Chalk Labs
Need help deploying storyboard-breaker?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ddlmanus-storyboard-breaker
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/storyboard-breaker
What's inside
- Skill name
storyboard-breaker- Description
- 分镜拆解专业规范
- License
- MIT
- Instructions
- 73 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "storyboard-breaker" does not match folder "storyboard_breaker"
Files (1)
- SKILL.md
SKILL.md (first lines)
# 分镜拆解指南 ## 拆解原则 每个镜头聚焦**单一动作**,描述要详尽具体。每个镜头时长 10-15 秒。 ## 镜头要素 1. **镜头标题**:3-5字概括核心内容(如"噩梦惊醒") 2. **时间**:具体时分 + 光线描述 3. **地点**:场景完整描述 + 空间布局 + 环境细节 4. **景别**:远景/全景/中景/近景/特写 5. **角度**:平视/仰视/俯视/侧面/背面 6. **运镜**:固定/推镜/拉镜/摇镜/跟镜/移镜 7. **动作**:谁 + 具体怎么做 + 肢体细节 + 表情 8. **对话**:该镜头的完整对话 9. **画面结果**:动作的即时后果 + 视觉细节 10. **氛围**:光线 + 色调 + 声音 + 整体氛围 11. **时长**:每个镜头 10-15 秒 12. **静态画面提示词**:`image_prompt`,用于首帧/尾帧/镜头图片生成 13. **视频提示词**:`video_prompt`,按 3 秒分段的视频生成描述(必填) 14. **配乐提示词**:`bgm_prompt`,描述该镜头适合的配乐风格 15. **音效提示词**:`sound_effect`,描述该镜头关键环境音/动作音 16. **场景关联**:若能匹配已有场景,必须填写 `scene_id` 17. **角色关联**:填写 `character_ids`,绑定当前镜头涉及的 0 到多个角色 ## 视频提示词格式 每个镜头必须包含 `video_prompt` 字段,用于驱动 AI 视频生成: ``` 0-3秒:<location>咖啡厅</location>,近景,<role>小明</role>低头看手机,表情焦虑。 <n>3-6秒:<location>咖啡厅</location>,全景,门铃响,<role>小红</role>推门走入。 <n>6-9秒:<location>咖啡厅</location>,中景,<role>小红</role>微笑走向小明,坐下。 ``` 标签说明: - `<location>地点</location>` — 场景标记 - `<role>角色名</role>` — 角色标记 - `<voice>角色名</voice>` — 画外音/旁白标记 - `<n>` — 时间段分隔符 ## 使用步骤 1. 调用 `read_storyboard_context` 读取剧本、角色、场景、已有分镜摘要 2. 先基于剧本完成镜头拆解,确保总时长和叙事连续性合理 3. 为每个镜头补全完整字段:`title / shot_type / angle / movement / location / time / character_ids / action / dialogue / description / result / atmosphere / image_prompt / video_prompt / bgm_prompt / sound_effect / duration / scene_id` 4. 调用 `save_storyboards` 一次性保存完整分镜 5. 如需调整,调用 `update_storyboard` 修改具体镜头 ## 场景关联规则 - 优先使用 `read_storyboard_context` 返回的 `scenes` - `location + time` 可明确匹配时,必须回填正确 `scene_id` - 不要凭空生成不存在的场景 ID - 如果剧本内容明显落在已有场景中,不要重复创造新场景描述 ## 角色绑定规则 - `character_ids` 必须从 `read_storyboard_context` 返回的角色列表中选择 - 一个镜头可以没有角色,也可以绑定多个角色 - 只要镜头里有明确出场、被看见、发生动作或说话的角色,都应绑定进去 - 纯环境镜头、空镜头、物件镜头可以传空数组 ## 质量要求 - `description` 要适合人读,`video_prompt` 要适合模型生成,二者不要互相替代 - `image_prompt` 要突出单帧构图、角色外观、环境和光线 - `video_prompt` 要突出时间推进、动作变化、镜头语言 - `bgm_prompt` 和 `sound_effect` 用简洁短语即可,但不能空泛到只有“紧张”“悲伤” - 若存在旁白,统一写入 `dialogue`,格式为 `旁白:内容`
From ddlmanus/lovarts-drama, MIT.
More from ddlmanus/lovarts-drama
- 0.545score
grid-image-generator
ddlmanus
图片提示词生成指南 — 角色、场景、宫格图三类提示词规范
SkillCFreshness: C★ 31Claude Code +9 - 0.545score
script-rewriter
ddlmanus
小说改写为格式化剧本的方法论和规范
SkillCFreshness: C★ 31Claude Code +9 - 0.512score
character-scene-extractor
ddlmanus
角色和场景提取的规范与方法
SkillCFreshness: C★ 31Claude Code +9 - 0.512score
voice-assigner
ddlmanus
角色音色分配原则与音色库
SkillCFreshness: C★ 31Claude Code +9
Signals
- Stars
- 31
- Forks
- 12
- Open issues
- 0
- Last commit (this folder)
- May 19, 2026 (5 months ago)
- Last release
- May 22, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ddlmanus/lovarts-drama
- Website
- drama.lovarts.art
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from ddlmanus
- 0.545score
grid-image-generator
ddlmanus
图片提示词生成指南 — 角色、场景、宫格图三类提示词规范
SkillCFreshness: C★ 31Claude Code +9 - 0.545score
script-rewriter
ddlmanus
小说改写为格式化剧本的方法论和规范
SkillCFreshness: C★ 31Claude Code +9 - 0.512score
character-scene-extractor
ddlmanus
角色和场景提取的规范与方法
SkillCFreshness: C★ 31Claude Code +9 - 0.512score
voice-assigner
ddlmanus
角色音色分配原则与音色库
SkillCFreshness: C★ 31Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get storyboard-breaker running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
storyboard-breaker skill. Agent Mart. https://agentmart.dev/skills/ddlmanus-storyboard-breaker (last updated 2026-10-24)