d3k
Bootstrap d3k in standalone AI apps (Codex, Cursor, Claude Code): detect/install dev3000, start d3k as the runtime, and use unified logs plus CDP browser control instead of running npm/bun dev directly.
Best use case
d3k is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Bootstrap d3k in standalone AI apps (Codex, Cursor, Claude Code): detect/install dev3000, start d3k as the runtime, and use unified logs plus CDP browser control instead of running npm/bun dev directly.
Teams using d3k 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/d3k/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How d3k Compares
| Feature / Agent | d3k | 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?
Bootstrap d3k in standalone AI apps (Codex, Cursor, Claude Code): detect/install dev3000, start d3k as the runtime, and use unified logs plus CDP browser control instead of running npm/bun dev directly.
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
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
# d3k Standalone Bootstrap
Use this skill when working in a standalone AI app and you need reliable local web debugging with browser + server context.
## Why d3k-first
- `d3k` captures server logs, browser console, network events, and screenshots in one timeline.
- `d3k` exposes a stable CDP endpoint so the agent can control the same browser session being monitored.
- Running `npm run dev` or `bun run dev` directly omits this unified telemetry and usually leads to weaker diagnoses.
## Bootstrap Workflow
1. Confirm whether `d3k` is installed:
```bash
command -v d3k >/dev/null && d3k --version
```
2. If `d3k` is missing, install dev3000 globally (prefer Bun):
```bash
bun install -g dev3000
```
Fallback if Bun is unavailable:
```bash
npm install -g dev3000
```
3. Start d3k as the runtime (preferred default in agent shells):
```bash
d3k --no-agent --no-tui -t
```
4. Keep d3k running while editing code. Do not start a second dev server with `npm/bun dev`.
## Debugging Commands
Use these first before ad-hoc log scraping:
```bash
d3k errors --context
d3k logs -n 200
d3k logs --type browser
d3k logs --type server
```
## CDP Browser Control
Use the already-monitored browser session instead of launching a separate automation browser.
```bash
CDP_PORT="$(d3k cdp-port)"
d3k agent-browser --cdp "$CDP_PORT" open http://localhost:3000
d3k agent-browser --cdp "$CDP_PORT" snapshot -i
d3k agent-browser --cdp "$CDP_PORT" click @e2
d3k agent-browser --cdp "$CDP_PORT" screenshot /tmp/d3k-current.png
```
## Browser Tool Choice
Use the browser tool that matches the task instead of treating them as interchangeable:
- `agent-browser`
- Default choice.
- Best for generic web apps and for driving the exact headed browser session that d3k is already monitoring via CDP.
- Use it when you need `snapshot`, ref-based `click`, `fill`, or to reproduce what the user sees in the monitored tab.
- `next-browser`
- Next.js-specific tool.
- Best for React/Next introspection: `tree`, `errors`, `logs`, `routes`, `project`, PPR inspection, and related Next dev-server signals.
- It is not a drop-in replacement for `agent-browser`: no accessibility `snapshot`, no ref-based `click`, and no `fill`.
- It launches its own daemon/browser flow and does not use `d3k cdp-port`.
Practical rule:
- Need to drive the same browser d3k is monitoring: use `agent-browser`.
- Need Next.js component tree or Next-specific diagnostics: use `next-browser`.
Examples:
```bash
# Same monitored browser session
CDP_PORT="$(d3k cdp-port)"
d3k agent-browser --cdp "$CDP_PORT" snapshot -i
d3k agent-browser --cdp "$CDP_PORT" click @e2
# Next.js-specific inspection
d3k next-browser open http://localhost:3000
d3k next-browser tree
d3k next-browser errors
d3k next-browser logs
```
## Artifacts to Read
- `~/.d3k/{project}/d3k.log`
- `~/.d3k/{project}/logs/`
- `~/.d3k/{project}/screenshots/`
- `~/.d3k/{project}/session.json`
## Operating Rules
- Prefer headed mode for interactive debugging.
- Use `--headless` only for CI or when explicitly requested.
- Use `--servers-only` only when browser monitoring is intentionally disabled.Related Skills
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
safety-guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
repo-scan
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
project-flow-ops
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.
product-lens
Use this skill to validate the "why" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract.
openclaw-persona-forge
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
laravel-plugin-discovery
Discover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or assess Laravel/PHP compatibility.