agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/video-research/SKILL.md

video-research

Skill4 starsChanged 12 days agoMITView on GitHub

Ingest video URLs, video attachments, or local files into timestamped transcripts, OCR, and research-ready artifacts. Use when researching, summarizing, quoting, or extracting evidence from video.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use untracked .context/video-research/<slug>/ when ignored, else temporary output.

    line 11
  2. Very specific:

    Read research.md, then analysis.json and frames.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Turn video into searchable evidence. Start immediately when the user supplied it as a source.

Ingest

  1. Resolve accessible URL/absolute attachment path. Use only authorized media; ask before browser cookies or another auth boundary.
  2. Use untracked .context/video-research/<slug>/ when ignored, else temporary output.
  3. From the absolute skill directory run:
bash <skill-dir>/scripts/analyze-video.sh \
  --output-dir <untracked-output-dir> \
  <video-url-or-path>

It prefers captions, then local Whisper, samples frames, OCRs text, and writes analysis.json, transcript.txt, research.md. One-shot tools are pinned; first run may download a local model. Report progress; never add runtimes to target dependencies.

Optional: --language <code>, difficult audio --model medium, non-English visuals --ocr-language <codes>. Transcription is local by default. Cloud transcription uploads audio and may cost money, so requires explicit approval.

Research

Read research.md, then analysis.json and frames. ASR/OCR are derived: verify important wording at timestamp/frame before quoting. Combine transcript, on-screen text, visuals, description, chapters, and linked primary sources.

Durable multi-source work uses /research; cite the original video with timecodes, not generated transcript as an independent source.

Failure

Surface all warnings. A missing transcript from unavailable speech backend is failure: install runtime in scratch cache and rerun. Distinguish genuinely silent video and use OCR/frames. For private, removed, DRM, or inaccessible media, report boundary and request an accessible file; never bypass it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free