video-cut SKILL.md skillA
video-cut from zenstory-ai/video-recap-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zenstory-ai/video-recap-skills/video-cut@git:20261015.5785c33Pins git:20261015.5785c33 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zenstory-ai/video-recap-skills
- Path
skills/video-cut/SKILL.md- Versions recorded
- 16
- Latest version
- git:20261015.5785c33, committed Oct 15, 2026
- First version recorded
- Jun 19, 2026
- Size
- 11,734 bytes
- Repository stars
- 600
- License
- MIT
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 clip_plan.json 与源视频， 输出 edited_source.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。 触发词：视频剪辑、剪辑式解说、video cut、clip plan、拼剪。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## 1. 定位
本技能只执行 Agent 已经做出的剪辑决定：
1. 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`。
2. 先避开原片硬切附近的闪帧风险，再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。
3. 把每个入点对齐到源视频帧网格、每段时长对齐到整数个输出帧（不足一帧的移动，优先选句界门禁仍判为安全、仍在停顿内的一侧；两侧同样安全时选不跨过原片硬切的一侧，避免闪一帧），句界门禁检查的是对齐后的边界。
4. 拼接选定区间，输出恒定帧率的 `edited_source.mp4`，帧数与 `clip_plan_validated.json` 记录的一致。
5. 到此停止，由 Agent 按真实输出时间线写 `narration.json`；本工具不读取旁白，也不做原片→输出映射。
渲染缓存按输入与设置复用。`edited_source.mp4.meta.json` 记录标准化 clips、渲染设置和每个源文件的 `size`/`mtime_ns`；三者与当前一致且 `edited_source.mp4` 存在非空才复用，任一不同即重渲染。只有 sidecar 而没有媒体文件不复用。
## 2. 输入契约
`work_dir/clip_plan.json` 可以是数组，也可以是 `{"clips": [...]}`：
```json
{"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`（不接受 `id` 代替），并用 `--sources-manifest` 传入来源清单（形状见下）。
- `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。只含语气词或 ASR 杂音的窗口（"啊！"、"Hi."）不算讲话区间，只在紧挨真实对白的一侧保留 1 秒保护。只有标点的窗口（"……"）仍算讲话。
多视频来源清单只接受一种形状，其他形状直接报错并写明期望形状：
```json
…Read the whole file at its exact version.
How to install
mdr add zenstory-ai/video-recap-skills/video-cut@sha256:063eef0a661dd72cThe line at the top of this page pins the label git:20261015.5785c33, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_fjysta2lu2zg2gr5)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 16 versions of this file, between Jun 19, 2026 and Oct 15, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.5785c33 latest | 2026-10-15 | 5785c33 | 11,734 B | A | view · diff |
| git:20261014.14640fd | 2026-10-14 | 14640fd | 11,750 B | A | view · diff |
| git:20261003.f3c9c63 | 2026-10-03 | f3c9c63 | 11,756 B | A | view · diff |
| git:20261003.1fa335a | 2026-10-03 | 1fa335a | 11,660 B | A | view · diff |
| git:20261003.2bbde94 | 2026-10-03 | 2bbde94 | 9,717 B | A | view · diff |
| git:20261003.ed436e4 | 2026-10-03 | ed436e4 | 9,243 B | A | view · diff |
| git:20261003.c1e9698 | 2026-10-03 | c1e9698 | 9,058 B | A | view · diff |
| git:20260921.aeb0238 | 2026-09-21 | aeb0238 | 7,281 B | A | view · diff |
| git:20260920.306f2db | 2026-09-20 | 306f2db | 8,270 B | A | view · diff |
| git:20260920.6122439 | 2026-09-20 | 6122439 | 8,852 B | A | view · diff |
| git:20260920.9e9f356 | 2026-09-20 | 9e9f356 | 7,462 B | A | view · diff |
| git:20260824.370010a | 2026-08-24 | 370010a | 6,060 B | A | view · diff |
| git:20260715.affe325 | 2026-07-15 | affe325 | 4,857 B | A | view · diff |
| git:20260714.468182c | 2026-07-14 | 468182c | 4,276 B | A | view · diff |
| git:20260627.00f5ff7 | 2026-06-27 | 00f5ff7 | 5,037 B | A | view · diff |
| git:20260619.9e63de7 | 2026-06-19 | 9e63de7 | 4,422 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11734 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
zenstory-ai/video-recap-skills · 600 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fjysta2lu2zg2gr5 GET https://markdownregistry.com/api/v1/resolve?ref=zenstory-ai/video-recap-skills/video-cut GET https://markdownregistry.com/api/v1/blob/063eef0a661dd72cdcd987dbf7b59785094a32a69f0fbfded6e5675f01947dea
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from zenstory-ai/video-recap-skills
Every file in zenstory-ai/video-recap-skills