Borrowing it
Nothing to install: this file belongs to geekfujiwara/CodeAppsDevelopmentStandard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/geekfujiwara/CodeAppsDevelopmentStandard/main/.github/skills/data-platform/SKILL.mdgit clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/data-platform)<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/data-platform"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/data-platform/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/geekfujiwara/codeappsdevelopmentstandard/data-platform"><img src="https://agentmods.dev/badge/skills/geekfujiwara/codeappsdevelopmentstandard/data-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.02375 |
| Opus 5.5 | $0.00046 | $0.00950 |
| Sonnet 5.5 | $0.00023 | $0.00475 |
| Haiku 4.5 | $0.00012 | $0.00237 |
Grade A, and why
data-platform scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
データ基盤構築スキル（Fabric / Databricks / Foundry IQ）
architecture の §6.6 で決めたデータ基盤を、すべて API で構築・検証する。 Foundry IQ はデータストアではなく、文書やオントロジーを根拠付きでエージェントに渡す knowledge layer として扱う。
| 原則 | 内容 |
|---|---|
| 役割ごとに選ぶ | system of record / analytics / semantic / knowledge を別々に決める（選定ガイド） |
| 1 基盤 = 1 リソースグループ | Databricks の managed RG は Databricks が作るので事前作成しない |
| 変更は hash 承認 | plan → planHash を提示 → apply --approve-hash。削除はスキルに含めない |
| 実測で判定 | HTTP 200・リソース存在・MCP の initialize だけで成功にしない。業務の正解まで確認する |
| キーレス | Entra トークン（standard の auth_helper）とロールで認可する。API キー・PAT を使わない |
| コストを止める | 検証後は必ず manage_compute.py stop を実行し、常時課金されるリソースを報告する |
サブリファレンス
| リファレンス | 内容 |
|---|---|
| 設計 | 責務分担、契約、状態分類、安全モデル、認証スコープ |
| テスト計画 | Unit / Contract / Live / E2E の ID と合格基準 |
| Microsoft Fabric | capacity・workspace・Lakehouse・Ontology item・Ontology MCP |
| Azure Databricks | workspace・SQL warehouse・metric view・Genie・managed MCP |
| Foundry IQ | Search・knowledge source・knowledge base・retrieve / MCP |
| Dataverse への委譲 | system of record が Dataverse の場合の担当範囲 |
| MCP 公開 | 基盤ごとの MCP エンドポイントと公開先スキル |
| capability-matrix.json | 基盤選定の重みと MCP テンプレート（正本） |
| .env サンプル | 本スキルのパラメータ |
| 異常系・トラブルシュート | 実際に踏んだ失敗と恒久対策 |
ワークフロー（正常系）
スクリプトはすべて .github/skills/data-platform/scripts/ にある。以下では $dp と略す。
$dp = ".github/skills/data-platform/scripts"
Step 1: 選定契約を確定する
spec/data-platform.json が無ければ、architecture のヒアリング結果から作る。
python $dp/recommend_platform.py --requirements spec/data-requirements.json --out spec/data-platform.json
終了コード 3（needsDecision あり）なら、候補と理由を AskUserQuestion で提示して確定する。
decision.systemOfRecord が dataverse の部分は dataverse スキル に渡す。
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/.env.example 2.3 KB
- references/capability-matrix.json 2.2 KB
- references/databricks.md 3.5 KB
- references/dataverse.md 1.2 KB
- references/design.md 6.6 KB
- references/fabric.md 3.1 KB
- references/foundry-iq.md 3.0 KB
- references/mcp-exposure.md 2.3 KB
- references/samples/cold-chain-expected.json 765 B
- references/samples/cold-chain-manuals.json 874 B
- references/samples/cold-chain-semantics.json 4.3 KB
- references/templates/databricks-workspace.json 1.2 KB
- references/templates/fabric-capacity.json 1.0 KB
- references/templates/foundry-iq.json 7.2 KB
- references/test-plan.md 9.2 KB
- references/troubleshooting.md 3.9 KB
- scripts/configure_semantics.py 12 KB runs code
- scripts/data_platform_common.py 14 KB runs code
- scripts/deploy_platform.py 15 KB runs code
- scripts/manage_compute.py 3.8 KB runs code
- scripts/preflight_platform.py 4.8 KB runs code
- scripts/recommend_platform.py 7.6 KB runs code
- scripts/verify_platform.py 17 KB runs code
- tests/fakes.py 2.0 KB runs code
- tests/test_common.py 5.6 KB runs code
- tests/test_configure_semantics.py 5.6 KB runs code
- tests/test_deploy_platform.py 6.4 KB runs code
- tests/test_manage_compute.py 2.2 KB runs code
- tests/test_recommend_platform.py 4.3 KB runs code
- tests/test_verify_platform.py 9.5 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 28d ago Changed 42c8ae32b842
- 1mo ago First seen · 156 lines · 115 tokens per session scan A d0836c9c4a1e
data-platform is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (78 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 2,375 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
data-platform compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| data-platformgeekfujiwara/CodeAppsDevelopmentStandard | Skill | 78 | yesterday | MIT | A | 115 | Claude Code, Codex |
| arrowspacesickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 28 | Claude Code |
| docetlucbepic/docetl | Skill | 4.2k | 7d ago | MIT | A | 59 | Claude Code, Codex |
| senior-data-engineerbenchflow-ai/skillsbench | Skill | 1.9k | 2d ago | Apache-2.0 | A | 100 | Claude Code, Codex |
| swiftidebosun-ai/swiftide | Skill | 802 | yesterday | MIT | A | 47 | Claude Code, Codex |
| malloy-modelmalloydata/publisher | Skill | 130 | today | MIT | A | 59 | Claude Code, Codex |
| eval-importmalloydata/publisher | Skill | 130 | today | MIT | A | 142 | Claude Code, Codex |