claw-drive-start

Spawn a driven Claude Code session (Session B) in the given directory and start the Monitor flow against the returned watch_command. Usage — /claw-drive-start <cwd> [--brief <file>] [--policy <file>] [--verbose]. The cwd must exist and be a real project root. If --brief is omitted, the user will be asked for the scenario brief inline. If --policy is omitted, the conservative starter shipped with claw-drive is used. By default Session B receives a system-prompt wrapper teaching a two-token vocabulary — emit [NEEDS-INPUT] when the human is needed, [DONE] when the task is complete, nothing otherwise — and Monitor surfaces turn_completed only when one of those two trailing tokens is present. Pass --verbose to bypass both the wrapper injection and the sentinel filter (raw stream including every turn_completed and tool_output_provided).

Safety Notice

This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.

Copy this and send it to your AI assistant to learn

Install skill "claw-drive-start" with this command: npx skills add renatodarrigo/skillsmp-renatodarrigo-renatodarrigo-claw-drive-start

No markdown body

This source entry does not include full markdown content beyond metadata.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

claw-drive-status

Fetch a snapshot of one or all driven claw-drive sessions and characterize what's happening. Usage — /claw-drive-status [<session-id>]. Calls `claw-drive status [--json]` under the hood, parses the result, and surfaces what's noteworthy (sessions waiting on input, pending tool decisions, recent failures) — does NOT dump raw JSON to the user. Use this when the user asks "what's going on?" or you need a cold-start snapshot of in-flight driven sessions.

Repository SourceNeeds Review
Coding

visual-summary-analysis

Performs AI analysis on input video clips/image content and generates a smooth, natural scene description. | 视觉摘要智述技能,对传入的视频片段/图片内容进行AI分析,生成一段通顺自然的场景描述内容

Archived SourceRecently Updated
Coding

frontend-skill

全能高级前端研发工程师技能。擅长AI时代前沿技术栈(React最新 + shadcn/ui + Tailwind CSS v4 + TypeScript + Next.js),精通动效库与交互特效开发。采用Glue Code风格快速实现代码,强调高质量产品体验与高度友好的UI视觉规范。在组件调用、交互特效、全局Theme上保持高度规范:绝不重复造轮子,相同逻辑出现两次即封装为组件。具备安全意识,防范各类注入攻击。开发页面具有高度自适应能力,响应式设计贯穿始终。当用户无特殊技术栈要求时,默认采用主流前沿技术栈。

Archived SourceRecently Updated
Coding

mtl-api-create

摩天轮开放接口二次封装技能。当用户需要对接摩天轮(MTL)开放平台接口、创建MTL HTTP接口、封装摩天轮API时触发。支持自动检测并添加mtl-open-sdk-consumer依赖、初始化ApiClient Bean、创建MtlRestController、根据原生接口定义生成HTTP接口代码。

Archived SourceRecently Updated
claw-drive-start | V50.AI