Skip to content

zenstory-ai/video-recap-skills / skills/video-recap

video-recap

Verified

把一段或多集视频做成带画框字幕的中文解说成片或纯原声高光短片。用户提供 .mp4 / .mov / .mkv / .webm,要求做影视解说、短剧二创、加旁白配音、跨集混剪或导出剪映草稿时使用;串联完成看片识台词、定主线与留原声、按台词停顿切镜头、写词检查、TTS 配音与混音加字幕。触发词:视频解说、影视解说、视频旁白、生成解说、视频 recap、video recap、voiceover、narration、recap。

FileKindSize
SKILL.mdskill md18.4 KB
assets/dashboard/app.jsscript16.2 KB
assets/dashboard/index.htmlother867 B
assets/dashboard/styles.cssother22.6 KB
assets/dashboard/tokens.cssother8.9 KB
assets/dashboard/views.jsscript31.4 KB
references/audio-modes.mdmarkdown3.6 KB
references/config-playbook.mdmarkdown8.1 KB
references/creative-editing-playbook.mdmarkdown12.3 KB
references/data-schema.mdmarkdown34.6 KB
references/index-tts.mdmarkdown2.1 KB
references/jianying/LICENSE.duo-videoother1.0 KB
references/jianying/SOURCE.mdmarkdown703 B
references/jianying/empty_draft_meta_info.jsonconfig1.7 KB
references/jianying/empty_jy_material_video.jsonconfig1.8 KB
references/jianying/empty_jy_meta_material_value.jsonconfig358 B
references/jianying/empty_jy_project_info.jsonconfig3.6 KB
references/jianying/empty_jy_segment.jsonconfig1.3 KB
references/jianying/empty_jy_text_styles.jsonconfig440 B
references/jianying/empty_yj_material_audio.jsonconfig865 B
references/jianying/empty_yj_material_text.jsonconfig2.4 KB
references/packaging.mdmarkdown6.8 KB
references/promotional-copy.mdmarkdown4.1 KB
references/prompt-templates.mdmarkdown2.0 KB
references/research-guide.mdmarkdown2.7 KB
references/resource-library.mdmarkdown12.1 KB
references/shot-review.mdmarkdown4.8 KB
scripts/agent_text.pyscript2.7 KB
scripts/artifacts.pyscript972 B
scripts/asr.pyscript12.5 KB
scripts/asr_timing_evidence.pyscript4.2 KB
scripts/assemble.pyscript31.0 KB
scripts/assemble_constants.pyscript894 B
scripts/assembly_contract.pyscript10.3 KB
scripts/assembly_settings.pyscript3.8 KB
scripts/audio_automation.pyscript6.6 KB
scripts/audio_mix.pyscript18.5 KB
scripts/briefing/__init__.pyscript101 B
scripts/briefing/builder.pyscript31.1 KB
scripts/briefing/context.pyscript6.1 KB
scripts/briefing/timeline.pyscript23.0 KB
scripts/codec_peak.pyscript5.1 KB
scripts/cut.pyscript148 B
scripts/cut_cli.pyscript12.4 KB
scripts/cut_contract.pyscript13.3 KB
scripts/cut_qc.pyscript1.9 KB
scripts/cut_render.pyscript13.2 KB
scripts/dashboard/__init__.pyscript159 B
scripts/dashboard/data.pyscript24.6 KB
scripts/dashboard/io.pyscript7.1 KB
scripts/dashboard/runs.pyscript21.8 KB
scripts/dashboard/templates.pyscript9.6 KB
scripts/dashboard_server.pyscript9.3 KB
