jianshuo/claude-skills / wjs-segmenting-video
wjs-segmenting-video
VerifiedUse when the user has a long-form video (interview / lecture / podcast / conversation) and a transcript SRT, and wants to extract 3–6 stand-alone topical short clips from it. This skill ONLY cuts and crops — it produces raw clips + per-clip SRTs as a hand-off package for downstream post-production (`/wjs-overlaying-video`). Triggers — "切成几段", "分主题", "拆成短视频", "切片", "topic segments", "split into clips".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.8 KB |
| references/example_segments.json | config | 1.2 KB |
| references/platform_sizes.md | markdown | 907 B |
| references/segments_schema.json | config | 1.8 KB |
| scripts/burn_subs.py | script | 9.3 KB |
| scripts/compose_cover.py | script | 7.5 KB |
| scripts/make_cover.py | script | 5.3 KB |
| scripts/prepend_intro.py | script | 11.6 KB |
| scripts/segment.py | script | 4.8 KB |
references/example_segments.json
View on GitHub{
"source_video": "talk.mp4",
"source_srt": "talk.zh-CN.srt",
"platform": "wechat_channels",
"segments": [
{
"id": 1,
"slug": "intent-not-code",
"title": "AI 时代不写代码\n而是写意图",
"summary": "代码已经从机器码 → 汇编 → 高级语言一路抽象上来,下一层抽象是用自然语言表达意图。AI 把意图编译成代码,人不再去改编译产物。",
"start": "00:00:43.460",
"end": "00:02:35.220",
"cover_prompt": "A developer at a glowing terminal, intent flowing as light into the screen, cinematic vertical composition, modern soft tech aesthetic, rich blues and amber"
},
{
"id": 2,
"slug": "code-as-compiled-not-handwritten",
"title": "代码是编译产物\n不应再手工修改",
"summary": "把 AI 生成的代码当成汇编/机器码——它是从你自然语言 prompt 编译下来的产物,bug 应在 prompt 层修,不在产物层修。",
"start": "00:02:35.220",
"end": "00:04:30.000",
"cover_prompt": "Layers of abstraction stacked vertically — natural language at the top, source code in the middle, machine code at the bottom — connected by glowing arrows, soft schematic style"
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |