Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zenstory-ai/video-recap-skills --skill video-scriptgit clone --depth 1 https://github.com/zenstory-ai/video-recap-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zenstory-ai/video-recap-skills/video-script)<a href="https://agentmods.dev/skills/zenstory-ai/video-recap-skills/video-script"><img src="https://agentmods.dev/badge/skills/zenstory-ai/video-recap-skills/video-script/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zenstory-ai/video-recap-skills/video-script"><img src="https://agentmods.dev/badge/skills/zenstory-ai/video-recap-skills/video-script.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00154 | $0.03798 |
| Opus 5 | $0.00077 | $0.01899 |
| Sonnet 5 | $0.00031 | $0.00760 |
| Haiku 4.5 | $0.00015 | $0.00380 |
Grade A, and why
video-script scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- video-script — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. 定位
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:
- 导演
- 故事编辑
- 画面剪辑师
- 声音/旁白编辑
- 第一次观看的观众
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;full 模式还会把旁白对齐到安静窗口。
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。本技能不从其他技能目录读取参考文件或辅助脚本;外部输入只来自显式路径与 work_dir 产物。
1.1 创作控制模式
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:
- CREATE:首次创作。比较至少两个真正可行的故事/剪辑假设后再选择。
- DIRECTED:用户已指定结构、镜头、台词或表达。忠实落实,不为满足“创作流程”虚构替代方案。
- REVISION:用户针对已有版本看片修改。最新反馈是当前事实来源;未点名部分默认冻结。
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。
2. 读取素材并确认状态
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。- brief 顶部列出的 contact sheet:不要只依赖场景摘要;反应、走位、静止和台词前后的具体时刻常常更重要。
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。- full 模式:没有
narration.json时进入写稿;存在时先复核再校验。 - cut 第一阶段:尚无
clip_plan_validated.json/edited_source.mp4,只写clip_plan.json。 - cut 第二阶段:两者都存在,按
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。
3. 制定创作方案
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。
3.1 导演判断
锁定:
- 观众承诺
- POV
- 戏剧问题
- 起始与结束情绪
- 隐瞒与揭示
- 结尾余味
3.2 故事编辑
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。
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/creative-editing-playbook.md 12 KB
- references/research-guide.md 3.2 KB
- scripts/agent_brief.py 26 KB runs code
- scripts/agent_text.py 11 KB runs code
- scripts/brief_context.py 14 KB runs code
- scripts/brief_inputs.py 9.8 KB runs code
- scripts/brief_timeline.py 13 KB runs code
- scripts/deslop_qc.py 10 KB runs code
- scripts/evidence_bundle.py 17 KB runs code
- scripts/lib.py 17 KB runs code
- scripts/narration_lint.py 27 KB runs code
- scripts/narration.py 370 B runs code
- scripts/review_grounding.py 9.6 KB runs code
- scripts/review_response.py 32 KB runs code
- scripts/review_runner.py 7.2 KB runs code
- scripts/review.py 1.1 KB runs code
- scripts/speech_ownership.py 4.9 KB runs code
- scripts/timeline_fusion.py 4.2 KB runs code
- scripts/validate.py 6.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 249 lines · 154 tokens per session scan A 58d03a784e81
video-script is a skill published in the GitHub repository zenstory-ai/video-recap-skills (505 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 3,798 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
narrator-ai-cli
A command-line client for creating AI-narrated movie and short-drama videos. It can guide a workflow from selecting source material, templates, music, and voices to writing narration and combining the video.
narrator-ai-cli
Create AI-narrated film/drama commentary videos via CLI. Two workflow paths (Original & Adapted narration), 93 movies, 146 BGM tracks, 63 dubbing voices in 11 languages, 90+ narration templates. Use when creating narration videos, film commentary, short drama dubbing, or video production.
recut-editor
A timeline-editing skill for creating new videos or changing parts of an existing timeline in a CapCut-style editor. It can work with media assets and export the result while keeping edits undoable.
recut-directing-qc
A quality-control workflow for diagnosing problems in a finished video. It connects each visible symptom to a likely cause and a repair, then checks whether the fix passes review.
recut-directing-short-drama
A directing guide for planning the production of story-based AI short dramas, animated dramas, and narrative short videos. It covers decisions from story intent through a controlled production process and contract management.
ai-storyboard-director
A set of instructions for an AI storyboard director used in video editing or planning.