scripts/detect.pyscript22.2 KB
scripts/doctor.pyexecutablescript12.9 KB
scripts/entry_suggestion.pyscript4.6 KB
scripts/export_jianying.pyscript5.6 KB
scripts/extract.pyscript2.5 KB
scripts/final_qc.pyscript19.0 KB
scripts/frame_grid.pyscript10.6 KB
scripts/jianying/__init__.pyscript49 B
scripts/jianying/builders.pyscript11.3 KB
scripts/jianying/model.pyscript2.7 KB
scripts/jianying/optional.pyscript1012 B
scripts/jianying/schema.pyscript2.5 KB
scripts/jianying/templates.pyscript1.0 KB
scripts/jianying/timeline_contract.pyscript5.8 KB
scripts/jianying/tracks.pyscript2.0 KB
scripts/jianying/writer.pyscript7.8 KB
scripts/lib.pyscript29.6 KB
scripts/library.pyscript31.1 KB
scripts/lint_summary.pyscript5.0 KB
scripts/loudness.pyscript14.7 KB
scripts/materials.pyscript22.1 KB
scripts/media.pyscript18.8 KB
scripts/narration_audio.pyscript13.5 KB
scripts/narration_lint.pyscript24.1 KB
scripts/narrative_selection.pyscript8.9 KB
scripts/packaging.pyscript6.1 KB
scripts/packaging_fonts.pyscript12.0 KB
scripts/packaging_plates.pyscript31.2 KB
scripts/packaging_studio.pyscript34.1 KB
scripts/providers/__init__.pyscript72 B
scripts/providers/fish_audio.pyscript3.1 KB
scripts/providers/index_tts.pyscript8.8 KB
scripts/recap.pyscript183 B
scripts/recap_cli.pyscript6.9 KB
scripts/recap_inspect.pyscript16.5 KB
scripts/recap_runner.pyscript22.0 KB
scripts/recap_runtime.pyscript11.8 KB
scripts/recap_source.pyscript1.8 KB
scripts/recap_stage_qc.pyscript2.7 KB
scripts/recap_timeline.pyscript7.7 KB
scripts/render_preflight.pyscript1.7 KB
scripts/resources/__init__.pyscript200 B
scripts/resources/lock.pyscript6.8 KB
scripts/resources/project_binding.pyscript16.1 KB
scripts/sentence_boundaries.pyscript28.8 KB
scripts/sentence_gate.pyscript8.6 KB
scripts/sfx_mix.pyscript14.6 KB
scripts/shot_review.pyscript18.9 KB
scripts/source_subtitles.pyscript7.2 KB
scripts/speech_ownership.pyscript9.3 KB
scripts/storyboard.pyscript21.8 KB
scripts/subtitles/__init__.pyscript56 B
scripts/subtitles/core.pyscript19.0 KB
scripts/subtitles/render.pyscript8.0 KB
scripts/timeline.pyscript8.2 KB
scripts/timeline_emit.pyscript5.4 KB
scripts/tts_audio.pyscript9.6 KB
scripts/tts_cache.pyscript4.5 KB
scripts/understand.pyscript171 B
scripts/understanding_brief.pyscript6.3 KB
scripts/understanding_cache.pyscript8.0 KB
scripts/understanding_runner.pyscript9.8 KB
scripts/understanding_storyboard.pyscript11.9 KB
scripts/validate.pyscript5.7 KB
scripts/visual_render.pyscript10.1 KB
scripts/vlm.pyscript16.4 KB
scripts/voiceover.pyscript28.0 KB

