Roadshow Video Generator
anbeime/skill
Turns a document into a narrated roadshow video through ten staged roles, from document analysis and slide planning to audio, subtitles and final composition.
对已完成分析的视频进行导演与剪辑策划,再写带时间戳的中文解说并校验;也处理已有短片的 宣发标题、花字修订和外部文案回填。普通策划输入 workdir 的 agentnarrationbrief.md 与 vlmanalysis.json;文案返修输入当前成片的工程与内容证据。策划输出 recapstoryplan.json、visualaudioboard.json、 可选…
$ npx skills add zenstory-ai/video-recap-skills --skill video-script -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-script --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/video-script .claude/skills/video-script && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "video-script" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-script into .claude/skills/video-script/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-script", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-scriptType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zenstory-ai/video-recap-skills --skill video-script -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-script --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/video-script .agents/skills/video-script && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "video-script" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-script into .agents/skills/video-script/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-script", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/video-recap-skills --skill video-script -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-script --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/video-script .cursor/skills/video-script && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "video-script" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-script into .cursor/skills/video-script/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-script", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zenstory-ai/video-recap-skills.git --path skills/video-script--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zenstory-ai/video-recap-skills --skill video-script -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-script --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/video-script .gemini/skills/video-script && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "video-script" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-script into .gemini/skills/video-script/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-script", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zenstory-ai/video-recap-skills video-scriptInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zenstory-ai/video-recap-skills --skill video-script -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/video-script .github/skills/video-script && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "video-script" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-script into .github/skills/video-script/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-script", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zenstory-ai/video-recap-skills --skill video-script -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zenstory-ai/video-recap-skills video-script --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/video-script .opencode/skills/video-script && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "video-script" agent skill from https://github.com/zenstory-ai/video-recap-skills/tree/main/skills/video-script into .opencode/skills/video-script/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-script", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
video-script对已完成分析的视频进行导演与剪辑策划,再写带时间戳的中文解说并校验;也处理已有短片的 宣发标题、花字修订和外部文案回填。普通策划输入 workdir 的 agentnarrationbrief.md 与 vlmanalysis.json;文案返修输入当前成片的工程与内容证据。策划输出 recapstoryplan.json、visualaudioboard.json、 可选…
Video Script is an agent skill from zenstory-ai/video-recap-skills. 对已完成分析的视频进行导演与剪辑策划,再写带时间戳的中文解说并校验;也处理已有短片的 宣发标题、花字修订和外部文案回填。普通策划输入 workdir 的 agentnarrationbrief.md 与 vlmanalysis.json;文案返修输入当前成片的工程与内容证据。策划输出 recapstoryplan.json、visualaudioboard.json、 可选 stylecard.json、cut 模式需要的 clipplan.json,以及通过校验的 narration.json;仅宣发文案任务交付提案或回填既有包装计划。 外发说明:只有建议型评审 review.py 联网,它把旁白稿全文与理解证据、策划文件的文字摘录发到 MiMo chat 接口 (MIMOAPIKEY / MIMOAPIURL,不发视频、图片或音频);单独使用时只在显式执行时运行,端到端编排默认在 TTS 前运行一次, 可用 --no-review-narration / REVIEWNARRATION=0 关闭(严格评审开启时除外);validate.py 与 lint 仅在本地运行。…
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts and reference files (for example `references/creative-editing-playbook.md`, `references/promotional-copy.md` and `references/research-guide.md`).
It sits in Media & Creative, covering Text to speech and voice and Video scripts and shorts. The repository describes itself as: Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly, optional editable JianYing / CapCut… The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 5391686. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 13 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.xiaomimimo.comtoken-plan-cn.xiaomimimo.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
MIMO_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Video Script loads about 2.4k tokens when it runs, and up to ~8k if it reads all its reference files. Until then it costs about 148 tokens; SKILL.md has 525 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from zenstory-ai/video-recap-skills at commit 5391686, republished under its MIT licence (© zenstory-ai). 525 words, ~2,376 tokens.
