Automated summary
This skill retrieves live Japanese public-sector data — MLIT real-estate transaction prices, public procurement listings (kkj), and the e-Stat statistics portal — through an MCP server invoked by a curl-based script.
Strengths
- Bundles three distinct official data sources (property prices, public tenders, government statistics) in one skill
- Ships a ready-to-use helper script (scripts/mcp-call.sh) with concrete invocation examples
- Captures real-world gotchas: prefecture/municipality codes, missing region filter in kkj-search, and the e-Stat lookup order
- Flags public-API limitations such as rate limits and tender details living on the source portal
Limitations
- Fully dependent on the external mcp.n-3.ai MCP server being reachable
- Requires shell/exec access; web_fetch is unusable because the endpoint speaks SSE
- Procurement results are search listings only — no specs, budgets, or deadlines
Use it when a request concerns actual Japanese property transaction prices, Japanese public tenders, or official Japanese government statistics.
Avoid it when the environment cannot run shell commands or the mcp.n-3.ai MCP server is not configured.
Security analysis
CautionThe skill uses powerful but legitimate mechanisms—bash and curl—to query public Japanese government open-data APIs through an external MCP server. There is no evidence of destructive commands, credential exfiltration, obfuscation, or safety-disabling instructions. However, the referenced shell script is not shown and the external MCP endpoint must be trusted, so it warrants caution rather than being marked fully safe.
- •Instructs execution of a bundled shell script (`scripts/mcp-call.sh`) via `bash`; the script contents are not included, so behavior cannot be fully verified from SKILL.md.
- •Makes outbound `curl` requests to a third-party MCP endpoint (`mcp.n-3.ai`), creating a network dependency and trust requirement.
- •No explicit handling of secrets or credentials, and no destructive commands are present.
Examples
大阪市の2025年第3四半期の不動産取引価格を調べて、価格帯の傾向をまとめてください。AI・人工知能関連の官公需(役務)の入札案件を検索して、見つかった案件を一覧にしてください。e-Statで「人口」に関する統計を検索し、統計IDを特定してメタ情報を確認してください。name: japan-gyousei-data description: 日本の行政オープンデータにアクセスする。不動産取引価格(国交省)、官公需・入札情報、e-Stat政府統計の3つのデータソースを検索・取得できる。「不動産価格を調べて」「入札情報を検索」「政府統計を取得」「官公需で○○を探して」「地価を調べて」「統計データ」などで使用。MCP server (mcp.n-3.ai) 経由でリアルタイムにデータ取得する。
行政オープンデータスキル
日本政府のオープンデータに MCP サーバー(mcp.n-3.ai)経由でアクセスする。
データソース
| # | 名前 | 用途 | ツール |
|---|------|------|--------|
| 1 | 不動産取引価格 | 国交省の実取引データ | reinfolib-real-estate-price, reinfolib-city-list |
| 2 | 官公需(入札) | 政府・自治体の調達案件検索 | kkj-search |
| 3 | e-Stat | 政府統計ポータル | e-stat-get-stats-list, e-stat-get-meta-info, e-stat-get-data-catalog |
呼び出し方法
exec で curl を使う。web_fetch は SSE 非対応のため不可。
スクリプト scripts/mcp-call.sh を使う:
bash <skill_dir>/scripts/mcp-call.sh <data_source> <tool_name> '<arguments_json>'
例
# 不動産: 大阪市の取引価格
bash scripts/mcp-call.sh reinfo reinfolib-real-estate-price '{"year":"2025","quarter":"3","area":"27","city":"27102"}'
# 不動産: 市区町村一覧を取得
bash scripts/mcp-call.sh reinfo reinfolib-city-list '{"area":"27"}'
# 官公需: AI関連の入札検索(カテゴリ3=役務)
bash scripts/mcp-call.sh kkj kkj-search '{"query":"AI 人工知能","category":"3"}'
# e-Stat: 統計一覧検索
bash scripts/mcp-call.sh estat e-stat-get-stats-list '{"searchWord":"人口"}'
ツール詳細
各ツールのパラメータ詳細は references/tools.md を参照。
注意点
- 官公需の地域フィルタ:
kkj-searchは都道府県パラメータ未対応。クエリ文字列に地名を含めて絞り込む - 官公需の詳細情報: MCP は検索結果一覧のみ返す。仕様書・金額・締切は元ポータルサイトを確認
- 不動産の都道府県コード: 2桁コード(東京=13, 大阪=27 等)。市区町村コードは
reinfolib-city-listで取得 - e-Stat: まず
get-stats-listで統計IDを特定し、get-meta-infoでメタ情報、get-data-catalogでデータ取得 - レート制限: 公共APIのため常識的な頻度で利用する
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/japanese-government-open-data-access-mrwakf33' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/japanese-government-open-data-access-mrwakf33/download' --output '.skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md.part' && mv '.skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md.part' '.skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md' && test -s '.skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/japan-gyousei-data' && cp -R '.skill-downloads/japanese-government-open-data-access-mrwakf33' '.claude/skills/japan-gyousei-data'Codex
test -f '.skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md' && test -s '.skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/japan-gyousei-data' && cp -R '.skill-downloads/japanese-government-open-data-access-mrwakf33' '.agents/skills/japan-gyousei-data'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/japanese-government-open-data-access-mrwakf33'openskills read 'japanese-government-open-data-access-mrwakf33'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/japanese-government-open-data-access-mrwakf33/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Agent-Driven Parameter Optimization
Data & AI
Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.
ICP Visitor Outreach
Data & AI
Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.