references/resource-library.md

View on GitHub
# 资源库、模板与样片

资源库归用户自己维护,与素材库共用同一个根目录(通过 `--material-library-dir` 或 `VIDEO_RECAP_MATERIAL_LIBRARY_DIR` 指定)。仓库不内置任何真实 BGM、音效、音色、字体或包装素材;可运行的合成演示见 `examples/resource-library/`。

```text
<library>/
  library.json                                     # {"schema": "video-recap.library.v1", "name": "…"}
  materials/…                                      # 视频理解分析缓存与剧集分集元数据(见 data-schema.md)
  resources/<kind>/<id>/resource.json (+ 资源文件) # 或按二级分类目录存放:resources/<kind>/<category>/<id>/resource.json
  templates/<kind>/<id>/v<version>/template.json
  samples/<id>/sample.json (+ 样片文件,或指向库外的绝对路径)
```

本技能目录下提供三个只读查询命令:

```bash
python3 scripts/library.py --library-dir <library> check          # 存在错误时退出码为 1;加 --json 输出机器可读报告
python3 scripts/library.py --library-dir <library> list [--kind bgm]
python3 scripts/library.py --library-dir <library> show <id|id@vN>
```

也可以打开本地只读审片与素材页浏览资源、模板与样片(支持图片、音频与样片预览):`python3 scripts/dashboard_server.py --root <library 或其上层目录>`。

以上查询命令都不改写资源库。新增或修改条目时直接编辑 JSON,再跑 `check` 校验。**错误(error)**表示该条目无法投入使用;**警告(warning)**表示可以使用但需要人工复核(例如版权或声音授权未确认、样片文件不在本机、模板采纳后底层资源文件发生过变动)。

## 通用规则

- `id` 必须与所在目录名一致,只能使用小写字母、数字和 `. _ -`;模板版本目录命名为 `v<version>`。
- 顶层字段受严格校验:出现未定义的字段直接报错,防止拼写错误不报错就被跳过。
- 资源与模板内的文件路径相对于记录所在目录解析,且解析后的真实路径必须留在资源库根目录内(`..` 越界、绝对路径和指向库外的符号链接都会报错)。唯一例外是样片记录可以填写库外绝对路径,方便直接指向存放在外部磁盘上的成片。
- 文件身份只比对 `{size, mtime_ns}`,不计算内容哈希。
- 运行中生成的派生文件(如归一化 WAV、转码片段)只写入 `work_dir`,不会回写进资源库。

## 资源 `resource.json`

```json
{
  "schema": "video-recap.resource.v1",
  "id": "pulse-demo",
  "kind": "bgm",
  "title": "合成脉冲底噪(演示)",
  "files": [{"role": "main", "path": "pulse-demo.wav"}],
  "origin": {"creator": "…", "url": "…"},
  "license": {"status": "owned", "terms": "…", "evidence": "…"},
  "tags": ["低频"],
  "notes": ""
}
```

| `kind` | 必需文件 | 额外字段 |
|---|---|---|
| `bgm` | 至少一个音频文件(wav / mp3 / m4a / aac / flac / ogg) | 可选分类与声学画像:`category`(未填时自动继承二级分类目录名)、`sub_category`、`moods`、`scene_fit`、`energy`、`tempo_band`、`bpm`、`has_vocal`(布尔值;`true` 时 `check` 报警告且解说模式拒绝绑定)、`speech_friendly`、`measured`(如 `{duration_sec, lufs_i}`) |
| `sfx` | 至少一个音频文件(wav / mp3 / m4a / aac / flac / ogg) | 可选 `category`(如 `whoosh` / `impact` / `riser` / `accent`)、`tone`、`scene_fit`、`peak_offset_ms`(音效最响处的毫秒位置,混音时自动前移对齐画面切点)、`recommended_gain_db`、`measured` |
| `voice` | 可选参考音频 | `voice.provider` ∈ `mimo-tts` / `fish-audio` / `index-tts`,并填写 `voice.voice_id` 或附带一个参考音频;附带参考音频时必须填写 `consent.status` ∈ `unknown` / `granted` / `denied`;可选 `category`、`persona`、`gender`、`languages`、`recommended_speed` |
| `font` | 至少一个字体文件(ttf / otf / ttc) | 可选 `font.family`、`font.index`、`visibility` |
| `image` | 至少一张图片(png / jpg / webp),用于角标、包框或片尾卡 | 可选 `visibility` ∈ `public` / `internal`(`internal` 供模板内部引用,不在素材库主视图平铺展示) |

`license.status` ∈ `unknown` / `owned` / `licensed` / `restricted`,必须由人工填写;工具不会因为文件放进了资源库就默认已获授权。`unknown` 与 `restricted` 在 `check` 时会报出警告。

## 模板 `template.json`

```json
{
  "schema": "video-recap.template.v1",
  "id": "clean-white",
  "version": 1,
  "kind": "subtitle_style",
  "title": "白字细描边",
  "canvas": {"width": 900, "height": 1600},
  "params": {
    "font": {"family": "Arial"},
    "size_px": {"value": 52, "provenance": "specified"},
    "max_chars": {"value": 15, "provenance": "measured"},
    "band": {"value": {"y_top": 1280, "y_bot": 1440}, "provenance": "measured"}
  },
  "samples": ["demo-sample"],
  "status": "adopted",
  "adoption": {"date": "2026-09-27", "by": "user", "statement": "用户原话", "scope": "适用范围"}
}
```