.claude/skills/video-script/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.只改宣发标题、封面、花字或回填外部文案时,直接读 references/promotional-copy.md,
按当前短片的观看理由和兑现位置处理指定文字层,不重做下述策划/旁白链。
普通解说写作不因此增加平台调研或包装任务。
本技能负责:创作方向、画面/声音计划、旁白写作与校验。Agent 不是 JSON 填写器,而要依次扮演:
Agent 先记录简洁决定,再写时间线产物。validate.py 负责对理解索引做机械校验,从不改写 Agent 的稿子:段落顺序、数量、时间、文本、停顿和扩展元数据原样保留,只依据现有声音证据回写实测的 overlaps_speech。文本装不下时间窗、段落未按时间排序等问题以 error 退回给 Agent 修改。
下面的 scripts/... 均相对于本技能目录。若执行器从仓库根目录启动,请给脚本路径加上本技能的绝对目录。
先根据用户要求和 work_dir 判断本轮模式;它不是 full|cut|dub 渲染模式:
REVISION 先明确本轮修改项与冻结项,再编辑对应层:表达、口语节奏、字幕反馈更新 style_card.json;镜头、入出点、表演和声音分工更新 visual_audio_board.json;只有观众承诺、POV、主线或 beat 改变时才更新 recap_story_plan.json。被删除的镜头、原声或文案也要从相关计划中删除,不能保留过期锚点。不要把看片修改重新做成一次 CREATE。
本技能只有一个脚本会联网:review.py(§7.1 的建议型语义评审)。其余全部在本地运行:validate.py 及其 lint、去 AI 味检查只读写 work_dir 里的文件,不发任何网络请求;策划与写稿由 Agent 直接读写 work_dir 完成。
review.py 发给谁:
<MIMO_API_URL>/chat/completions,用 MIMO_API_KEY 认证,模型为 MIMO_MODEL(默认 mimo-v2.5)。未设 MIMO_API_URL 时,按量计费 key 发往 https://api.xiaomimimo.com/v1,tp- 开头的 Token Plan key 发往 MIMO_TOKEN_PLAN_CLUSTER 选定的 token-plan 集群(默认 https://token-plan-cn.xiaomimimo.com/v1)。MIMO_API_KEY 时直接退出,不构造也不发送任何请求。review.py 发送什么(只有文字,不发视频、帧图片或音频文件):
narration.json 全部旁白段的时间与文字。vlm_analysis.json 的场景描述与 frame_facts 文字,以及对白转写(有 asr_clean.json 时用它,否则 asr_result.json)。background_research.json 的梗概、角色、关系与剧情线摘录。packaging_plan.json、recap_story_plan.json、visual_audio_board.json、style_card.json(各截前 3000 字)和 original_subtitles.json 的原声字幕文字。narration_review.json / narration_review.md。何时运行、怎样关闭:
review.py 只在用户或 Agent 显式执行它时运行;不执行它就没有任何外发。用户不希望稿件离开本机时,不要运行它,改为人工复核后直接跑 validate.py。--no-review-narration 或环境变量 REVIEW_NARRATION=0。若同时开启了严格评审(--require-narration-review 或 REQUIRE_NARRATION_REVIEW=1),评审必须运行,关闭开关不生效。narration.json;是否修改由 Agent 或用户决定。首先阅读:
work_dir/agent_narration_brief.md:场景、时长、安静窗口与字数预算。asr_writing_chunks.json:长对白的写作分块。timeline_fusion.json:判断某段是否有对白或静音槽。vlm_analysis.json / asr_result.json:核对具体画面与原声证据;有 asr_clean.json 时以它的文本为准(lint、评审、剪辑和合成都读它)。production_reference.json(仅当 work_dir 里有):另一部成片拆出的可迁移方法与节奏数值,用法见 §4。full 模式使用原片时间。cut 模式第一阶段只写 clip_plan.json;edited_source.mp4 产生后,第二阶段才按输出时间写 narration.json。
写任何创作产物前,直接读取 work_dir 判断当前阶段:
recap_run_manifest.json:确认 edit_mode、源视频和本轮设置。narration.json 时进入写稿;存在时先复核再校验。clip_plan_validated.json / edited_source.mp4,只写 clip_plan.json。clip_plan_validated.json.clips[] 中的 source_start/end 与 output_start/end 核对映射,再写输出时间的旁白。必须确认旁白没有跨越错误剪辑边界,也没有落进已删除区间。整个判断只依赖 work_dir 产物。
先阅读 references/creative-editing-playbook.md,再按创作控制模式写或更新工作产物:
