ReddRadar
Agent skill
typespec-sdk-generator
Microsoft TypeSpec-based API and SDK generation
Install this agent skill to your Project
npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/sdk-platform-development/skills/typespec-sdk-generator
SKILL.md
TypeSpec SDK Generator Skill
Overview
This skill utilizes Microsoft TypeSpec (formerly Cadl) to design APIs and generate multi-language SDKs following Azure SDK guidelines. TypeSpec provides a concise, type-safe language for API definition.
Capabilities
- Design APIs using TypeSpec language
- Generate multi-language SDKs (TypeScript, Python, Java, C#, Go)
- Emit OpenAPI and other specification formats
- Apply Azure SDK style guidelines automatically
- Implement decorators for rich API semantics
- Support versioning and deprecation patterns
- Generate strongly-typed clients
Target Processes
- SDK Code Generation Pipeline
- API Design Specification
- Multi-Language SDK Strategy
Integration Points
- TypeSpec compiler and emitters
- AutoRest for SDK generation
- Azure SDK code generation pipeline
- OpenAPI emitters
- Custom emitter development
Input Requirements
- TypeSpec model files (.tsp)
- Emitter configurations per target
- Versioning requirements
- Style guide preferences
- Custom decorators (if any)
Output Artifacts
- Generated SDK source code per language
- OpenAPI specifications
- JSON schemas
- API documentation
- Client library packages
Usage Example
skill:
name: typespec-sdk-generator
context:
modelDirectory: ./typespec
emitters:
- "@azure-tools/typespec-ts"
- "@azure-tools/typespec-python"
- "@typespec/openapi3"
applyAzureGuidelines: true
apiVersion: "2024-01-01"
Best Practices
- Use namespaces to organize API structure
- Leverage decorators for documentation and behavior
- Implement proper versioning with @versioned
- Use templates for reusable patterns
- Define clear model inheritance hierarchies
- Apply Azure SDK guidelines for consistency
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
a5c-ai/babysitter
gsd-tools
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
a5c-ai/babysitter
model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
a5c-ai/babysitter
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
a5c-ai/babysitter
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
a5c-ai/babysitter
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
a5c-ai/babysitter
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
Didn't find tool you were looking for?