visual-storytelling-skills

leynos/visual-storytelling-skills

visual-storytelling-skills 是 GitHub 上 leynos 的 agent skill 项目：从文字到画面：场景清单、镜头设计、视频模型提示词、视频生成。覆盖分镜、提示词、出片阶段，提示词适配可灵 Kling、Seedance / 即梦、Nano Banana。目前 9 星，最近更新于 2026-10-10，许可证 ISC。

编者说明

这组 Claude Code 技能从 scene-inventory-extractor-v2 依次串到 media-project，最后把选中的片段打包成 OpenShot 的 .osp 工程。生图固定走 nanobanana MCP 的 gemini-3-pro-image-preview，不可用时直接停止；视频经 Higgsfield MCP 提交，在 Seedance 2.0、可灵 3.0 等模型间路由。shot-specifier 会为每个镜头生成故事板图，自述成本较高。文档为英文，README 的克隆地址指向 df12-productions 账号。

类型: 分镜 · 视觉资产 · 视频提示词
创作阶段: 分镜 · 提示词 · 出片
视频模型: 可灵 Kling · Seedance / 即梦 · Nano Banana
形式: 标准 skill
正文语言: 英文
GitHub 星数: ★ 9
最近更新: 2026-10-10
许可证: ISC
SKILL.md 数量: 8
人工核对: 2026-10-13

在 GitHub 查看信息有误？提交更正

仓库自述

Agent skills for AI film production — from prose to picture.

仓库里的 skill（8 个）

名字和说明取自各 SKILL.md 的 frontmatter。

kling-3-0-deep-dive
Deep operating guidance for Kling 3.0 video generation. Use when selecting Kling 3.0 for a shot, designing multi-shot scene structure, writing Kling-native cinematic prompts, planning Elements or Motion Control references, using start/end frame anchors, handling native audio or dialogue, building p…
media-project
Package completed visual storytelling video outputs into OpenShot editor projects with the system-installed media-project command. Use when an agent needs to run or verify a playable .osp handoff, preserve production sidecar metadata, or decide whether a project is ready for OpenShot packaging.
nanobanana
Craft high-precision prompts and edit instructions for Nano Banana image workflows, especially when using the local nanobanana MCP tools for generation, editing, character consistency, or multi-image fusion. Use when the task needs structured prompts, reference-role assignment, layout-heavy image s…
phoneticize
Build pronunciation tables, generate text-to-speech (TTS) preview samples, and produce phoneticized scripts ready for narration. Use whenever a script is intended for text-to-speech rendering and the user wants to catch words the engine will mispronounce — proper nouns, Gaelic and Welsh names, bran…
scene-inventory-extractor
End-to-end production-prep workflow: extracts comprehensive scene inventories from narrative writing, extracts continuity inventory and reset-critical state before prompt writing, generates all reference images (characters, locations under multiple angles/conditions, props), produces start/end/keyf…
seedance-2-deep-dive
Deep operating guidance for Seedance 2.0 video generation. Use when selecting Seedance 2.0 for a shot, designing multimodal references, writing Seedance-native prompts, choosing duration/aspect/quality settings, planning batch generations, troubleshooting drift or artifacts, or comparing Seedance 2…
shot-specifier
Per-shot production specification workflow: takes a completed scene inventory (from scene-inventory-extractor-v2) and decomposes every scene into numbered shots with full directorial direction — actor position and movement, camera mount and motion, lens, lighting setup, practical effects, timing, a…
video-generator
Execute production video generation from shot-specifier outputs through the Higgsfield Model Context Protocol (MCP). Use when prompts, storyboard frames, media roles, model routing, Higgsfield MCP uploads, generate_video calls, status polling, retakes, resume behaviour, or final assembly order are…

安装

npx skills add leynos/visual-storytelling-skills

# 只装其中一个 skill
npx skills add leynos/visual-storytelling-skills --skill kling-3-0-deep-dive

# 指定 agent（claude-code / codex / cursor / opencode / gemini-cli / openclaw）
npx skills add leynos/visual-storytelling-skills -a claude-code -a codex

默认命令基于 skills CLI，未逐个验证，以仓库 README 为准。安装前先读一遍 SKILL.md。安装指南 →

visual-storytelling-skills

编者说明

仓库自述

仓库里的 skill（8 个）

安装

同类项目