask "What should I focus on in my first internship?"
jobgpt ask "How do I negotiate salary?" --copy
```

**Sample output:**

```
╭─ Career Advice ────────────────────────────────────────────────────╮
│                                                                     │
│  Focus on three things in your first internship:                   │
│                                                                     │
│  1. **Shipping something real** — even a small feature that goes   │
│     to production teaches you more than any tutorial.              │
│  2. **Building relationships** — your intern cohort and your       │
│     manager are your longest-lasting professional network.         │
│  3. **Asking good questions** — juniors who ask precise, well-     │
│     researched questions are remembered positively.                │
│                                                                     │
╰─────────────────────────────────────────────────────────────────────╯
```

------------------------------------------------------------------------

### why-company

Generate a compelling answer to "Why do you want to work at [Company]?"

``` bash
jobgpt why-company "Company Name" --background "Your background"
```

**Parameters:**

-   **company** (positional, required): Company name

**Options:**

-   `--background`: Your background summary (optional, recommended)
-   `--model`: OpenAI model to use (default: `gpt-4o`)
-   `--copy`: Copy output to clipboard (flag)

**Example:**

``` bash
jobgpt why-company "Google" --background "Software Engineering student with Python and web development experience"
jobgpt why-company "Meta" --background "Full-stack developer with React and Node.js expertise" --copy
```

------------------------------------------------------------------------

### behavioral

Generate a STAR-format answer to a behavioral interview question.

``` bash
jobgpt behavioral "Question here" [--resume path/to/resume.txt]
```

**Parameters:**

-   **question** (positional, required): The behavioral interview question

**Options:**

-   `--resume`: Path to resume text file (optional)
-   `--model`: OpenAI model to use (default: `gpt-4o`)
-   `--copy`: Copy output to clipboard (flag)

**Example:**

``` bash
jobgpt behavioral "Tell me about a time you dealt with conflict on a team"
jobgpt behavioral "Describe your biggest failure and how you learned from it" --resume resume.txt --copy
```

**Sample output:**

