Skip to content
TrustedSkillsbeta
Back to all skills

Type Inference

Checked
biomejs·vlatest·ai-ml·Apache-2.0

This skill automatically infers data types from code snippets, boosting developer productivity and reducing manual type annotations.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add biomejs/biome --skill type-inference -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

biomejs

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned biomejs/biome at ef0edd4a2f.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
ef0edd4a2f
Manifest
.claude/skills/type-inference/SKILL.md
Scanned
1 file, 209 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill provides access to Biome's type inference system, which automatically determines data types within code snippets. It leverages a module graph and specialized data structures like TypeReference and TypeData to enable fast, IDE-focused updates and performance. The system handles various TypeScript type constructs including primitives, functions, objects, unions, intersections, tuples, and more, represented by distinct variants of the TypeData enum.

When to use it

  • When working with Biome's code editor for improved developer productivity.
  • To understand how Biome infers types in local expressions (e.g., a + b).
  • For debugging or analyzing type inference results within a Biome project.
  • When needing to examine the module-level ("thin") type inference process, which resolves references within a single module's scope.

Key capabilities

  • Type Inference: Automatically determines data types from code.
  • Module Graph Integration: Operates within Biome’s module graph architecture.
  • TypeReference Usage: Utilizes TypeReference for type referencing instead of direct references to avoid stale data.
  • TypeData Enum Representation: Provides access to the TypeData enum, which represents various TypeScript types (e.g., Unknown, Boolean, Function, Object).
  • Local Inference: Performs type inference based on expressions without surrounding context.
  • Module-Level Inference: Resolves references within a module's scope.

Example prompts

  • "What is the inferred type of 'a + b' in this Biome project?"
  • "Show me the TypeData representation for the inferred type of this function."
  • "Explain how Biome resolves type references during module-level inference."

Tips & gotchas

  • This skill requires familiarity with TypeScript type system concepts and Biome's architecture.
  • Refer to crates/biome_js_type_info/CONTRIBUTING.md for detailed architectural information.
  • Biome prioritizes IDE support and instant updates, so data copying between modules is prohibited; instead, use TypeReference.