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/oh-story-dsh --skill video-cutgit clone --depth 1 https://github.com/zenstory-ai/oh-story-dshWrote 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/oh-story-dsh/video-cut)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/video-cut"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/video-cut/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/oh-story-dsh/video-cut"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/video-cut.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00119 | $0.01764 |
| Opus 5 | $0.00060 | $0.00882 |
| Sonnet 5 | $0.00024 | $0.00353 |
| Haiku 4.5 | $0.00012 | $0.00176 |
Grade A, and why
video-cut 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 7d 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.
This is a copy
100% identical to video-cut — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. 定位
本技能只执行 Agent 已经做出的剪辑决定:
- 校验并补全
clip_plan.json,写出带clip_id、原片/输出时间与时长的clip_plan_validated.json。 - 先避开原片硬切附近的闪帧风险,最后把边界吸附到可靠句末/自然停顿;声音完整性拥有最终优先级。
- 拼接选定区间,输出
edited_source.mp4。 - 编排流程默认到此停止,由 Agent 按真实输出时间线写
narration.json。 - 旧版单阶段路径还会把原片时间的旁白映射为
narration_mapped.json。
相同输入会得到相同输出。缓存仅表示:当 edited_source.mp4 新于 clip_plan.json 时复用成片。
2. 输入契约
work_dir/clip_plan.json 可以是数组,也可以是 {"clips": [...]}:
{"start": 12.0, "end": 28.5, "reason": "b02 | turn | power: A→B | POV=女主 | 保留反应 | 入点=问题落下 | 出点=沉默结束"}
start/end是原片秒数;也接受source_start/source_end或in/out。- 顶层可选
target_duration,例如"10m"。 - 多视频项目的每个片段还必须填写
source_id。 speech_boundary_anchors.json与 ASR 时间段由理解阶段提供;Agent 先写大致区间,工具会尝试吸附并把仍在讲话区间内的入/出点作为 blocker 返回。
work_dir/narration.json 只在旧版单阶段路径中可选读取;该路径要求旁白使用原片时间。若允许重复或重叠片段,旁白可带 source_clip_id 消歧。
3. 剪辑意图契约
工具不会替 Agent 做创作选择。写片段前先完成本节的剪辑意图检查,并让每个区间映射到 recap_story_plan.json 的一个 beat。
使用现有自由文本 reason 保存简洁决定:
beat_id | function | change | POV | preferred moment | 入点 reason | 出点 reason
不要因为“事件重要”就保留整段;要保留最能让 change 成立的具体表演、反应、动作或揭示。理解与情绪允许时晚进早出,同时保证台词、动作和技术边界完整。
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。脚本不从其他技能目录读取文件;外部输入仅限命令显式传入的视频、参数与 work_dir 产物。
4. 运行命令
python3 scripts/cut.py <video> --work-dir <work_dir> \
[--target-duration 10m] [--clip-padding 0] [--allow-overlap]
5. 输出契约
clip_plan_validated.json:标准化片段,包含clip_id、source_start/end、output_start/end与duration。edited_source.mp4:按计划拼接后的短视频。narration_mapped.json:仅旧版单阶段路径生成;编排流程使用--no-narration-map,不会生成该文件。
编排流程下游把 edited_source.mp4 当作视频,把 Agent 按输出时间写的 narration.json 当作旁白。
6. 边界与时间线规则
- 旧版路径中,
clip_plan.json与narration.json都使用原片时间;本工具负责原片 → 输出映射。 - 编排路径中,
narration.json直接使用剪后输出时间,不再映射。 - 默认禁止重叠或重复原片区间;
--allow-overlap开启后,旁白应填写source_clip_id。 - 片段起点只能位于源头、可靠句末/静音窗,或与上一片段构成无损同源连续连接;片段终点同理。ASR 判定仍在讲话且无法吸附时写入
unsafe_clip_sentence_boundary并阻断。 SCENE_CUT_SNAP默认开启:先按画面把 source start 向后、source end 向前吸附到附近硬切,随后句末吸附再做最终修正,避免视觉修正重新制造半句原声。默认范围为SCENE_CUT_SNAP_MARGIN=0.5秒,检测阈值为SCENE_CUT_DETECT_THRESHOLD=0.4。- scene-change score 只提供接点候选,不证明接点自然。先检查短时间窗内是否出现密集候选,再区分来源:原片自带的无关短镜头整段删除;相关但短到像闪帧的镜头通过扩展 IN/OUT 保留完整动作、反应或台词,不用定格/慢放伪造时长;由本次拼接制造的切点则优先移动边界、恢复同源连续运动、合并相邻片段或改用更自然的连接,尽量消除。成片后仍要逐个播放接点前后约 0.5–1 秒;白闪或曝光叠化再结合逐帧亮度定位,不能为了通过视觉检测切断完整台词,也不能用转场遮掩坏接点。
- 连续同源片段的无损连接不做句中双侧音频淡出;非连续片段仍在安全停顿内做防爆音淡入淡出。
- 旧版旁白映射若跨越 clip 边界,不再裁短后继续:
clamped_beats永久阻断,--allow-sparse-cut也不能绕过旁白句子完整性。
What ships with it
8 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.
- scripts/cut_cli.py 12 KB runs code
- scripts/cut_contract.py 19 KB runs code
- scripts/cut_render.py 11 KB runs code
- scripts/cut.py 1.7 KB runs code
- scripts/lib.py 3.2 KB runs code
- scripts/media_geometry.py 8.4 KB runs code
- scripts/narration_mapping.py 8.8 KB runs code
- scripts/sentence_boundaries.py 22 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.
- 7d ago First seen · 91 lines · 119 tokens per session scan A 6ac561990a6e
video-cut is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (338 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 1,764 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to video-cut, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-short-analyze
A Chinese-language guide for analysing short popular web fiction, such as stories published on 番茄, 故事会, or 知乎盐选. It examines the core premise, plot structure, emotional arc, twists, writing techniques, and reader appeal.
browser-cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…
novel-language-style
A guide to choosing and controlling the writing style of online fiction. It covers narration, word choice, figurative language, dialogue, and techniques for making scenes easier to picture.
style-fingerprint
A Chinese-language system for measuring the writing style of a novel from a sample of its text. It records patterns in viewpoint, timing, sentences, word choice, dialogue, description, themes, and chapter structure.