SkillFoxx

Skillrush Town skill

A skill that keeps daily snapshots of the ClawHub Top100, spots newcomers and fast-growing skills and prepares a report.

  • 112 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • The skill calls the open ClawHub interface and public GitHub Pages data.
  • The agent sets up reminders and schedules only at your request.
All reasons and checks

learnprompt/skillrush-townAuthor:LearnPrompt

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/skillrush-town

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The skill calls the open ClawHub interface and public GitHub Pages data.
  • The agent sets up reminders and schedules only at your request.

This is third-party code. Review the repository files before installing.

What it does

Skillrush Town, "淘金小镇" in Chinese, posts the ClawHub Top100 ranking on a noticeboard every morning. The skill watches who suddenly appeared more than who is first: new entries, fast growth in downloads and stars, climbs in position. The skill fixes the whole path of working with an open data source: pick the source, fix the fetch method, save snapshots every day, compare history, build a report and remind the user. ClawHub Top100 is the first source because it has pagination and stitching of a full list. Data is published as static files: `data/latest.json`, `data/snapshots/<date>.json`, `data/dates.json`, daily reports in `data/reports/` and the Atom feed `feed.xml`. Agents and scripts read them with a plain GET and no authorization. New sources are added only after writing a source contract.

Who it is for. Skill authors and anyone tracking the agent ecosystem who wants to know which skills are gaining traction.

Good fit when

  • In the morning you want to know which skills entered the Top100 and grow fastest in downloads.
  • You want a daily ranking feed as an Atom subscription.
  • You want your own town for another source: fork the repository with the same Actions workflow.
  • You need to compare data across dates through static JSON.

Not a fit when

  • You need data before 4 May 2026: the first snapshot is dated that day.
  • You need strict daily dynamics right after the first run: without two days of history there are no changes.
  • You need rankings of other registries that have no source contract yet.

Example request

What is new in Skillrush Town today? Show the Top10 and the skills with the fastest download growth.

Limitations

The skill depends on the open ClawHub interface: if it changes, the report and ranking table break, which is recorded in the `limitations` field and in reports. The first run shows no changes because there is no previous snapshot, and exact daily deltas appear after two days in a row. The skill does not create schedules silently on install: a reminder is set up separately, with your consent. The repository and docs are in Chinese, and data is served as static files with no availability guarantee.

How to disable. Delete the `skillrush-town` folder from `~/.agents/skills`. If you set up a reminder or schedule, disable it separately.

FAQ

How do I install Skillrush Town?

Run `npx skills add LearnPrompt/skillrush-town -g`. It suits Claude Code, Codex, Cursor and dozens of other agents and installs the skill into `~/.agents/skills`.

Where can I see the data without an agent?

On the project GitHub Pages site: today's Top10, rising skills, fastest by downloads and stars, entries and drop-outs, and the full Top100 for a chosen date.

How do I subscribe to the daily report?

Subscribe to the Atom feed `feed.xml` on the project GitHub Pages: it has one entry per day with the Top3 and the count of rising skills.

Can I use the data in my own scripts?

Yes. Files are available with a plain GET and no authorization, and fields promise only to grow: names and meaning of existing fields do not change.

How do I add another source?

First write a source contract in `skills/skillrush-town/references/source-contract-<source>.md`, then build the fetch and comparison. A fetcher without a contract is not accepted.

Discussion

No questions or reviews yet.

Skills

A skill set for SEO and indie development: keyword picking, launching a site on Cloudflare, backlinks, dashboard data and growth.

