geo-software-eval SKILL.md skillA

geo-software-eval from yuiseki/geo-software-factory is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yuiseki/geo-software-factory/geo-software-eval@git:20261114.7ec3565

Pins git:20261114.7ec3565 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yuiseki/geo-software-factory
Path
.agents/skills/geo-software-eval/SKILL.md
Versions recorded
5
Latest version
git:20261114.7ec3565, committed Nov 14, 2026
First version recorded
Nov 12, 2026
Size
10,372 bytes
Repository stars
12
License
Apache-2.0

地図プロダクトの正しさを、人間のコードレビューに頼らずに評価する仕組み (評価ハーネス) を設計し、動かす。昼に人間と一緒に、利用者が達成したいことを外から観測できるシナリオにし、実装から切り離して置く。夜は実装とは別の評価者がシナリオを手元と本番で動かし、観測した振る舞いで判定し、症状だけを実装に返す。評価そのものが正しいかも確かめる。「完成の条件を決めたい」「受け入れテストを作って」「シナリオを書いて」「評価して」「本当に動くか確かめて」と言われたとき、ダークファクトリーの昼の擦り合わせと、夜の geo-software-build と geo-software-deploy の間で使う。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# geo-software-eval

ダークファクトリーの中心は、AI がコードを書くことではなく、ソフトウェアの正しさを人間のコードレビュー以外の方法で評価し、その結果で開発を進めることにある ([WHAT_IS_DARK_FACTORY.md](../../../WHAT_IS_DARK_FACTORY.md))。評価基準と検証の仕組みは不要にならず、むしろ人間が先に設計する必要が高まる。このスキルは、その評価の設計 (昼) と実行 (夜) を扱う。

| reference | 読むとき | 中身 |
|---|---|---|
| [design-review](references/design-review.md) | 実装前に設計案を別の文脈で確かめるとき、設計と実装のずれを調べるとき | 会話を知る設計者と初見のレビュー者の役割、指摘の扱い、振る舞いの独立評価との違い |
| [scenarios](references/scenarios.md) | 昼に評価を設計するとき | シナリオの書き方、粒度、本人と決めること、置き場所 |
| [map-observables](references/map-observables.md) | シナリオの観測と判定を書くとき | 地図のアプリで外から観測できるもの (描画、地物、タイル、帰属表示、現在地、端末) |
| [judging](references/judging.md) | 判定の仕方を決めるとき、夜に評価するとき | 機械の判定と LLM の判定の使い分け、評価者の独立、実装への返し方 |
| [twins](references/twins.md) | 外部のサービスに頼る機能を評価するとき | 地図のタイル、認証、ジオコーダなどの代役と、その限界 |
| [progress](references/progress.md) | 進み具合を報告するとき、群れを動かしているとき | マージ数でなく、価値づけされ、検証され、届き、持ちこたえた変更で測る。逃げた不具合の数え方 |
| [brakes](references/brakes.md) | 人間の確認を減らすかを決めるとき | ブレーキ (人間の確認) を評価の証拠で 1 つずつ外し、崩れたら戻す。外さないブレーキ |
| [eval-of-eval](references/eval-of-eval.md) | 評価を作ったとき、評価が全部通ったとき | 評価そのものが正しいかの確かめ方 (壊した版で落ちるか、甘い判定の見つけ方) |
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_er53em6rrxg76ryw/f4f72a329182402e012f3d842e402ca31e3e50305a4e32d41a62ec8731eaf914.json

Then /plugin install geo-software-eval@markdownregistry-er53em6rrxg76ryw in Claude Code. It installs git:20261114.7ec3565, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add yuiseki/geo-software-factory/geo-software-eval@sha256:f4f72a329182402e

The line at the top of this page pins the label git:20261114.7ec3565, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_er53em6rrxg76ryw.svg)](https://markdownregistry.com/a/art_er53em6rrxg76ryw)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in yuiseki/geo-software-factory/geo-software-eval since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of geo-software-eval from somewhere else? Ask it: where did my geo-software-eval come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Nov 12, 2026 and Nov 14, 2026, more than one a day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261114.7ec3565 latest2026-11-14 7ec3565 10,372 BA view · diff
git:20261112.6eaa66e2026-11-12 6eaa66e 9,695 BA view · diff
git:20261112.5fa93682026-11-12 5fa9368 9,183 BA view · diff
git:20261112.e30bb8e2026-11-12 e30bb8e 8,769 BA view · diff
git:20261112.91f2e7e2026-11-12 91f2e7e 8,199 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10372 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

yuiseki/geo-software-factory · 12 stars · license Apache-2.0 · pushed 2026-11-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_er53em6rrxg76ryw
GET https://markdownregistry.com/api/v1/resolve?ref=yuiseki/geo-software-factory/geo-software-eval
GET https://markdownregistry.com/api/v1/blob/f4f72a329182402e012f3d842e402ca31e3e50305a4e32d41a62ec8731eaf914

