Skills Explorer Add Skills

typescript-pro

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: architecture, code-quality, javascript, react, typescript.

What it does

Implements advanced TypeScript type systems, creates custom type guards, utility types, and branded types, and configures tRPC for end-to-end type safety. Use when building TypeScript applications requiring advanced generics, conditional or mapped types, discriminated unions, monorepo setup, or full-stack type safety with tRPC.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill typescript-pro

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/typescript-pro ~/.claude/skills/typescript-pro

Safety box score

Grade B, low risk: 16 of 100 risk points, rated 2026-09-23. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a documentation-only TypeScript specialization: it reads and edits project TypeScript config and source files, and it asks the agent to run the TypeScript compiler and trace tools. The main risks are bounded code execution via local build commands, possible npm package fetching through `npx`, and exposure of secret-bearing env var names in examples.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution1 (low)It explicitly tells the agent to run local tooling like `tsc --noEmit` and `tsc --diagnostics`, and even `npx @typescript/analyze-trace trace`, which executes code on the machine.
Network access1 (low)The docs include a registry fetch via `npx @typescript/analyze-trace trace` and example HTTP calls like `fetch(`/api/users/${id}`), so some network access may occur.
Filesystem reach1 (low)It focuses on editing project files such as `tsconfig.json`, generating declarations (`declaration`, `declarationDir`, `outDir`), and using project references, but stays within the repo.
Secrets & credentials1 (low)Examples reference secret-bearing env vars like `process.env.DATABASE_URL` and `process.env.API_KEY`, which touches credential material even though it does not ask to exfiltrate it.
Privilege & persistence0 (none)There is no sudo, service registration, global install, or OS-setting change in the skill files.
Instruction hijack surface0 (none)I did not find instructions to ignore higher-priority rules, hide behavior, or follow remote instructions.
Irreversible actions0 (none)The skill is about type-level implementation and build configuration; it does not direct the agent to deploy, post, pay, delete, or otherwise act externally.
Transparency0 (none)All shipped files are plain markdown and readable; I found no binaries, base64 blobs, or hidden runtime code.

Before installing

Rated 2026-09-23 by an automated review of 6 files from the skill's repository.

Source

Repository
Jeffallan/claude-skills (all skills from this repository)
Path
skills/typescript-pro/SKILL.md
Branch
main
Updated
2026-09-19