video-content-analysis — Claude Code skill: video analysis
Turns a local video into a transcript, frames, manifest, and short summary. It fits focus groups, webinars, training sessions, and recorded meetings.
npx skills add gasserane/personal-skills --skill video-content-analysis -a claude-codeWhat video-content-analysis does
This skill takes a local mp4, mkv, mov, or webm file and builds a manifest-led result pack. The pack contains the transcript, extracted frames, a manifest, and a Tier 1 BLUF summary that downstream MEL specialists can use for coding and assessment.
Privacy and consent are collected before processing. Sensitive material is transcribed with local Whisper, while internal or public recordings can use a Microsoft 365 caption file. Optional switches add speaker diarization through pyannote.audio or create summary.docx using the IPPF Visual Identity 2025 template.
The workflow is file-based, so live capture and audio-only input fall outside its scope. A consent_unclear status stops downstream analysis, which makes consent validation a hard prerequisite for the run.
What it helps with
- transcribe a focus-group recording
- extract frames from a webinar video
- create a manifest for downstream coding
- identify which voices appear in a recording
- write a branded Word summary
Example prompts for the agent
- Run
/analyze-video <path>onrecording.mp4and return the generated artefact pack. - Process a sensitive focus-group video with local Whisper and speaker diarization enabled.
- Run
/analyze-video --retrospectiveto review the recorded processing results.
How to install video-content-analysis
1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill video-content-analysis -a claude-code2Manually: put the files in place
~/.claude/skills/video-content-analysis/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/video-content-analysis/
1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill video-content-analysis -a codex2Manually: put the files in place
.agents/skills/video-content-analysis/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill video-content-analysis -a cursor2Manually: put the files in place
.cursor/skills/video-content-analysis/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install gasserane/personal-skills video-content-analysis2Manually: put the files in place
.github/skills/video-content-analysis/SKILL.md1Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill video-content-analysis -a gemini-cli2Platform CLI
gemini skills install https://github.com/gasserane/personal-skills --path skills/video-content-analysisManually: put the files in place
.devin/skills/video-content-analysis/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add gasserane/personal-skills --skill video-content-analysis -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about video-content-analysis
How do I install video-content-analysis in Claude Code?
Run npx skills add gasserane/personal-skills --skill video-content-analysis -a claude-code, then check ~/.claude/skills/video-content-analysis/SKILL.md.
What does video-content-analysis do?
It turns a local video into a transcript, extracted frames, a manifest, and a Tier 1 BLUF summary. The manifest is ready for follow-up MEL coding and assessment work.
What happens when consent is unclear?
The consent_unclear status blocks downstream analysis. Sensitive recordings use local Whisper transcription.