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from yuiseki/geo-software-factory

AGENTS.md@.agents/skills AGENTS.md file
yuiseki/geo-software-factory · .agents/skills/AGENTS.md
git:20261113.a912aab · audit A · 12 stars
geo-software-arch SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-arch/SKILL.md · 地図プロダクトのアーキテクチャを、保存・計算・表現の 3 つの要素と、クラウド・エッジ・ブラウザ/アプリの 3 つの置き場所の組み合わせとして比較し決める。タイル配信、検索…
git:20261113.2f9f217 · audit A · 12 stars
geo-software-auth SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-auth/SKILL.md · 地図プロダクトの認証と認可の仕組みを比較し選ぶ。管理型の認証サービス (Auth0、Clerk、Firebase Authentication、Supabase Auth、Neon Auth、Amazon…
git:20261112.c078140 · audit A · 12 stars
geo-software-build SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-build/SKILL.md · 技術選定の済んだ地図プロダクトを、人間を呼ばずに実装してテストし、実装と別の評価者 (geo-software-eval) の評価に通るまで直す。技術選定の結果から、テストを先に書いて小さく積み、地図に載せるデータを出典つきで組み立て、画面…
git:20261114.05b9cc4 · audit A · 12 stars
geo-software-data SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-data/SKILL.md · 地図に載せる主題データ (ベースマップ以外) の出どころを比較し選ぶ。OpenStreetMap、Overture Maps、国土数値情報、基盤地図情報、e-Stat…
git:20261113.0d9593d · audit A · 12 stars
geo-software-deploy SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-deploy/SKILL.md · 実装とテストの済んだ地図プロダクトを、人間を呼ばずに公開し、本番で確かめる。昼に準備した認証と権限の範囲で、DB のマイグレーション、デプロイ、独自ドメインの割り当て、本番の URL…
git:20261113.0d9593d · audit A · 12 stars
geo-software-growth SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-growth/SKILL.md · (未着手のプレースホルダー。中身はまだ無い) 公開した地図アプリの利用者を増やす。手順が書かれるまでは使わない。
git:20261112.c078140 · audit A · 12 stars
geo-software-infra SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-infra/SKILL.md · 地図プロダクトの要件に応じて、ベースマップ、衛星・航空写真、3D データの供給元を比較し技術選定する。商用サービス (Google Maps, Mapbox, MapTiler, Esri, HERE, TomTom, Geolonia…
git:20261116.e26f846 · audit A · 12 stars
geo-software-legal-check SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-legal-check/SKILL.md · 地図プロダクトを公開する前に、法令と規約と権利の確認をする。帰属表示、ODbL の派生データベース、測量法による地図の複製・使用の承認 (地理院地図、基盤地図情報)、位置情報と個人情報、電気通信事業法の外部送信規律、地図 API の規約…
git:20261112.c078140 · audit A · 12 stars
geo-software-library SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-library/SKILL.md · 地図プロダクトを実装するためのライブラリや SDK を、要件に応じて比較し技術選定する。Web (Leaflet, MapLibre GL JS, Mapbox GL JS, Google Maps JavaScript API…
git:20261116.e26f846 · audit A · 12 stars
geo-software-migrate SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-migrate/SKILL.md · 既存の地図プロダクトを、別の地図サービスやライブラリへ乗り換える計画を立てる。Google Maps Platform、Mapbox、Leaflet とラスタタイルからの移行で、今の地図が使っているものの棚卸し、API…
git:20261114.05b9cc4 · audit A · 12 stars
geo-software-monetize SKILL.md skill
yuiseki/geo-software-factory · .agents/skills/geo-software-monetize/SKILL.md · (未着手のプレースホルダー。中身はまだ無い) 地図アプリで収益を得る。手順が書かれるまでは使わない。
git:20261112.c078140 · audit A · 12 stars

Every file in yuiseki/geo-software-factory

Browse by kind, by grade A, or by owner.

Kept in .agents/skills, the folder Codex reads. More agent skills for Codex.