```
╭─ STAR Answer ───────────────────────────────────────────────────────╮
│                                                                      │
│  **Situation:** During my internship at Acme, our team disagreed    │
│  on the API design for a new service — two engineers wanted REST,   │
│  one pushed for GraphQL.                                            │
│                                                                      │
│  **Task:** As the engineer writing the initial spec, I needed to    │
│  drive us to a decision before our sprint planning the next day.    │
│                                                                      │
│  **Action:** I drafted a one-page trade-off doc comparing latency,  │
│  client complexity, and team familiarity for both options, then     │
│  scheduled a 30-minute sync. I proposed REST with a versioning      │
│  convention that addressed the GraphQL advocate's flexibility       │
│  concerns.                                                          │
│                                                                      │
│  **Result:** We reached consensus in 20 minutes. The service        │
│  shipped on time and has had zero breaking-change incidents in      │
│  six months.                                                        │
│                                                                      │
╰──────────────────────────────────────────────────────────────────────╯
```

------------------------------------------------------------------------

## Output Contract

-   Output is written to **STDOUT**
-   Format is **human-readable markdown** with rich text formatting
-   Organized in clear panels with proper section headers
-   Optimized for reading and copying to clipboard

------------------------------------------------------------------------

## Execution Guarantees

-   Requires OpenAI API key (set via `OPENAI_API_KEY` environment variable)
-   No persistent storage
-   Safe for repeated execution
-   Deterministic given identical input (within model capabilities)

------------------------------------------------------------------------

## Error Behavior

-   Missing `OPENAI_API_KEY` environment variable produces clear error message
-   Invalid OpenAI model names produce API errors
-   Missing resume file produces OSError with clear message
-   Network issues may raise runtime errors

------------------------------------------------------------------------

## Environment Requirements

-   Python 3.8+
-   OpenAI API key (`OPENAI_API_KEY`)
-   Internet access for API calls
-   Supported on macOS, Linux, Windows

------------------------------------------------------------------------

## Agent-Oriented Use Cases

-   Preprocessing candidate data for interview coaching bots
-   Generating interview preparation materials at scale
-   Feeding career advice into autonomous career planning agents
-   Integration with resume builders and application workflows

------------------------------------------------------------------------

## Known Limitations

-   Requires OpenAI API key and internet connection
-   Responses vary based on model capability
-   No local caching of responses
-   No built-in follow-up question handling

------------------------------------------------------------------------

## Safety & Compliance

-   Uses only public OpenAI API
-   No data persistence
-   No credential sharing or exposure
-   Respects OpenAI usage policies

------------------------------------------------------------------------

End of document.

ビジネス運営の人気スキル

标书写作专家【百炼标书】ビジネス運営

百炼®标书是一个面向投标场景标书写作的skill,可以帮用户完成四件事:解读招标文件、生成投标文件、审查投标文件合规风险以及标书查重。它适合用自然语言直接写作,用户只要提供文件和需求,就能拿到解读结果、成品标书、审查报告、查重报告。百炼®标书官网:https://biaoshu.zhiliaobiaoxun.com

↓ 70.7万★ 61u_62be253f
AdMapix广告投放工具ビジネス運営

AdMapix广告原始数据层,广告创意/应用/排名/下载收入

↓ 30.9万★ 1u_8ee34d77
全国招标中标查询及分析【知了标讯】ビジネス運営

知了标讯:入札、落札、サプライヤー、調達市場の情報を検索・分析します。

↓ 21.4万★ 14user_98035bfb
招标中标查询及分析服务ビジネス運営

知了標訊APIを通じて入札・落札情報を検索・分析します。

↓ 12.1万★ 16user_98035bfb
标书审查【喜鹊标书】ビジネス運営

喜鹊标书审查|让投标风险看得见、查得清、改得准 投标文件准备好了,还有哪些遗漏和隐患?喜鹊标书审查对照招标要求,检查投标文件中的响应缺漏、内容矛盾和潜在风险,帮助您在提交前发现问题、明确修改重点。 - 问题一目了然:区分已确认风险与待核实事项,清晰呈现问题位置、具体表现及潜在影响。 - 审查有据可查:关联招标条款与投标内容,让您看清“要求是什么、哪里存在问题、判断依据是什么”。 - 原文快速定位:结合页码、检索线索和证据截图,减少来回翻找,方便逐项核对。 - 完整报告可交付:提供 Word 审查报告及审查版 PDF,便于团队复核、修改和留档。 支持 PDF、DOCX 及多附件审查。先检查文件,再展示价格并按次付费;支持随时查询进度、继续已付款任务和补领报告,让每一次审查都有清晰结果。 https://www.xiquebiaoshu.com/?source=skillhub](https://www.xiquebiaoshu.com/?source=bid-review-pay

↓ 10.5万★ 1u_84923c62
PollyReachビジネス運営

AI エージェントに電話番号を与え、電話での用件を代行するスキルです。

↓ 10.2万★ 56PollyReach
商品图ビジネス運営

将真实产品照片制作成影棚级电商主图、场景图或面向市场平台的高清商品图。这款 AI 商品图工作室用于商品图片处理和电商图片编辑,可替换背景、改善光效、搭建场景。它以原图中的商品外观特征为依据,从一张手机随拍就能做出白底主图、生活场景图和高级广告图。适用于亚马逊白底产品图、淘宝主图、Shopify 产品大图和社交媒体商品图。从一张产品照片出发,组合多张参考图,或在选定草稿上做定向精修,完成适合上架使用的成品;生活场景图和广告图也能直接用作商品详情页图片。

↓ 10.2万★ 10user_87b8e34f
会员体系搭建ビジネス運営

【零一数科·出品】会员体系搭建(免费版)。为私域用户设计会员体系搭建,产出会员等级成长表、积分获取消耗规则表、权益配置矩阵、积分财务测算表四件套。适用于会员积分体系设计、会员等级阶梯、成长值规则、权益配置、积分获取与消耗、积分财务测算、私域会员运营。

↓ 9.7万★ 8u_c19e970c

Yuan Chenのその他のスキル

データ月:2026-10 · ダウンロード数とスター数は公開スキルレジストリ(ClawHub、SkillHub)から月単位で集計しています。詳しくはデータの方法論をご覧ください。