SkillExtended access304

Yandex Direct statistics skill

ya-direct-statistics

Russian stack

A Codex skill for building and reading Yandex Direct reports: Report Wizard, the report library, filters, attribution and safe browser workflows

SkillExtended access1
Russian stack

Three Agent Skills in one repository: calling the Yandex Direct, Metrica and Wordstat APIs directly via JSON

SkillBroad access1

Yandex rank tracker skill via Apify

claude-skill-yandex-rank-tracker

Russian stack

A skill that uses a third-party Apify scraper to pull a site's Yandex ranking for a keyword, domain and region

SkillExtended access
Russian stack

A skill and condensed Yandex Metrika API documentation for an agent: reports, Logs API, counter management, OAuth without leaking the token into chat

SkillExtended access16

Backlink Skills is a Codex skill set for submitting a product to directories and writing SEO text to each platform's rules.

SkillExtended access892

README in short

The project is meant as a pattern for working with any open source, not just a table page. GitHub Actions collects the daily snapshot and the board is published on GitHub Pages.

README badge

Original SKILL.md

---
name: skillrush-town
description: "淘金小镇 | Skillrush Town — 每日 ClawHub Top100 淘金雷达。消费侧触发：用户问「今天 ClawHub 有什么新 skill」「淘金小镇今天有什么」「最近什么 skill 在涨」「有什么潜力 skill 值得装」「ClawHub 榜单」「skill 下载榜 / 增速榜 / 新进榜」时，读取 data/latest.json（或 GitHub Pages 数据）总结 Top10、潜力 Skill 与新进榜。即使用户只是说「帮我看看 skill 圈最近有什么动静」也应该触发。维护侧触发：building, maintaining, forking, or publishing Skillrush Town; tracking ClawHub Top100 downloads snapshots; generating daily Skill reports; evaluating ClawHub source changes; or packaging a public GitHub Pages skill radar. 不要用于：AI 资讯/新闻（用 ai-news-radar）、评估单个信息源是否值得接入（用伯乐）、安装某个具体 skill 本身。"
---

# Skillrush Town

## 消费侧用法（用户只想看榜时）

当用户问"今天有什么新 skill / 什么在涨 / 有什么值得装"这类问题时，不要走维护流程，直接读数据回答：

1. 取数据：仓库内优先读 `data/latest.json`；不在仓库内时读
   `https://learnprompt.github.io/skillrush-town/data/latest.json`。
   回看历史用 `data/snapshots/<YYYY-MM-DD>.json`，可用日期列表在 `data/dates.json`。
2. 总结三块：今日 Top10（`items` 前 10 条）、潜力 Skill（报告
   `data/reports/<date>.md` 的「潜力 Skill」节，或按 SKILL.md 潜力标准从 items 现算）、
   新进榜（有历史时 `prev_rank` 为 null 的条目）。
3. 给出"值得点开看"的 2-3 个，并说清理由（下载/星标增量、排名变化、summary 里的用途），
   附上 `https://learnprompt.github.io/skillrush-town/?date=<snapshot_date>` 方便用户自己看。
4. 诚实转述 `limitations` 与 `comparison_basis.note`：缺历史切片时不要把数字说成日环比。

## First Reads

When this skill triggers inside the repo, read:

- `README.md` for product positioning and user paths.
- `scripts/clawhub_daily.py` before changing data generation.
- `data/dates.json` and the latest `data/snapshots/*.json` before changing the UI.
- `assets/app.js`, `assets/styles.css`, and `index.html` before changing the page.
- `references/source-contract.md` before changing ClawHub request semantics.
- `references/source-adapter-pattern.md` before adding changelog, model leaderboard,
  or any non-ClawHub monitoring source.
- `references/publishing.md` before changing GitHub Pages or Actions.

## Product Direction

Maintain three surfaces:

- **Public town board**: a phone-friendly GitHub Pages site where anyone can
  read the latest ClawHub Top100, growth lists, potential Skills, and history.
- **Forkable Skill generator**: a repo plus Skill that lets users generate their
  own Skill radar without copying private tokens or personal notes.
- **Source-monitoring workflow**: a repeatable pattern for turning public
  leaderboards, changelogs, and release pages into dated snapshots, diffs,
  reports, and optional Agent reminders.

Report a problem