AGENT SKILL

director-brief

选定 Mode / style,初始化作品工作包,产出 video_brief

使用场景图像与多媒体
License 许可
MIT
最近更新
2026-11-10
Stars
★ 3
Forks
1

01 前言 Front Matter

name
director-brief
x-runner
{ "budget": { "max_rounds": 8, "max_tokens": 40000, "max_seconds": 300 }, "outputs": { "root": "works", "globs": [ "*/video_brief.json" ], "write_mode": "repo", "allowed_exts": [ "md", "json", "txt" ] }, "version": 1, "builtin_tools": [ "init_work_package", "write_file", "read_file", "confirm_video_gate", "probe_backend" ] }
x-workflow
{ "version": 1, "consumes": [ { "kind": "ticket_brief", "mode": "text" } ], "priority": 20, "produces": [ { "glob": "*/video_brief.json", "kind": "video_brief" } ], "stage_id": "director_brief", "human_gate": true, "stage_name": "视频简报", "required_traits": { "all_of": [ "category:video", "pipeline:video" ] }, "required_ticket_type": { "none_of": [ "bug-fix", "rollback", "polish" ] }, "pipeline_view_contrib": { "group": "video_pipeline", "create_if_missing": { "icon": "?", "name": "视频制片", "insert_after": "requirement_analysis" } } }
description
选定 Mode / style,初始化作品工作包,产出 video_brief

03 SKILL.md 正文

视频简报

  1. 读 ticket_brief,判断 Mode:animated-explainer / storytime-animation / cinematic-drama。无法判断就停,向用户提问。未支持类型明确拒绝。
  2. 用 read_file(CLI:mcp__skill_io__read_repo_file)读 director-knowledge/modes/<mode>/workflow.md 确认适用边界。
  3. init_work_package(CLI:mcp__skill_io__init_work_package,title 用工单标题),记下返回的 slug。
  4. 把简报写入 works/<slug>/video_brief.json(CLI:mcp__skill_io__write_repo_file),字段至少包括:mode、style(可先空)、ratio、duration_per_clip、language、backend(默认 lightai)、resolution(默认 720p)、slug。用户指定 LibTV / 即梦才改 backend,不要因为 LightAI 缺 Key 就改。
  5. 调用 confirm_video_gate(CLI:mcp__skill_io__confirm_video_gate,title=确认 Mode 与简报,work_slug=slug,gate=brief,preview_paths 含该 json),然后 mcp__skill_io__done。

禁止搜索或打开 D:\A_Works\director、~/.codebuddy/projects、用户主目录里的 director 源仓。不要用原生 Write / Glob / Bash 满盘搜 skill。知识只走 director-knowledge/ 前缀。

04 同仓库更多 Skills

welflau
welflau/ai-dev-system

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 3
welflau
welflau/ai-dev-system

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

设计师前端开发视觉设计
★ 3
welflau
welflau/ai-dev-system

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

视觉设计
★ 3
welflau
welflau/ai-dev-system

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 3
welflau
welflau/ai-dev-system

browsing

Use when you need direct browser control - teaches Chrome DevTools Protocol for controlling existing browser sessions, multi-tab management, form automation, and content extraction via use_browser MCP tool

Skill与智能体开发
★ 3
welflau
welflau/ai-dev-system

slack-gif-creator

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

邮件与沟通图像与多媒体
★ 3