- 模板只对 `canvas` 声明的画布尺寸生效;更换画幅必须新建模板,不会自动按比例缩放。
- 凡带 `provenance` 的参数都必须包含 `value`,且 `provenance` ∈ `measured`(从成片画面实测)/ `fitted`(调试校准得出)/ `specified`(人工直接指定)/ `unknown`。剪辑软件面板上的字号读数不等于实际像素高,应记为 `specified` 或 `unknown`。
- 引用库内资源时写 `{"resource": "<id>"}`:`params.font` 必须指向 `font` 资源,包装图层的 `image` 必须指向 `image` 资源。
- `subtitle_style` 必须包含 `params.font`(填 `resource` 或 `family`)、`params.size_px` 与 `params.max_chars`(按该画布能容纳的最长单行字数校准);当 `size_px × max_chars` 超过画布宽度减去左右各 40px 默认边距时报错。可选参数为 `outline_px`、`shadow_px`、`primary_color`、`outline_color`、`max_lines`、`band`,出现其他参数名直接报错;若给出 `params.band.value`,需满足 `0 <= y_top < y_bot <= canvas.height`。
- `packaging` 支持静态图层 `params.layers` 或画框版式配置 `params.studio_plan`(`preset` ∈ `portrait_cinema` / `portrait_stage` / `landscape_cinema`),也可二者同时组合;静态图层包含唯一 `name`、`image` 资源引用以及落在画布内的整数 `rect {x, y, width, height}`;可选 `params.safe_rect`。
- `production_reference` 模板见下一节。
- `status` ∈ `draft` / `adopted` / `retired`。状态为 `adopted` 时必须填写 `adoption.date`(YYYY-MM-DD)、`by`、`statement`(用户确认原话)与 `scope`。可选 `adoption.resources` 记录采纳当下底层资源文件的大小与修改时间:

  ```json
  "resources": {"frame-demo": [{"path": "resources/image/frame-demo/frame-demo.png", "size": 6063, "mtime_ns": 0}]}
  ```

  此后若资源文件的大小或修改时间发生变化,`check` 会报 `changed_since_adoption` 警告,提醒重新确认采纳或发布新版本模板。由于修改时间属于本机文件系统属性,把资源库复制到另一台机器后,所有快照都会提示已变化。

### 制作参考模板 `production_reference`

把独立拆片技能导出的 `production_reference.json`(仅含可迁移方法与实测数值,不含原片剧情与人名)登记为带版本、需确认采纳的模板:

1. 创建 `templates/production_reference/<id>/v1` 目录,把导出的 `production_reference.json` 原样复制进去,保持文件名不变。
2. 编写 `template.json`:`params` 固定写 `{"reference": {"path": "production_reference.json"}}`;`canvas` 从导出物复制,仅作信息展示,项目绑定时不校验画布尺寸。
3. 编写 `samples/<id>/sample.json` 指向原成片,在 `demonstrates` 与 `not_reusable` 中写明供人查阅的摘要;包含原片事实的完整拆解稿留在本地工作目录,不进资源库。
4. 运行 `library.py check`:导出物的 `schema` 必须为 `video-reference.production.v1`,`methods` 非空且每条包含合法 `dimension` 与 `rule`;任意层级只要出现 `source_facts`、`labels`、`evidence`、`entities`、`statement`、`from`、`path` 键即报错(与参考技能导出时的防泄漏复扫规则一致)。
5. 用户确认后,将 `status` 改为 `adopted` 并在 `adoption` 中记录用户原话。后续如需调整方法,新建 `v2` 目录,不直接修改已采纳的版本。

## 样片 `sample.json`

```json
{
  "schema": "video-recap.sample.v1",
  "id": "demo-sample",
  "title": "纯色演示片",
  "file": {"path": "demo-sample.mp4"},
  "canvas": {"width": 900, "height": 1600},
  "demonstrates": ["字幕带位置", "画布尺寸"],
  "not_reusable": "这条样片里哪些东西不能照搬",
  "templates": ["clean-white@v1"]
}
```