recap_story_plan.json:导演意图、CREATE 中至少两个剪辑假设、选定的 POV / 主线,以及由“变化”定义的 beats。DIRECTED / REVISION 不强行新增假设。visual_audio_board.json:每拍的画面任务、具体表演/反应、入点/出点、audio_owner、原声锚点与 narration_job。style_card.json(适用时):用户当前认可的声音、口语节奏、字幕阅读姿态和明确禁忌。收到表达或字幕反馈后更新原文件,而不是只改最终文案。只记录决定、证据锚点、被放弃的备选方案和简短理由,不写冗长思维过程。
若 work_dir 有 production_reference.json,制定方案前先读它。它来自另一部成片,只含可迁移的方法和测得的节奏,不含本片事实,不能作为本片画面、剧情或台词的证据。优先级:用户指令 > 本片证据 > 参考。CREATE 可把它的 structure 当作一个候选假设,与素材自生的假设比较;DIRECTED / REVISION 默认不套用。targets 是参考值,不是配额:与本片的 audio_owner、完整台词或表演冲突时以素材为准。可在 recap_story_plan.json 写可选字段 reference_methods: [{"id": "m1", "decision": "adopt|adapt|skip", "note": "…"}]。没有这个文件就跳过本段。
锁定:
CREATE 比较两个真正可行的结构后选择一个;DIRECTED / REVISION 沿用用户指定或已确认的结构,除非最新反馈明确改变故事方向。每个 beat 至少改变一项:知识、权力、目标、关系、情绪或风险。若删除后因果、人物和情绪都没有损失,该 beat 通常不应保留。
选择具体时刻,而不是只选择事件。比较:
在不破坏理解的前提下晚进早出,同时保留不可替代的表演、停顿、失误、动作声和完整台词。
先指定 audio_owner,再写字。旁白只允许承担以下 narration_job:
contextcausal_linkforeshadowinterpretationtransitionnone画面、原声或沉默已经足够时使用 none,不要默认铺旁白。
cut 模式先根据 recap_story_plan.json 与 visual_audio_board.json 写原片时间的 clip_plan.json,此时不要写 narration.json:
{
"target_duration": "10m",
"clips": [
{
"start": 12.0,
"end": 38.0,
"reason": "b01 | hook | knowledge: unknown→threat | POV=主角 | 保留倾听反应 | 入点=问题已问出 | 出点=沉默落地"
}
]
}reason 统一使用:
beat_id | function | change | POV | preferred moment | 入点 | 出点片段顺序必须构成一条完整故事线,而不是无序高光。可使用 0–1 个 cold open,随后回到因果清楚的 setup → turn → escalation → payoff。片段长度服从具体时刻,不使用统一秒数模板;片尾必须保留完整台词或动作。密集 scene-change 候选的来源判断与处理规则由剪辑阶段定义,写计划时遵循同一规则,不制造人工闪切。
full 模式直接按原片时间写;cut 第二阶段先查看 edited_source.mp4 与剪后故事板,补充 visual_audio_board.json 的输出时间并重新确认 audio_owner / narration_job,再按输出时间写:
[
{
"start": 5.0,
"end": 12.0,
"narration": "解说文本。",
"pause_after_ms": 250,
"overlaps_speech": true,
"emotion": "紧张"
}
]字段说明:
| 字段 | 含义 |
|---|---|
start / end | full 模式为原片时间;cut 第二阶段为输出时间。与上一块间隔不超过 1.6 秒的块属于同一段落,assemble 会让它紧接上一块的实际结尾(间隔 0.35 秒)播放,最多比 start 提前 1.2 秒,且提前的那一段不会进入原声对白;段落首块从 start 开始,上一块超时则顺延到上一块结尾加停顿之后 |
narration | 解说文本 |
pause_after_ms | 段后停顿,默认 250ms |
overlaps_speech | 是否与原对白重叠;连续铺底窗口通常为 true,真正静音槽才为 false |
emotion | 整个解说块的 MiMo TTS 情绪/语气标签 |
narration_job,后有句子:没有明确任务就不写;旁白不是默认音轨。audio_owner;强对白、动作声或沉默可以完整拥有一个 beat。字数 / brief 头部 speech budget 估算朗读秒数,每块再加约 0.45 秒 TTS 首尾静音。brief 里每个窗口标的字数没扣这段静音,2–3 秒的短窗口要比它少写一两个字;装不下时删减或拆分叙事任务,不用加速堆字。可选写 original_subtitles.json,使用成片输出时间:
[{"start": 15.0, "end": 17.0, "text": "原声台词"}]只写留白中实际听得到的台词,订正 ASR 错字与人名,每条尽量控制在一行;被旁白盖住或已经剪掉的句子不要写。省略时,合成阶段会使用保守的 ASR 映射兜底,并在成片中用 「」 区分原声对白与旁白。
在调用 LLM 评审前做以下反事实检查:
只记录并优先修复 1–3 个回报最高的问题;先改结构,再润色句子。
REVISION 还要逐项确认:用户点名的问题已经改变,未点名的冻结项没有意外变化,相关 style_card.json / visual_audio_board.json 中不存在旧镜头或旧表达。除非用户要求备选版本,不额外扩展新方向。
