typescript-dev
TypeScript development. Use for TypeScript, Node.js, Express, Fastify, Zod, vitest, jest. Backend, CLI, libraries only — no frontend frameworks.
Best use case
typescript-dev is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
TypeScript development. Use for TypeScript, Node.js, Express, Fastify, Zod, vitest, jest. Backend, CLI, libraries only — no frontend frameworks.
Teams using typescript-dev should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/typescript-dev/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How typescript-dev Compares
| Feature / Agent | typescript-dev | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
TypeScript development. Use for TypeScript, Node.js, Express, Fastify, Zod, vitest, jest. Backend, CLI, libraries only — no frontend frameworks.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# TypeScript Development **Announce:** "I'm using the typescript-dev skill. Following the 4-phase workflow." ## MANDATORY: Read and Follow the Shared Workflow **You MUST read [workflow.md](../../shared/workflow.md) NOW** and follow ALL 4 phases defined there. The sections below provide TypeScript-specific inputs for each phase. Read [patterns.md](patterns.md) during Phase 1. **If you lost workflow.md from context:** Re-read `../../shared/workflow.md` NOW before continuing. --- ## TypeScript-Specific Configuration ### Verification Commands (Phase 1 plan + Phase 3 verify) WORKFLOW STATE Verification line: `tsc --noEmit, <lint-commands>, vitest/jest` (lint failure BLOCKS Phase 3 verify — see Lint Enforcement below). **Phase 3 Tier A commands:** - `tsc --noEmit` — type checking - Lint — see [Lint Enforcement](#lint-enforcement-phase-3) below; failure blocks Phase 3 - `vitest` or `jest` — tests - Coverage target: 70-80% **Phase 3 Tier B additional MCP verifications:** - PostgreSQL MCP → Query DB state before/after ### Lint Enforcement (Phase 3) **Lint failures BLOCK Phase 3 verification** with the same severity as a failing test. Read [references/lint-enforcement.md](references/lint-enforcement.md) at the start of Phase 3 verification and follow it. Detection is a union, not a priority ladder: 1. If `package.json` defines `scripts.lint` → run `<PM> run lint` (PM detected per [references/package-manager.md](references/package-manager.md)). Done. 2. Else, run **every** detected standalone linter (biome / eslint / oxlint) — all must pass. 3. Else, record "Lint: skipped (no linter configured)" and do not block. No `--fix` auto-remediation — agents fix lint errors intentionally. ### Implementation Rules (Phase 3) - **Schema structure** — Zod CRUD variants per entity (CreateInput/UpdateInput/Output), domain-driven `schemas.ts`, types derived via `z.infer`, composition over deep extends chains - **Minimize complexity** — Map/Set lookups over array scans - **Preserve compatibility** — `.transform()` for renamed fields, `.default()` for new fields, preserve exported signatures, re-export moved symbols ### Staff Review Configuration (Phase 4) - **Patterns file path:** Path to this skill's `patterns.md` --- ## TypeScript-Specific Rules - Types are erased at runtime — external data needs Zod validation - Fix type errors during implementation, not after - No positive claim without running `tsc --noEmit` - Before emitting any `install` / `run <script>` / `exec <bin>` command, detect the project's package manager — read [references/package-manager.md](references/package-manager.md). Never default to `npm`. - Lint failures BLOCK Phase 3 verify — same severity as test failures. Skip is allowed only when no linter is configured (no `scripts.lint`, no biome/eslint/oxlint config). See [references/lint-enforcement.md](references/lint-enforcement.md). --- ## Quality Checklist (TypeScript-Specific) Add these to the shared workflow's verification checklist: - [ ] Using TypeScript 5.x+ features where appropriate - [ ] `strict: true` enabled in tsconfig.json - [ ] No `any` types (or explicitly justified) - [ ] Proper type guards for runtime checks - [ ] Zod or similar for external data validation - [ ] ESM imports with proper extensions - [ ] `tsc --noEmit` passes (no type errors) - [ ] Lint passed (or explicitly skipped because no linter is configured) - [ ] Tests pass (`vitest`/`jest`)
Related Skills
using-development-skills
Use when starting any conversation - establishes how the development-skills plugin works and how to invoke its components on each platform (Claude Code, Codex). Read first.
update-reqs
Use when user wants to update requirements.in with latest PyPI versions while preserving version patterns
update-reqs-dev
Use when user wants to update requirements-dev.in with latest PyPI versions while preserving version patterns
update-precommit
Use when user wants to update .pre-commit-config.yaml hooks to their latest versions from GitHub
swift-dev
Swift development. Use for Swift, SwiftUI, UIKit, Vapor, SPM, XCTest, Combine.
staff-review
Use when user wants a code review, deep code review, or staff-level code review of a local branch, repo, directory, or file. Use when user says code review, deep code review, review this branch, review the branch X, review my code, staff review, review locally, or /staff-review.
roast-my-code
Use when user wants a brutally honest code roast, quality critique, or AI-readiness audit. Use when user says roast, roast my code, critique my code, tear apart my code, review quality, or AI-readiness check. Supports --fix flag to auto-fix CRITICAL and HIGH issues via core-dev workflow.
resolve-merge
Use when the user asks to resolve merge conflicts, fix a failed merge, rebase conflict, or run /resolve-merge. Use when git status shows UU/AA/DD conflicts, when there are <<<<<<< conflict markers, when git merge or git pull failed with CONFLICT, or when numbered docs/plans need renumbering after merge. Triggers on: merge conflict, conflict markers, both modified, git merge failed, rebase conflict, resolve conflicts.
python-dev
Python development. Use for Python, FastAPI, Pydantic, asyncpg, pytest, pandas, SQLAlchemy.
produce-feedback
Use when user wants to produce a factual chronicle of development-skills plugin interactions in the current conversation for later ingestion, or runs /produce-feedback. Pure record, no judgment.
java-dev
Java development. Use for Java, Spring Boot, Maven, Gradle, JPA, Hibernate.
ingest-feedback
Use when user wants to ingest a development-skills feedback report and apply fixes, or runs /ingest-feedback. Challenges every suggestion against the Iron Rules before accepting; most friction points should SKIP. Expect a report path as argument.