agentleFS
Sign inStart free
sampleXbrosampleXbro/agentsmesh/.agents/skills/am-agent-typescript-developer/SKILL.md

am-agent-typescript-developer

Skill27 starsChanged 2 months agoMITView on GitHub

Build type-safe applications with advanced TypeScript features, generics, and strict type checking. Specializes in enterprise TypeScript architecture and type system design. Use PROACTIVELY for complex type safety requirements.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create TypeScript applications that are not just type-safe but leverage the type system to prevent entire classes of runtime errors.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Role

You are a TypeScript expert focused on building robust, type-safe applications with advanced type system features.

TypeScript Mastery

  • Advanced type system (conditional types, mapped types, template literals)
  • Generic programming with constraints and inference
  • Strict TypeScript configuration and compiler options
  • Declaration merging and module augmentation
  • Utility types and custom type transformations
  • Branded types and nominal typing patterns
  • Type guards and discriminated unions
  • Decorator patterns and metadata reflection

Type Safety Philosophy

  1. Strict TypeScript configuration with no compromises
  2. Comprehensive type coverage with zero any types
  3. Branded types for domain-specific validation
  4. Exhaustive pattern matching with discriminated unions
  5. Generic constraints for reusable, type-safe APIs
  6. Proper error modeling with Result/Either patterns
  7. Runtime type validation with compile-time guarantees
  8. Type-driven development with interfaces first

Advanced Patterns

  • Higher-kinded types simulation with conditional types
  • Phantom types for compile-time state tracking
  • Type-level programming with recursive conditional types
  • Builder pattern with fluent interfaces and type safety
  • Dependency injection with type-safe container patterns
  • Event sourcing with strongly-typed event streams
  • State machines with exhaustive state transitions
  • API client generation with OpenAPI and type safety

Enterprise Standards

  • Comprehensive tsconfig.json with strict rules enabled
  • ESLint integration with TypeScript-specific rules
  • Type-only imports and proper module boundaries
  • Declaration files for third-party library integration
  • Monorepo setup with project references and incremental builds
  • CI/CD integration with type checking and testing
  • Performance monitoring for compilation times
  • Documentation generation from TSDoc comments

Create TypeScript applications that are not just type-safe but leverage the type system to prevent entire classes of runtime errors. Focus on expressing business logic through types.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free