python3 scripts/review.py --work-dir <work_dir> # 会联网:外发内容与关闭方式见 §2评审会自动识别 cut 模式,并在存在已校验剪辑计划时按输出时间线核对;--timeline source 可强制使用原片时间。打开 narration_review.md,逐项处理 error,尤其是 category=hallucination。
重复修改并评审,直到:
verdict 为 PASS 且没有 error;或覆盖决定追加到 work_dir/narration_review_override.md:
### 覆盖记录 — <date>
- 问题:segment 4 / category=hallucination
- 评审意见:“他早已知情”缺少画面/对白依据
- 决定:KEEP — 该事实来自用户提供的当前集背景,而非未来剧情
- 签署:<agent/human>review.py 本身只写报告,默认调用策略为建议型、失败开放;若调用方显式开启严格评审,事实矛盾、残句、解析失败或评审不可用可在 TTS 前阻断。覆盖记录只用于审计,review.py / validate.py 不读取它。
python3 scripts/validate.py --work-dir <work_dir> --mode full
# cut 输出时间线由编排器使用 --mode cut_output命令写出 narration_lint.json。full 与 cut_output 用同一套声音归属算法(原声对白区间减去安静窗口)回写 overlaps_speech,其余字段原样保留,不截短、不合并、不补标点、不重排。推荐字数按时间窗先扣 0.45 秒 TTS 首尾静音再计算;full 模式下某段字数超过推荐字数的 1.25 倍即报 over_budget error,报告里写明时间窗、budget_chars、limit_chars、actual_chars 和 over_chars:缩短文字或放宽/挪动时间窗,不要指望 TTS 替你缩稿。有 error 时命令以非零退出,逐块列出「段 N」(narration.json 里第 N 块,从 1 数;narration_lint.json 的 index 仍从 0 数)、错误码、关键数字和改法。修复所有 error 后重复运行,直到校验干净,再继续 TTS 与合成。
片名或题材明确但缺少剧情上下文时,先按本技能的 references/research-guide.md 写 background_research.json。若理解素材偏薄,brief 中的数量只能当上限:宁可少写、写实,也不要为凑数复述画面。
review.py 的 MiMo 文字评审(见 §2);validate.py 与 lint 只在本地运行。© zenstory-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 16 other files (scripts, references) in skills/video-script of zenstory-ai/video-recap-skills.
Open the folder on GitHubat commit 5391686
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in zenstory-ai/video-recap-skills, which our catalogue first saw on October 7, 2026.
Video Script next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Video Script this skillzenstory-ai/video-recap-skills | 559 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Roadshow Video Generatoranbeime/skill | 7.7k | — | ~1.4k | Automated safety check: Notes | None | |
| Document To Narrationjwynia/agent-skills | 169 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Short Video Scripteraaron-he-zhu/aaron-marketing-skills | 2.9k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| ShowtimeFavioVazquez/showtime | 206 | — | ~3k | Automated safety check: Pass | MIT | |
| TSX Vertical Shorts Builderhassancs91/claude-faceless-shorts-creator | 271 | — | ~1.9k | Automated safety check: Notes | MIT |
anbeime/skill
Turns a document into a narrated roadshow video through ten staged roles, from document analysis and slide planning to audio, subtitles and final composition.
jwynia/agent-skills
Convert written documents to narrated video scripts with TTS audio and word-level timing.
