Verified Research
sweetcornna/free-search-mcp
Use with the free-search MCP tools whenever a web lookup must yield facts someone will rely on: dates, deadlines, prices, prizes, fees, rules, eligibility, schedules, versions, statistics, news, or…
Find, download, and prepare official thematic statistics from the National Bureau of Statistics of China.
$ npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zzhonglei/GeoCode-Release china-statistics-data --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zzhonglei/GeoCode-Release.git skills-src && mkdir -p .claude/skills && cp -r skills-src/contributions/china-statistics-data/skill .claude/skills/china-statistics-data && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "china-statistics-data" agent skill from https://github.com/zzhonglei/GeoCode-Release/tree/main/contributions/china-statistics-data/skill into .claude/skills/china-statistics-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-statistics-data", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zzhonglei/GeoCode-Release/tree/main/contributions/china-statistics-data/skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zzhonglei/GeoCode-Release china-statistics-data --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zzhonglei/GeoCode-Release.git skills-src && mkdir -p .agents/skills && cp -r skills-src/contributions/china-statistics-data/skill .agents/skills/china-statistics-data && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "china-statistics-data" agent skill from https://github.com/zzhonglei/GeoCode-Release/tree/main/contributions/china-statistics-data/skill into .agents/skills/china-statistics-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-statistics-data", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zzhonglei/GeoCode-Release china-statistics-data --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zzhonglei/GeoCode-Release.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/contributions/china-statistics-data/skill .cursor/skills/china-statistics-data && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "china-statistics-data" agent skill from https://github.com/zzhonglei/GeoCode-Release/tree/main/contributions/china-statistics-data/skill into .cursor/skills/china-statistics-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-statistics-data", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zzhonglei/GeoCode-Release.git --path contributions/china-statistics-data/skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zzhonglei/GeoCode-Release china-statistics-data --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zzhonglei/GeoCode-Release.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/contributions/china-statistics-data/skill .gemini/skills/china-statistics-data && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "china-statistics-data" agent skill from https://github.com/zzhonglei/GeoCode-Release/tree/main/contributions/china-statistics-data/skill into .gemini/skills/china-statistics-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-statistics-data", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zzhonglei/GeoCode-Release china-statistics-dataInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zzhonglei/GeoCode-Release.git skills-src && mkdir -p .github/skills && cp -r skills-src/contributions/china-statistics-data/skill .github/skills/china-statistics-data && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "china-statistics-data" agent skill from https://github.com/zzhonglei/GeoCode-Release/tree/main/contributions/china-statistics-data/skill into .github/skills/china-statistics-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-statistics-data", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zzhonglei/GeoCode-Release china-statistics-data --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zzhonglei/GeoCode-Release.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/contributions/china-statistics-data/skill .opencode/skills/china-statistics-data && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "china-statistics-data" agent skill from https://github.com/zzhonglei/GeoCode-Release/tree/main/contributions/china-statistics-data/skill into .opencode/skills/china-statistics-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-statistics-data", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
china-statistics-dataFind, download, and prepare official thematic statistics from the National Bureau of Statistics of China.
China Statistics Data is an agent skill from zzhonglei/GeoCode-Release. Find, download, and prepare official thematic statistics from the National Bureau of Statistics of China. Use this skill when the user needs Chinese statistical indicators such as GDP, population, employment, industry, agriculture, energy, environment, transport, education, census/yearbook tables, or other socio-economic data for mapping, analysis, charts, or reports.
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Data & Analytics, covering Statistics. It works with Model Context Protocol and Playwright. The repository describes itself as: A desktop AI assistant for geoscience data processing. The licence is MIT.
Read from SKILL.md and the folder at commit 6e3534f. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
data.stats.gov.cnFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
China Statistics Data loads about 2.7k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 1,068 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from zzhonglei/GeoCode-Release at commit 6e3534f, republished under its MIT licence (© zzhonglei). 1,068 words, ~2,691 tokens.
.claude/skills/china-statistics-data/SKILL.md (or your agent's skills folder).Use this skill to obtain official thematic statistics for China from the National Bureau of Statistics of China (NBS). Read it whenever the task requires Chinese socio-economic indicator data, especially data that will later be joined to administrative boundaries, mapped, charted, or used in a report.
The National Bureau of Statistics data portal is not a simple static download page. It is a browser-based JavaScript application. To search indicators, expand tables, switch dimensions, and trigger exports reliably, you need to operate the official website through Playwright MCP.
Before entering the data-download workflow, look at the tools currently available to you. If Playwright MCP browser-control tools are present, use them to open the official NBS website and work through the visible interface just as a user would.
When you find that Playwright MCP is not available, do not continue with the NBS data-download workflow yet. In your own words, remind the user to open GeoCode's top-right status button and enable Playwright MCP, explaining that you need browser-control capability before you can operate the NBS website and download thematic data.The GeoCode platform has included Playwright MCP since version 0.9.3, but users need to manually enable it before they can use its tools.
