Provides quick access to project build, test, and lint commands, plus structural and convention standards.

Install

mkdir -p .claude/skills/dev-serithemage && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9516" && unzip -o skill.zip -d .claude/skills/dev-serithemage && rm skill.zip

Installs to .claude/skills/dev-serithemage

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Development workflow guide. Covers build, test, lint, format commands, package structure, Git hooks, TDD methodology, and coding conventions. Use when setting up dev environment, running tests, or following project conventions.
227 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Execute project build and lint commands
  • Run unit and E2E tests
  • Sync shared skills
  • Verify project structure conventions

How it works

The tool provides a centralized reference for project-specific commands, package structures, and coding conventions to maintain development standards.

Inputs & outputs

You give it
development workflow command
You get back
execution of build, test, or lint tasks

When to use dev

  • Run project tests
  • Check build and lint status
  • View directory structure conventions

About this skill

Development Workflow

Full guide: docs/development.md

Quick Command Reference

npm run build          # tsc --build (all packages via project references)
npm run lint           # eslint "packages/**/*.ts"
npm run format         # prettier
npm run test           # vitest run (unit tests, excludes *.e2e.test.ts)
npm run test:e2e       # vitest e2e (CDK synth E2E tests)
npm run skills:sync    # sync shared skills into Claude/Codex mirrors
npm run skills:check   # verify shared skill mirrors are in sync

# Single test file
npx vitest run packages/gateway/__tests__/handlers/ws-connect.test.ts

# Single test by name
npx vitest run -t "should verify JWT"

Package Structure (6 packages)

packages/
├── shared/      # Types + constants (TABLE_NAMES, BRIDGE_PORT, key prefixes)
├── cdk/         # CDK stacks (lib/stacks/)
├── gateway/     # 7 Lambda handlers (ws-connect/message/disconnect, telegram-webhook, api-handler, watchdog, prewarm)
├── container/   # Fargate container (Bridge server + OpenClaw JSON-RPC client)
├── lambda-agent/ # Lambda agent (Phase 2 — OpenClaw embedded in Lambda)
└── web/         # React SPA (Vite, amazon-cognito-identity-js for auth)

Git Hooks (husky)

HookChecks
pre-commitnpm run build + npm run lint + unit tests
pre-pushE2E tests (CDK synth verification)

TDD Rules

  • Tests first for all packages except web
  • Write test → watch it fail → implement → watch it pass
  • Unit tests: packages/<pkg>/__tests__/
  • E2E tests: packages/<pkg>/__tests__/*.e2e.test.ts

Import Path Rule

TypeScript uses NodeNext module resolution. All imports must use .js extension:

// Correct
import { TABLE_NAMES } from "@serverless-openclaw/shared/constants.js";
import { routeMessage } from "../services/message.js";

// Wrong — omitting .js will fail at runtime
import { TABLE_NAMES } from "@serverless-openclaw/shared/constants";

Coding Conventions

  • DI pattern: Inject send function (same pattern as container package)
  • AWS SDK send binding: ddb.send.bind(ddb) as (cmd: any) => Promise<any> cast needed
  • vi.mock hoisting: Use vi.hoisted() when referencing variables in module-level mocks
  • npm workspaces: Use "*" for local dependencies ("workspace:*" is pnpm-only)
  • TypeScript: ES2022, Node16 module resolution, strict, composite builds

When not to use it

  • When working outside of the defined project package structure

Prerequisites

npm

Limitations

  • Requires strict adherence to .js extension in imports
  • E2E tests are excluded from standard test runs

How it compares

It enforces project-wide standards like import path rules and TDD methodology through a unified command interface rather than relying on individual developer memory.

Compared to similar skills

dev side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
dev (this skill)04moReviewIntermediate
playwright-browser-automation297moReviewIntermediate
swarm-advanced74moReviewAdvanced
documenso-local-dev-loop226dReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

playwright-browser-automation

lackeyjb

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

29146

swarm-advanced

ruvnet

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

7110

documenso-local-dev-loop

jeremylongshore

Set up local development environment and testing workflow for Documenso. Use when configuring dev environment, setting up test workflows, or establishing rapid iteration patterns with Documenso. Trigger with phrases like "documenso local dev", "documenso development", "test documenso locally", "documenso dev environment".

26

orchardcore-tester

OrchardCMS

Tests OrchardCore CMS features through browser automation. Use when the user needs to build, run, setup, or test OrchardCore functionality including admin features, content management, media library, and module testing.

14

app-commands

growilabs

GROWI main application (apps/app) specific commands and scripts. Auto-invoked when working in apps/app.

13

replit-load-scale

jeremylongshore

Implement Replit load testing, auto-scaling, and capacity planning strategies. Use when running performance tests, configuring horizontal scaling, or planning capacity for Replit integrations. Trigger with phrases like "replit load test", "replit scale", "replit performance test", "replit capacity", "replit k6", "replit benchmark".

13

Search skills

Search the agent skills registry