Skip to content

jianshuo/claude-skills / wjs-segmenting-video

wjs-segmenting-video

Verified

Use 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".

references/segments_schema.json

View on GitHub
{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "title": "video-segmentation segments.json",
  "type": "object",
  "required": ["source_video", "segments"],
  "properties": {
    "source_video": {
      "type": "string",
      "description": "path to the source video, relative to segments.json"
    },
    "source_srt": {
      "type": "string",
      "description": "optional path to the source SRT used to pick boundaries"
    },
    "platform": {
      "type": "string",
      "enum": ["wechat_channels", "douyin", "xiaohongshu", "shorts", "reels"],
      "default": "wechat_channels"
    },
    "segments": {
      "type": "array",
      "minItems": 1,
      "items": {
        "type": "object",
        "required": ["id", "slug", "title", "start", "end"],
        "properties": {
          "id": {"type": "integer", "minimum": 1},
          "slug": {
            "type": "string",
            "pattern": "^[a-z0-9-]+$",
            "description": "kebab-case English; used in filenames"
          },
          "title": {
            "type": "string",
            "description": "cover title; use \\n for line breaks; aim for 8-12 Chinese chars per line, 2 lines max"
          },
          "summary": {"type": "string"},
          "start": {
            "type": "string",
            "pattern": "^\\d{2}:\\d{2}:\\d{2}[,.]\\d{1,3}$",
            "description": "HH:MM:SS.mmm or HH:MM:SS,mmm; must align to an SRT cue boundary"
          },
          "end": {
            "type": "string",
            "pattern": "^\\d{2}:\\d{2}:\\d{2}[,.]\\d{1,3}$"
          },
          "cover_prompt": {
            "type": "string",
            "description": "passed to gpt-image-2 along with a real frame as ref-image; describe visual concept, not literal scene; ALWAYS include 'no text' in your wrapper prompt to suppress hallucinated glyphs"
          }
        }
      }
    }
  }
}
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall