Hkdata

Use when the user asks about Hong Kong government open data, statistics, or datasets — e.g. transport, weather, population, employment, finance, health, education, housing, crime, tourism, facilities, etc. — in English or Chinese. Queries data.gov.hk and returns sourced, live answers, or an honest "no dataset".

11 stars 1 forksData & Analytics

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add gnokit/hkdata --skill hkdata

Manual install

git clone --depth 1 https://github.com/gnokit/hkdata.git /tmp/hkdata
mkdir -p ~/.claude/skills
cp -r /tmp/hkdata/. ~/.claude/skills/hkdata

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 港數通 · hkdata — Hong Kong Open Data Library

**Scope: Hong Kong data.gov.hk datasets only.** General web search, non-HK data,
or non-government sources are handled by the agent's native web search tools, not
this skill.

## Resolve the skill root once

The commands below use `$SKILL_DIR`; resolve it before the first call (the docs
never assume a runtime's install directory):

```bash
: "${SKILL_DIR:=$(for d in "${HKDATA_SKILL_DIR:-}" "$HOME/.agents/skills/hkdata" \
    "$PWD/.agents/skills/hkdata" "$HOME/.claude/skills/hkdata" \
    "$HOME/.config/agents/skills/hkdata" "$PWD"; do [ -f "$d/hk.sh" ] && { echo "$d"; break; }; done)}"
[ -n "$SKILL_DIR" ] || { echo "hkdata: set HKDATA_SKILL_DIR to the dir containing hk.sh" >&2; exit 1; }
```

The wrapper is cwd-safe (it resolves its own root) and picks the venv
interpreter when present, else `python3`. From the skill directory itself,
`bash ./hk.sh <subcommand> …` works the same way.

## You are a coding agent with a library of reusable programs

This skill gives you a growing library of **runnable, docstring-documented
functions** under `programs/` — each one a **reusable capability over one
data.gov.hk API/dataset**, grouped by department/org. Each function returns
JSON-serializable data (it never prints); its docstring says what data it
provides, its dataset ID, endpoints, and quirks.

**A program answers a *class* of questions, not one specific question.**

Read the full skill on GitHub

Details

Skill name: hkdata
Repository: gnokit/hkdata
License: MIT
Repo updated: 20 October 2026

FAQ

What does the Hkdata skill do?

How do I install the Hkdata skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add gnokit/hkdata --skill hkdata. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Hkdata popular?

It lives in gnokit/hkdata, which has 11 GitHub stars and 1 forks.

Related skills

Base R

iremaydas/base-r-skill

Provides base R programming guidance covering data structures, data wrangling, statistical modeling, visualization, and I/O — using only packages included in a standard R installation. Use when the user writes or debugs R scripts, works with vectors, matrices, lists, data frames, or factors, applies the apply family (sapply, lapply, vapply, tapply), fits models with lm/glm/aov/nls, creates base graphics with plot/barplot/hist/boxplot/par, reads or writes CSV/RDS/RData files, or asks about R language semantics such as environments, scoping, and non-standard evaluation. Also use for R statistica

Data & Analytics

Notebooklm Course Builder

hmj1026/notebooklm-course-builder

以條件式瀏覽器自動化或 14 階段嚮導建構 NotebookLM 課程教材。適用於：(1) 將課程大綱轉為包含來源引用、逐節講義、Quiz 與 Study Guide 的完整課程；(2) 規劃 Notebook 與研究分群、來源審核、Coverage 分析；(3) 自動操作 NotebookLM 或延續既有建置進度。

Data & Analytics

Xcatcher

lvpiggyqq/xcatcher-mcp-manifest

Fetch fresh or recent public X (Twitter) posts from one or many named account handles through Xcatcher, with structured JSON results and optional x402 v2 USDC pay-per-crawl access on Base. Use for account monitoring, social intelligence, OSINT, tweet/post collection, timeline snapshots, or requests to scrape, crawl, watch, compare, or summarize specified X/Twitter handles or profile URLs.

Data & Analytics

Clawarr Suite

omiron33/clawarr-suite

Comprehensive management for self-hosted media stacks (Sonarr, Radarr, Lidarr, Readarr, Prowlarr, Bazarr, Overseerr, Plex, Tautulli, SABnzbd, Recyclarr, Unpackerr, Notifiarr, Maintainerr, Kometa, FlareSolverr). Deep library exploration, analytics, dashboard generation, content management, request handling, subtitle management, indexer control, download monitoring, quality profile sync, library cleanup automation, notification routing, collection/overlay management, and media tracker integration (Trakt, Letterboxd, Simkl).

Data & Analytics

Paywall Bypass

Lunatic16/paywall-bypass-skill

Identify paywall types and generate bypass strategies for web scraping and content extraction. Covers 500+ news sites, major paywall providers (Piano, TinyPass, Poool, etc.), and extraction techniques (bot spoofing, AMP, JSON-LD, archive fetching).

Data & Analytics

Media Crawler Easy

isheng-eqi/media-crawler-easy

多平台社媒评论数据采集爬虫工具。覆盖 B站(bilibili)/小红书/抖音(douyin)/快手/微博/贴吧/知乎 7大平台。当用户提到"爬评论""采集评论""下载评论""爬数据""批量采集""舆情分析""评论分析""社媒数据" "抓取评论""导出评论""获取评论""视频评论""帖子评论""笔记评论""UP主评论""博主评论" "关键词搜索爬取""社交媒体数据采集""爬虫""数据爬取""评论数据""用户评论"时自动触发。支持按关键词搜索、指定链接采集、创作者主页三种模式。生成交互式 HTML 报告 + 数据文件。

Data & Analytics

Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.