$npx skillfedfor your agent

wjs-segmenting-video

Segment long-form video into multiple stand-alone short clips by reading the SRT transcript and identifying topic boundaries. The skill cuts and crops with accurate-seek precision, extracting raw clips plus per-clip subtitles as a hand-off package for downstream post-production tools like overlaying and styling.

wjs-segmenting-video extracts 3–6 stand-alone topical short clips from long-form video with SRT transcript.

AI-generated summary based on this skill's SKILL.md

107 15 MITupdated by jianshuo

Decision gist · record as of 2026-07-23

wjs-segmenting-video extracts 3–6 stand-alone topical short clips from long-form video with SRT transcript. Segment long-form video into multiple stand-alone short clips by reading the SRT transcript and identifying topic boundaries. The skill cuts and crops with accurate-seek precision, extracting raw clips plus per-clip subtitles as a hand-off package for downstream post-production tools like overlaying and styling.

manual: git clone https://github.com/jianshuo/claude-skills → cp -r claude-skills/wjs-segmenting-video ~/.claude/skills/wjs-segmenting-video
wjs-segmenting-video/SKILL.md · version 43cf0dd2

Use it when

  • Yes.
  • wjs-segmenting-video delivers raw video clips plus per-clip SRT subtitle files for each segment.

Verify before relying

Read SKILL.md below before installing (9 files). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

jianshuo/claude-skills/wjs-segmenting-video · repository language: Python

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I cut long video into short clips with wjs-segmenting-video?

wjs-segmenting-video reads your SRT transcript to identify topic boundaries, then cuts your long-form video into multiple stand-alone short clips. It uses accurate-seek precision to extract raw clips and generates per-clip subtitles, creating a hand-off package ready for downstream post-production tools like overlaying and styling.

Can wjs-segmenting-video split an interview into topic segments?

Yes. wjs-segmenting-video is designed to segment interviews and lectures by topic boundaries. It analyzes your transcript to find natural topic breaks, then cuts the video at those points while preserving audio-subtitle sync accuracy, so each resulting clip stands alone without needing context from the original.

What output does wjs-segmenting-video provide for each clip?

wjs-segmenting-video delivers raw video clips plus per-clip SRT subtitle files for each segment. This paired output is optimized as a hand-off package for post-production workflows, letting you apply styling, overlays, and platform-specific formatting downstream without re-syncing audio and subtitles.

How does wjs-segmenting-video handle audio and subtitle sync?

wjs-segmenting-video cuts video segments using accurate-seek precision to maintain perfect audio-subtitle synchronization throughout the process. Each extracted clip retains its original sync quality, and the accompanying per-clip SRT files stay aligned with the video content, eliminating drift or desync issues.

Can wjs-segmenting-video extract short clips from podcast transcripts?

Yes. wjs-segmenting-video reads SRT transcripts to identify topic boundaries in podcasts, interviews, and lectures. It then extracts 3–6 topical short clips from your long-form content, converting each into a standalone clip viewable without the original context—ideal for platform distribution and social sharing.

What file formats does wjs-segmenting-video work with?

wjs-segmenting-video operates on long-form video paired with SRT subtitle files. It outputs raw video clips in their original format alongside per-clip SRT files, preserving compatibility with standard post-production pipelines and platform-ready workflows.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

wjs-segmenting-video

Cut a long video + SRT into multiple stand-alone short clips, each oriented for the target platform. This skill stops after cutting + cropping — it hands off the raw clips to /wjs-overlaying-video for covers, captions, illustrations, CTA, and final render.

When to use

  • Long-form video (≥10 min) with an existing SRT transcript.
  • Goal is stand-alone short clips (each viewable without context).
  • The user will (or you will) drive post-production separately in /wjs-overlaying-video.

When NOT to use

  • Single-topic trimming → just use ffmpeg -ss A -to B.
  • No transcript yet → run /wjs-transcribing-audio first (then /wjs-translating-subtitles if the segments need a non-source

(truncated - see the full file via the links below)

File tree — 9 files
wjs-segmenting-video/SKILL.md
wjs-segmenting-video/references/example_segments.json
wjs-segmenting-video/references/platform_sizes.md
wjs-segmenting-video/references/segments_schema.json
wjs-segmenting-video/scripts/burn_subs.py
wjs-segmenting-video/scripts/compose_cover.py
wjs-segmenting-video/scripts/make_cover.py
wjs-segmenting-video/scripts/prepend_intro.py
wjs-segmenting-video/scripts/segment.py

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Extract 3-6 topical short clips from a long-form video with transcript”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

wjs-overlaying-video
by jianshuo · jianshuo/claude-skills

Compose post-production overlays—captions, covers, illustrations, and calls-to-action—directly onto video clips using HyperFrames, rendering everything in one pass to preserve quality. Works seamlessly downstream of segmentation workflows, turning raw clips into upload-ready MP4s with HTML/CSS captions, AI-generated covers, and timed motion graphics.

MITupdated Jul 2026
★ 107repo stars
wjs-reframing-video
by jianshuo · jianshuo/claude-skills

Reframe videos between landscape and portrait by cropping a dynamic band that follows whoever is speaking, detected via mouth motion analysis. Ideal for repurposing interviews and podcasts across short-form platforms without rotating the source.

MITupdated Jul 2026
★ 107repo stars
wjs-editing-multicam
by jianshuo · jianshuo/claude-skills

Merge multiple camera angles into a single rendered video using audio energy to drive real-time cam selection. The skill reads sync metadata from each source, analyzes per-second loudness, and produces hard cuts or hard cuts with a corner PiP inset. Requires synced footage with `.sync.json` sidecars from wjs-syncing-multicam.

MITupdated Jul 2026
★ 107repo stars
wjs-burning-subtitles
by jianshuo · jianshuo/claude-skills

Embed SRT subtitles directly into video pixels using libass, or add them as a toggleable track for compatible players. This skill also serves as the final encoding stage for localized video: it can burn target-language subtitles, mix a dubbed audio track over the original at low volume, and produce a ready-to-upload MP4 in a single ffmpeg operation—no re-encoding cascade.

MITupdated Jul 2026
★ 107repo stars
wjs-syncing-multicam
by jianshuo · jianshuo/claude-skills

Synchronize footage from multiple cameras, phones, or audio recorders captured simultaneously by computing time offsets through audio envelope analysis. The skill generates `.sync.json` metadata sidecars alongside your originals—never modifying or re-encoding source files—so downstream tools can apply alignment at playback or editing time.

MITupdated Jul 2026
★ 107repo stars
wjs-localizing-video
by jianshuo · jianshuo/claude-skills

This orchestrator coordinates the complete video localization workflow by delegating each stage—transcription, translation, dubbing, and subtitle rendering—to specialized sub-skills. Invoke it when users request the full pipeline at once; for individual steps, call the sub-skills directly for faster, cleaner execution.

MITupdated Jul 2026
★ 107repo stars

More skills Context To Video (NOASSERTION) · wjs-converting-text-to-video (MIT)

Tags
topic-extractionvideo-cuttingclip-generationtranscript-awaremulti-segmentshort-form-prepaccurate-seekingplatform-agnostic