After the user enables Playwright MCP, continue from the official NBS website instead of relying on unofficial mirrors, guessed portal URLs, or hidden request parameters.
important: You cannot perform any other tasks while waiting for the user to enable MCP.
The main working site for this skill is the National Bureau of Statistics data platform: https://data.stats.gov.cn/dg/website/page.html. The site is organized as a navigation-based data platform. When you operate it through Playwright MCP, first identify which navigation entry matches the user's requested geography and time frequency, then open the corresponding page and work from the visible table interface.
The top-level navigation contains these major sections:
国家数据平台
├── 首页
├── 月度数据
├── 季度数据
├── 年度数据
├── 普查数据
├── 地区数据
├── 部门数据
├── 国际数据
├── 出版物
├── 我的收藏
└── 帮助For geospatial and thematic mapping tasks, the most common entry point is 地区数据. This menu contains province-level, major-city, Hong Kong, Macao, and Taiwan datasets. The URL hash suffix tells you which page you are on:
| URL suffix | Navigation item | What the page contains |
|---|---|---|
fsMonthData | 分省月度数据 | Monthly statistics for provinces, autonomous regions, and municipalities, such as monthly CPI and high-frequency industrial indicators. |
fsQuarterData | 分省季度数据 | Quarterly statistics for provinces, autonomous regions, and municipalities, such as quarterly GDP. |
fsYearData | 分省年度数据 | Annual statistics for provinces, autonomous regions, and municipalities. This is often the best starting point for province-level thematic maps and contains many indicator categories. |
mainMonthData | 主要城市月度价格 | Monthly price statistics for major cities, such as consumer prices and commodity prices. |
hongKongYearData | 香港特别行政区年度数据 | Annual statistics for the Hong Kong Special Administrative Region. |
macaoYearData | 澳门特别行政区年度数据 | Annual statistics for the Macao Special Administrative Region. |
taiwanYearData | 台湾省年度数据 | Annual statistics for Taiwan Province. |
Use these direct page URLs when you already know the correct regional data entry:
| Page | URL |
|---|---|
| 分省月度数据 | https://data.stats.gov.cn/dg/website/page.html#/pc/national/fsMonthData |
| 分省季度数据 | https://data.stats.gov.cn/dg/website/page.html#/pc/national/fsQuarterData |
| 分省年度数据 | https://data.stats.gov.cn/dg/website/page.html#/pc/national/fsYearData |
| 主要城市月度价格 | https://data.stats.gov.cn/dg/website/page.html#/pc/national/mainMonthData |
| 香港特别行政区年度数据 | https://data.stats.gov.cn/dg/website/page.html#/pc/national/hongKongYearData |
| 澳门特别行政区年度数据 | https://data.stats.gov.cn/dg/website/page.html#/pc/national/macaoYearData |
| 台湾省年度数据 | https://data.stats.gov.cn/dg/website/page.html#/pc/national/taiwanYearData |
Use this quick selection rule:
| Geography | Monthly | Quarterly | Annual |
|---|---|---|---|
| Provinces, autonomous regions, municipalities | fsMonthData | fsQuarterData | fsYearData |
| Major cities | mainMonthData | - | Use the corresponding major-city annual entry if the site exposes it for the requested indicator. |
| Hong Kong | - | - | hongKongYearData |
| Macao | - | - | macaoYearData |
| Taiwan Province | - | - | taiwanYearData |
When the user asks for province-level annual thematic data, prefer fsYearData first. When the user asks for monthly or quarterly province-level indicators, use fsMonthData or fsQuarterData instead. When the user asks for Hong Kong, Macao, or Taiwan annual statistics, use their dedicated annual pages instead of forcing them into the mainland province table.
Pay close attention to the region selector on province-level pages such as fsMonthData, fsQuarterData, and fsYearData. This selector contains the names of individual provinces, autonomous regions, and municipalities, but it also contains a special option named 序列.
When the user needs data for all provinces nationwide, choose 序列 in the region selector. This shows all provincial units at once and is usually the correct way to build a province-level table for mapping or cross-region comparison.
Do not select provinces one by one unless the user explicitly asks for only a small set of specific regions. Selecting 序列 is faster, less error-prone, and avoids accidentally omitting a province.
After you find the likely data location on the NBS website, do not immediately turn the first visible table into a deliverable. The NBS pages often contain multiple indicators, time ranges, regional dimensions, units, and table layouts that look similar. Use what you can see on the official website to help the user make a precise choice.
Before preparing the final file, confirm the key details with the user:
Once the user confirms the dataset, organize the data visible on the website into an .xlsx workbook and provide that workbook as the deliverable. The workbook should be clean enough for downstream mapping or analysis: use clear column names, keep the original region names and time labels, record the unit shown on the page when available, and include a small source note with the NBS page URL and access date.