样片是核对模板效果的实物依据,不是模板本身:`demonstrates` 写明它示范了哪些版式或节奏特征,`not_reusable` 写明哪些具体内容(人物、台词字幕、时间点等)不能照搬,`templates` 用 `id@vN` 指回它所对应的模板版本。

## 项目绑定 `recap_project.json`

```json
{
  "schema": "video-recap.project.v1",
  "name": "某系列竖屏解说",
  "library": "../video-library",
  "bindings": {"subtitle_style": "clean-white@v1", "voice": "narrator-demo", "bgm": "pulse-demo"}
}
```

运行 `python3 scripts/recap.py <video> --project <recap_project.json 或所在目录> …` 时,编排器会在进入任何阶段前先解析项目绑定:`library` 路径相对于项目文件解析,所引用的模板状态必须为 `adopted`,且涉及的资源与模板都必须通过 `check`。解析结果会转换为各子阶段入口脚本既有的命令行参数或环境变量传递给各阶段脚本,子阶段脚本本身不直接读取资源库:

| 绑定项 | 传递方式 |
|---|---|
| `subtitle_style` | `SUBTITLE_PLAY_RES_X/Y` = 模板画布宽高,`SUBTITLE_FONT_SIZE` ← `size_px`,`SUBTITLE_OUTLINE` ← `outline_px`,`SUBTITLE_SHADOW` ← `shadow_px`,`SUBTITLE_PRIMARY_COLOR` / `SUBTITLE_OUTLINE_COLOR`(转成 ASS `&HAABBGGRR`),`SUBTITLE_MAX_CHARS` / `SUBTITLE_MAX_LINES`;`band` → 底对齐 `SUBTITLE_ALIGNMENT=2` 且 `SUBTITLE_MARGIN_V` = 画布高 − `y_bot`;`font.family` → `SUBTITLE_FONT_NAME`,若引用字体资源则同时设置 `SUBTITLE_FONT_FILE` |
| `voice` | provider → `--tts-provider`;MiMo 预置音色 → `--mimo-tts-voice`,参考音频 → `--voice-ref`;Fish Audio → `FISH_TTS_REFERENCE_ID`;index-tts → `INDEX_TTS_VOICE` |
| `bgm` | `BGM_PATH` ← 该资源下的第一个音频文件 |
| `production_reference` | 第一次暂停前写出 `work_dir/production_reference.json`(保留导出物原内容并附上 `written_by` 与 `template {id, version}`),仅供写稿 Agent 阅读,做片脚本不会读取,也不校验画布。若该路径已有非 `--project` 生成的文件:内容与导出物一致则原样保留,不一致则直接报错中止;解除绑定后只删除编排器自己写出的副本,不碰调用方手动放置的文件 |
| `packaging` | 合成前将模板 `params.layers` 写出到 `work_dir/packaging_layers.json`(含图层图片路径与 `rect`),并将 `params.studio_plan` 写出到 `work_dir/packaging_plan.json`(`video-recap.packaging_plan.v1`),由合成阶段渲染画布包装并同步写入 `timeline.json` |

- 若命令行或环境变量已显式传入某项配置,且与项目绑定解析出的值不一致,程序会在启动前报错中止并指明冲突项,不会悄悄覆盖。
- 合成前会核对字幕模板、包装模板的画布尺寸与成片实际画布是否一致;尺寸不符立即中止,换画幅必须绑定对应画幅的模板。
- 参考音频的 `consent.status` 为 `denied` 时拒绝绑定。
- 暂停打印的续跑命令只携带 `--project`,不把绑定展开成一长串散装参数;中途修改 `recap_project.json` 后续跑,会按新绑定重新解析。

## 运行记录

每次 `full` 或 `cut` 合成结束后,`work_dir/resource_lock.json` 都会记录本轮实际使用的原片、音色、BGM 与字幕字体,并关联资源库里的登记项与授权状态;字段定义见 `data-schema.md` 的 `resource_lock.json` 一节。
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall