How do I install the Baml Codegen skill?

Run npx skillmds@latest add modbender/baml-codegen in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Baml Codegen safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Baml Codegen?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Baml Codegen free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Baml Codegen?

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Baml Codegen by modbender — Agent Skill

Name: Baml Codegen
Rating: 4.2 (5 reviews)
Author: modbender

Baml Codegen

Use when generating BAML code for type-safe LLM extraction, classification, RAG, or agent workflows - creates complete .baml files with types, functions, clients, tests, and framework integrations from natural language requirements. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), Python/TypeScript/Ruby/Go, 10+ frameworks, 50-70% token optimization, 95%+ compilation success.

modbender Updated Sep 9, 2026 12 repo stars

File contents

BAML Code Generation

Generate type-safe LLM extraction code. Use when creating structured outputs, classification, RAG, or agent workflows.

Golden Rules

NEVER edit baml_client/ - 100% generated, overwritten on every baml-cli generate; check baml_src/generators.baml for output_type (python, typescript, ruby, go)
ALWAYS edit baml_src/ - Source of truth for all BAML code
Run baml-cli generate after changes - Regenerates typed client code for target language

Philosophy (TL;DR)

Schema Is The Prompt - Define data models first, compiler injects types
Types Over Strings - Use enums/classes/unions, not string parsing
Fuzzy Parsing Is BAML's Job - BAML extracts valid JSON from messy LLM output
Transpiler Not Library - Write .baml → generate native code (Python/TypeScript/Ruby/Go), no runtime dependency
Test-Driven Prompting - Use VS Code playground or baml-cli test to iterate

Workflow

Analyze → Pattern Match (MCP) → Validate → Generate → Test → Deliver
         ↓ [IF ERRORS] Error Recovery (MCP) → Retry

BAML Syntax

Element	Example
Class	`class Invoice { total float @description("Amount") @assert(this > 0) @alias("amt") }`
Enum	`enum Category { Tech @alias("technology") @description("Tech sector"), Finance, Other }`
Function	`function Extract(text: string, img: image?) -> Invoice { client GPT5 prompt #"{{ text }} {{ img }} {{ ctx.output_format }}"# }`
Client	`client<llm> GPT5 { provider openai options { model gpt-5 } retry_policy Exponential }`
Fallback	`client<llm> Resilient { provider fallback options { strategy [FastModel, SlowModel] } }`

Types

Primitives: string, int, float, bool | Multimodal: image, audio
Containers: Type[] (array), Type? (optional), map<string, Type> (key-value)
Composite: Type1 | Type2 (union), nested classes
Annotations: @description("..."), @assert(condition), @alias("json_name"), @check(name, condition)

Providers

openai, anthropic, gemini, vertex, bedrock, ollama + any OpenAI-compatible via openai-generic

Pattern Categories

Pattern	Use Case	Model	Framework Markers
Extraction	Unstructured → structured	GPT-5	fastapi, next.js
Classification	Categorization	GPT-5-mini	any
RAG	Answers with citations	GPT-5	langgraph
Agents	Multi-step reasoning	GPT-5	langgraph
Vision	Image/audio data extraction	GPT-5-Vision	multimodal

Resilience

retry_policy: retry_policy Exp { max_retries 3 strategy { type exponential_backoff } }
fallback client: Chain models [FastCheap, SlowReliable] for cost/reliability tradeoff

MCP Indicators

Found patterns from baml-examples | Validated against BoundaryML/baml | Fixed errors using docs | MCP unavailable, using fallback

Output Artifacts

BAML Code - Complete .baml files (types, functions, clients, retry_policy)
Tests - pytest/Jest with 100% function coverage
Integration - Framework-specific client code (LangGraph nodes, FastAPI endpoints, Next.js API routes)
Metadata - Pattern used, token count, cost estimate

References

providers.md - OpenAI, Anthropic, Google, Ollama, Azure, Bedrock, openai-generic
types-and-schemas.md - Full type system, classes, enums, unions, map, image, audio
validation.md - @assert, @check, @alias, block-level @@assert
patterns.md - Pattern library with code examples
philosophy.md - BAML principles, golden rules
mcp-interface.md - Query workflow, caching
languages-python.md - Python/Pydantic, async
languages-typescript.md - TypeScript, React/Next.js
frameworks-langgraph.md - LangGraph integration

---name: baml-codegendescription: Use when generating BAML code for type-safe LLM extraction, classification, RAG, or agent workflows - creates complete .baml files with types, functions, clients, tests, and framework integrations from natural language requirements. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), Python/TypeScript/Ruby/Go, 10+ frameworks, 50-70% token optimization, 95%+ compilation success.license: Apache-2.0--- # BAML Code Generation Generate type-safe LLM extraction code. Use when creating structured outputs, classification, RAG, or agent workflows. ## Golden Rules - **NEVER edit `baml_client/`** - 100% generated, overwritten on every `baml-cli generate`; check `baml_src/generators.baml` for `output_type` (python, typescript, ruby, go) - **ALWAYS edit `baml_src/`** - Source of truth for all BAML code - **Run `baml-cli generate` after changes** - Regenerates typed client code for target language ## Philosophy (TL;DR) - **Schema Is The Prompt** - Define data models first, compiler injects types - **Types Over Strings** - Use enums/classes/unions, not string parsing - **Fuzzy Parsing Is BAML's Job** - BAML extracts valid JSON from messy LLM output - **Transpiler Not Library** - Write `.baml` → generate native code (Python/TypeScript/Ruby/Go), no runtime dependency - **Test-Driven Prompting** - Use VS Code playground or `baml-cli test` to iterate ## Workflow ``` Analyze → Pattern Match (MCP) → Validate → Generate → Test → Deliver ↓ [IF ERRORS] Error Recovery (MCP) → Retry ``` ## BAML Syntax | Element | Example | |---------|---------| | Class | `class Invoice { total float @description("Amount") @assert(this > 0) @alias("amt") }` | | Enum | `enum Category { Tech @alias("technology") @description("Tech sector"), Finance, Other }` | | Function | `function Extract(text: string, img: image?) -> Invoice { client GPT5 prompt #"{{ text }} {{ img }} {{ ctx.output_format }}"# }` | | Client | `client<llm> GPT5 { provider openai options { model gpt-5 } retry_policy Exponential }` | | Fallback | `client<llm> Resilient { provider fallback options { strategy [FastModel, SlowModel] } }` | ## Types - **Primitives**: `string`, `int`, `float`, `bool` | **Multimodal**: `image`, `audio` - **Containers**: `Type[]` (array), `Type?` (optional), `map<string, Type>` (key-value) - **Composite**: `Type1 | Type2` (union), nested classes - **Annotations**: `@description("...")`, `@assert(condition)`, `@alias("json_name")`, `@check(name, condition)` ## Providers `openai`, `anthropic`, `gemini`, `vertex`, `bedrock`, `ollama` + any OpenAI-compatible via `openai-generic` ## Pattern Categories | Pattern | Use Case | Model | Framework Markers | |---------|----------|-------|-------------------| | Extraction | Unstructured → structured | GPT-5 | fastapi, next.js | | Classification | Categorization | GPT-5-mini | any | | RAG | Answers with citations | GPT-5 | langgraph | | Agents | Multi-step reasoning | GPT-5 | langgraph | | Vision | Image/audio data extraction | GPT-5-Vision | multimodal | ## Resilience - **retry_policy**: `retry_policy Exp { max_retries 3 strategy { type exponential_backoff } }` - **fallback client**: Chain models `[FastCheap, SlowReliable]` for cost/reliability tradeoff ## MCP Indicators - Found patterns from baml-examples | Validated against BoundaryML/baml | Fixed errors using docs | MCP unavailable, using fallback ## Output Artifacts 1. **BAML Code** - Complete `.baml` files (types, functions, clients, retry_policy) 2. **Tests** - pytest/Jest with 100% function coverage 3. **Integration** - Framework-specific client code (LangGraph nodes, FastAPI endpoints, Next.js API routes) 4. **Metadata** - Pattern used, token count, cost estimate ## References - [providers.md](references/providers.md) - OpenAI, Anthropic, Google, Ollama, Azure, Bedrock, openai-generic - [types-and-schemas.md](references/types-and-schemas.md) - Full type system, classes, enums, unions, map, image, audio - [validation.md](references/validation.md) - @assert, @check, @alias, block-level @@assert - [patterns.md](references/patterns.md) - Pattern library with code examples - [philosophy.md](references/philosophy.md) - BAML principles, golden rules - [mcp-interface.md](references/mcp-interface.md) - Query workflow, caching - [languages-python.md](references/languages-python.md) - Python/Pydantic, async - [languages-typescript.md](references/languages-typescript.md) - TypeScript, React/Next.js - [frameworks-langgraph.md](references/frameworks-langgraph.md) - LangGraph integration

Frequently asked questions