Skip to main content
Run any Skill in Manus
with one click
storyverse2025
GitHub creator profile

storyverse2025

Repository-level view of 16 collected skills across 3 GitHub repositories.

skills collected
16
repositories
3
updated
2026-06-30
repository explorer

Repositories and representative skills

cinematographer-agent
software-developers

Shoots beat-video clips via Seedance 2.0 from a director storyboard row + keyframe. Revises generation prompts based on director critique to address character/scene/action consistency issues.

2026-05-31
director-agent
producers-and-directors

Owns all storyboard logic — shot allocation, composition, table generation, timeline critique, fixes, and keyframe construction. Knowledge base derived from director-shot-language-skill.

2026-05-31
script-agent
writers-and-authors

Top-level script-domain agent. Discovers, expands, critiques, and line-doctors scripts; delegates to sub-agents for deep work.

2026-05-30
project-manager-agent
software-developers

The chat-panel front door. Receives free-form user requests, inspects current project state (canvas + storyboard), and decides which downstream agent (script / art-director / actor / director / cinematographer / sound) to dispatch — or replies in plain text when no agent fits. Keeps the user out of the "which button do I press" maze.

2026-05-27
art-director-agent
software-developers

Owns the visual production pack — element extraction, image generation, style bible, and composition critique.

2026-05-26
actor-agent
software-developers

Plays each character (rewrites the storyboard performance fields), writes biography + 7-pillar appearance for art-director image generation, picks voices from the voice library, and augments cinematographer video prompts.

2026-05-20
sound-agent
software-developers

Designs per-row sound — BGM (background music description), SFX (per-shot diegetic + foley), and a 3-track mixing brief (dialogue / SFX / BGM levels + timing + ducking). Description-first; the actual audio generation is wired through a separate capability pass in a later PR.

2026-05-17
dialogue-doctor-diagnosis
editors

Use for full-line dialogue diagnosis and rewrite rationale after a script exists.

2026-05-16
Showing top 8 of 13 collected skills in this repository.
keyframe-prompt
special-effects-artists-and-animators

AI 短剧(竖屏 9:16 微短剧)Keyframe / 空间基准帧提示词生成方法论。Keyframe 是一张静止图,把 Spatial Bible 的文字空间信息图像化,锁住"角色站位 + 家具光源位置 + 机位坐标系"三件事,作为整场戏的 scene-ref 反复挂载到每个 Beat,解决 AI 每次独立生成、空间随机漂移的问题。只要任务涉及下列任意一项就用这个 skill,哪怕用户没说"Keyframe"三个字:为某个场景写空间基准帧 / scene-ref / staging image 的提示词;把一段剧本或 Spatial Bible 转成静帧提示词;确认场景初始站位与机位;质检已写好的 Keyframe 提示词;诊断"生成出来角色位置/朝向不对";或在 Beat 提示词里写引用 scene-ref 的精简版 SPATIAL ANCHOR。配合 Kling、Seedance 等工具使用。它聚焦"建图像锚"这一交付物,是 ai-short-drama-storyboard 全流水线里 Spatial Bible 之后、写 Beat 之前的那一步。

2026-06-30
shots-prompt-writing
special-effects-artists-and-animators

AI 短剧(竖屏 9:16 微短剧)单条 Shots Prompt 的写作与质检方法论——聚焦"抽卡师把一个 Beat 写成 AI 能稳定生成的 15 秒视频提示词"这一交付物。覆盖提示词八区块标准结构、角色外貌锚定(外貌代替人名)、四要素机位推导、正反打视线轴线、走位三要素、情绪物理化描述、音频处理(V.O. 三步法 / O.S. 重叠 / reference audio 多角色绑定 / 美音防英音漂移)、节拍拆分与卡点、NEGATIVE 双重锁定、道具 vs 台词区分。只要任务涉及下列任意一项就用这个 skill,哪怕用户没说"提示词"三个字:写一条 shots prompt / Canvas Shot / shots1 / shots2;把某个 Beat 写成可生成的提示词;推导机位("想拍 B 的正面机位放哪");判定正反打后视线该朝 screen-left 还是 right;把"steps back / 转身离开"写成不会被 AI 误解的走位;把"她很崩溃"翻译成可渲染的物理表现;处理内心独白 / 画外音 / 口型同步 / 音色一致 / 口音漂移;写 NEGATIVE 锁定;质检一条已写好的 shots prompt;或诊断"生成出来角色背对/视线错/嘴在动/楼梯背景错/表情夸张"等问题。配合 Seedance、Kling、Runway、Veo 等工具使用。

2026-06-30
Showing 3 of 3 repositories
All repositories loaded