Mirror Types
CheckedThis skill mirrors specific token types (e.g., "mirror") to create variations and explore different narrative paths within your story.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add marius-townhouse/effective-typescript-skills --skill mirror-types -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
marius-townhouse
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.
Automated safety checks
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 marius-townhouse/effective-typescript-skills at d754db2077.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- d754db2077
- Manifest
- skills/mirror-types/SKILL.md
- Scanned
- 1 file, 59 lines
About this skill
What it does
The mirror-types skill allows AI agents to reflect TypeScript types, effectively creating new types based on existing ones. This is useful for generating more complex or specialized type definitions programmatically. It can also be used to create aliases and perform type transformations within a TypeScript project. The skill facilitates advanced type manipulation without manual coding.
When to use it
- Generating custom type guards: Create specific type checks based on existing types, improving code safety and clarity.
- Automating boilerplate type definitions: Reduce repetitive typing by programmatically generating type declarations from source data or other type information.
- Creating complex union or intersection types: Simplify the creation of intricate type combinations that would be cumbersome to write manually.
- Refactoring TypeScript codebases: Automate type changes across a project, ensuring consistency and reducing errors during large-scale refactorings.
Key capabilities
- Type reflection
- Type generation
- Type aliases
- Type transformations
Example prompts
- "Generate a new type based on
interface User { name: string; age: number; }but with the property 'age' optional." - "Create an alias for the type
type ApiResponse<T> = { data: T; status: number; }calledPaginatedResponsewhereTis always an array." - “Reflect the following type and output a summary of its properties:
interface Product { id: string, price: number, description?: string }”
Tips & gotchas
This skill requires a working TypeScript environment. The agent's understanding of TypeScript syntax and semantics will influence the quality of generated types; ensure it has sufficient context for accurate reflection.