When the NBS table is missing data for a region the user needs, such as Taiwan Province, Hong Kong, or Macao, first make sure the missing value is not available elsewhere on the NBS data platform. Check the dedicated regional pages when appropriate, especially hongKongYearData, macaoYearData, and taiwanYearData.
If the NBS platform still does not provide the needed value, you may search the internet for a reliable supplementary source. Prefer official statistical agencies, government publications, statistical yearbooks, or other clearly attributable sources. Do not silently merge supplementary values into the NBS table as if they came from the same source.
In the final .xlsx workbook, clearly mark any value that does not come from the National Bureau of Statistics. Add source columns or a source note sheet that records the supplementary source name, URL, access date, and any unit or definition differences. If the supplementary source uses a different statistical definition or time period, explain that limitation to the user instead of forcing the value into the table without qualification.
© zzhonglei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in contributions/china-statistics-data/skill of zzhonglei/GeoCode-Release.
Open the folder on GitHubat commit 6e3534f
China Statistics Data next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| China Statistics Data this skillzzhonglei/GeoCode-Release | 189 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Verified Researchsweetcornna/free-search-mcp | 126 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Find Hypertable Candidatestimescale/pg-aiguide | 1.9k | 1 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Querying Indonesian Gov Datasuryast/indonesia-gov-apis | 172 | — | ~997 | Automated safety check: Pass | MIT | |
| Sub2submekoand/sub2sub | 114 | — | ~5.2k | Automated safety check: Pass | MIT | |
| Scraplingforyourhealth111-pixel/Vibe-Skills | 3.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
sweetcornna/free-search-mcp
Use with the free-search MCP tools whenever a web lookup must yield facts someone will rely on: dates, deadlines, prices, prizes, fees, rules, eligibility, schedules, versions, statistics, news, or…
timescale/pg-aiguide
A skill your agent uses to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables.
suryast/indonesia-gov-apis
Query 57 Indonesian government APIs and data sources — BPJPH halal certification, BPOM food safety, OJK financial legality, BPS statistics, BMKG weather/earthquakes, Bank Indonesia exchange rates…
mekoand/sub2sub
Review first-use settings, check or install updates, open local management, troubleshoot and report problems, query task statistics or quota, share a node, connect with an invitation, delegate or…
foryourhealth111-pixel/Vibe-Skills
CLI-first web scraping & content extraction with optional MCP server.
tombelieber/claude-view
A skill your agent uses when the user asks about usage analytics, statistics, token usage, or cost summary — e.g.
zzhonglei/GeoCode-Release
Create well-designed maps that follow standard cartographic conventions.
zzhonglei/GeoCode-Release
Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm) where the workbook file is the primary deliverable.
zzhonglei/GeoCode-Release
GEE scripting and remote sensing analysis workflow guide. An agent skill from zzhonglei/GeoCode-Release.
zzhonglei/GeoCode-Release
Select an appropriate projected coordinate system for geographic data analysis or cartographic tasks.
zzhonglei/GeoCode-Release
Official, standards-compliant vector boundaries of China's administrative divisions — province, city and county polygons.
zzhonglei/GeoCode-Release
Sample skill verifying the GeoCode skill store pipeline end-to-end.
Works with
Categories
Find, download, and prepare official thematic statistics from the National Bureau of Statistics of China. China Statistics Data is an agent skill from zzhonglei/GeoCode-Release. Find, download, and prepare official thematic statistics from the National Bureau of Statistics of China.
China Statistics Data fits situations like: the user needs Chinese statistical indicators such as GDP; census/yearbook tables; other socio-economic data for mapping.
Run `npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a claude-code`. Or copy the skill folder (contributions/china-statistics-data/skill in zzhonglei/GeoCode-Release) into .claude/skills/china-statistics-data in your project. Claude Code loads it when a task matches its description.
Run `npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a codex`. Or copy the skill folder (contributions/china-statistics-data/skill in zzhonglei/GeoCode-Release) into .agents/skills/china-statistics-data in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zzhonglei/GeoCode-Release --skill china-statistics-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/china-statistics-data, .gemini/skills/china-statistics-data, .github/skills/china-statistics-data and .opencode/skills/china-statistics-data in your project.
SKILL.md names no scripts, command-line tools or credentials: China Statistics Data is instructions for the agent only.
SKILL.md names 1 domain. In commands or code: data.stats.gov.cn; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
China Statistics Data is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with China Statistics Data: Verified Research (sweetcornna/free-search-mcp, 126 stars), Find Hypertable Candidates (timescale/pg-aiguide, 1.9k stars), Querying Indonesian Gov Data (suryast/indonesia-gov-apis, 172 stars) and Sub2sub (mekoand/sub2sub, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
zzhonglei (a GitHub user) maintains it in zzhonglei/GeoCode-Release, which has 189 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 4, 2026.
Source: zzhonglei/GeoCode-Release on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.