ai-builder

A guide for creating custom AI Builder prompts in Microsoft Dataverse and adding them as actions for Copilot Studio agents or Power Automate flows.

In plain words
What is it for?
Use it to design prompt inputs and outputs, choose where the prompt runs, and activate the resulting AI model.
Why use it?
It provides a way to define document, image, classification, summarisation, or extraction tasks through prompts without training a custom model.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/geekfujiwara/codeappsdevelopmentstandard/ai-builder
Any agent
npx skills add geekfujiwara/CodeAppsDevelopmentStandard --skill ai-builder
Clone the repo
git clone --depth 1 https://github.com/geekfujiwara/CodeAppsDevelopmentStandard

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.04283
Opus 5 $0.00030 $0.02142
Sonnet 5 $0.00012 $0.00857
Haiku 4.5 $0.00006 $0.00428

Measured 3d ago against content hash 6f6539d4ef7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-builder scanned grade A with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/deploy_ai_prompt.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

r = requests.post(
.github/skills/ai-builder/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Builder AI プロンプト構築スキル

AI Builder の AI プロンプト(GPT Dynamic Prompt) を Dataverse API で作成し、 Copilot Studio エージェントに ツール(アクション) として追加する。 Power Automate フローから aibuilderpredict_customprompt で呼び出すパターンも含む。

基本方針: AI プロンプトを常にプレビルトモデルより優先する

AI Builder で AI 処理を実装する場合、以下の方針に従う:

✅ AI プロンプト(カスタムプロンプト)を常に第一選択肢とする
  - 請求書処理、ドキュメント情報抽出、分類、要約 等すべて
  - プロンプトテキスト + document/image 入力で柔軟に対応
  - トレーニングデータ不要、即座にデプロイ・更新可能
  - プロンプト変更だけで出力形式・抽出項目を自由に調整

❌ プレビルトモデル(請求書処理モデル等)は原則使用しない
  - 従来型のプレビルトモデルやカスタムモデルはトレーニング(学習)が必要
  - AI プロンプトで同等の処理がプロンプトだけで実現できる

⚠ プレビルトモデルを使う例外ケース(稀)
  - 手書き文字の高精度 OCR が必須で AI プロンプトでは精度不足の場合
  - 既存のプレビルトモデルが組み込まれたワークフローを維持する必要がある場合

前提: 設計フェーズ完了後に構築に入る(必須)

AI プロンプトを構築する前に、プロンプト設計をユーザーに提示し承認を得ていること。

設計提示時に含める内容:

項目 内容
プロンプト名 英語推奨(スキーマ名に使用される)
プロンプトテキスト リテラルテキスト+入力変数の組み合わせ
入力変数 名前・型(text / document / image)・説明・テスト値
出力形式 text or json(JSON の場合はスキーマ+サンプル)
モデルパラメータ モデル種別(gpt-41-mini 等)・temperature
利用先 Copilot Studio ツール or Power Automate フロー
shouldPromptUser 各入力変数をユーザーに自動的に尋ねるか(true/false)

重要事項: AIModelPublish 1ステップ・アクティベーション

2026-04-15 検証済み: AIModelPublish アクションは1ステップでモデルを完全にアクティブ化する。

従来(旧パターン — ❌ 複雑で環境差異に弱い):
  1. Create Model
  2. Create Training Config (statecode=2, statuscode=6 を指定)
  3. Create Run Config (statecode=2, statuscode=7 を指定)
  4. PATCH Model (_msdyn_activerunconfigurationid_value + statecode=1)
  → 環境によって statecode/statuscode 指定や _value PATCH が拒否される

正解(新パターン — ✅ シンプルで確実):
  1. Create Model([email protected] 形式)
  2. AIModelPublish(msdyn_ プレフィックスなし unbound action)
     → Published Training Config (state=2, status=6) を自動生成
     → Run Config (state=2, status=7) を自動生成(RunConfigurationId の値が ID になる)
     → Model を Active (state=1, status=1) に自動変更
  → 完了! わずか 2 API コール

更新時:
  1. 既存 Model を検索 → Active Run Config の ID を取得
  2. Run Config の msdyn_customconfiguration を PATCH
  → 完了!(再公開不要)

Read the full file on GitHub · 384 lines

Files

What ships with it

4 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.

Changes

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.

  1. 3d ago First seen · 384 lines · 60 tokens per session scan A 6f6539d4ef7c

Subscribe to this mod's changes

ai-builder is a skill published in the GitHub repository geekfujiwara/CodeAppsDevelopmentStandard (59 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 4,283 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

gpt-5-4-prompting

Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin.

openai/codex-plugin-cc · 40 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens

hve-builder

Author, review, or validate Copilot prompt-engineering artifacts through independent review, behavior testing, and host checks.

microsoft/hve-core · 27 tokens