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "script this short video", "write a TikTok / Reels / Shorts script", "给这条抖音或视频号视频写脚本", or "fix the hook — viewers drop off in the first seconds"…
FavioVazquez/showtime
A skill your agent uses when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a…
hassancs91/claude-faceless-shorts-creator
Builds a roughly 40-second vertical short end to end from a topic, scripting beats, rendering TSX compositions and layering voice and captions.
coleam00/hyperframes-ai-video-generation
A skill your agent uses when the user wants to create a new YouTube Short using one of the templates in this repo's templates/ folder.
zenstory-ai/video-recap-skills
从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm,并要求剪辑、添加旁白、 配音、总结、短剧/电视剧/电影/纪录片/科普解说时使用。负责编排 video- 技能链:视频理解 → Agent 制定故事与视听方案 → 剪辑 → 配音 → 合成。触发词:视频解说、视频旁白、生成解说、 视频 recap、video…
zenstory-ai/video-recap-skills
合成视频解说最终成片:把旁白音频铺到源视频上,按旁白窗口压低原声,生成 SRT / ASS 字幕并可烧录, 最后做响度标准化。作为最终合成阶段使用。输入源视频、ttsmeta.json 与旁白位置; 输出 recap 成片和字幕。触发词:视频合成、混音、字幕、压字幕、assemble video、mux、ducking、subtitles、成片。
zenstory-ai/video-recap-skills
把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节,读取 clipplan.json 与源视频, 输出 editedsource.mp4;随后 Agent 按输出时间线写 narration.json。支持单视频与多视频(sources manifest)拼剪, 本工具不读取、不映射旁白。
zenstory-ai/video-recap-skills
按需把一部成片拆成可复用的制作参考:测镜头节奏与响度,标注段落与音轨分工,把原片事实与可迁移方法分开, 导出不含原片人名台词的 productionreference.json 供下次制作参考。不在默认生产路径上。
zenstory-ai/video-recap-skills
把视频分析为结构化理解索引:场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief. An agent skill from zenstory-ai/video-recap-skills.
zenstory-ai/video-recap-skills
把带时间戳的 narration.json 合成为中文解说音频。使用 MiMo TTS(mimo-v2.5-tts)或 Fish Audio(s2.1-pro-free)或显式配置的通用 IndexTTS HTTP 服务逐段生成语音, 按时间窗动态适配语速并处理响度;输入输出时间线上的旁白,产出 ttssegments 与 ttsmeta.json。
Categories
对已完成分析的视频进行导演与剪辑策划,再写带时间戳的中文解说并校验;也处理已有短片的 宣发标题、花字修订和外部文案回填。普通策划输入 workdir 的 agentnarrationbrief.md 与 vlmanalysis.json;文案返修输入当前成片的工程与内容证据。策划输出 recapstoryplan.json、visualaudioboard.json、 可选…. Video Script is an agent skill from zenstory-ai/video-recap-skills.
Video Script fits situations like: tasks that involve Text to speech and voice; tasks that involve Video scripts and shorts.
Run `npx skills add zenstory-ai/video-recap-skills --skill video-script -a claude-code`. Or copy the skill folder (skills/video-script in zenstory-ai/video-recap-skills) into .claude/skills/video-script in your project. Claude Code loads it when a task matches its description.
Run `npx skills add zenstory-ai/video-recap-skills --skill video-script -a codex`. Or copy the skill folder (skills/video-script in zenstory-ai/video-recap-skills) into .agents/skills/video-script in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zenstory-ai/video-recap-skills --skill video-script -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-script, .gemini/skills/video-script, .github/skills/video-script and .opencode/skills/video-script in your project.
Going by SKILL.md and its folder, Video Script needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named MIMO_API_KEY. Our summary lists: Python 3; A credential in MIMO_API_KEY.
SKILL.md names 2 domains. In commands or code: api.xiaomimimo.com and token-plan-cn.xiaomimimo.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Video Script is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Video Script: Roadshow Video Generator (anbeime/skill, 7.7k stars), Document To Narration (jwynia/agent-skills, 169 stars), Short Video Scripter (aaron-he-zhu/aaron-marketing-skills, 2.9k stars) and Showtime (FavioVazquez/showtime, 206 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
zenstory-ai (a GitHub organization) maintains it in zenstory-ai/video-recap-skills, which has 559 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 4, 2026.
Source: zenstory-ai/video-recap-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.