How do I install the Video Memory skill?

Run npx skillmds@latest add oxbshw/video-memory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Video Memory safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Video Memory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Video Memory free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Video Memory?

oxbshw (@oxbshw) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Video Memory by oxbshw — Agent Skill

Name: Video Memory
Author: oxbshw

Video Memory

The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a question that spans several videos. Use this to search and answer from the persistent cross-video index instead of saying you don't remember.

oxbshw 0b7e48d 2.2 KB Updated Sep 17, 2026

File contents

Video memory

Every video ever watched on this machine is still here — frames, OCR, transcripts, and past answers, in one persistent index under ~/.watch-skill/. You never have to say "I don't remember that video." Sessions don't expire it; watching more videos makes it more useful.

What's in the library?

watch-skill list

Every indexed video: id, title, duration, when it was analyzed. Check here before watching anything — it may already be in memory from a previous session.

Find something across all of it

watch-skill search "<phrase or keywords>"

Hybrid keyword + semantic search across every video, any language (Arabic folding, CJK and Thai segmentation are handled). Hits come back with video + timestamp; follow up on a hit with:

watch-skill ask <video_id> "<the user's actual question>"
watch-skill ask <video_id> "what is on screen at <timestamp>?"

Questions that span videos

"What did we decide about the pricing page across those meetings?" — questions no single video answers go to the library synthesizer:

watch-skill library ask "<the question>"

It answers from distilled notes across every indexed video, drills into real evidence, and cites video + timestamp for each finding. When it says the library does not clearly answer, trust that — do not stitch a guess together from weak search hits. watch-skill library overview shows what the library knows (videos, note counts, entities recurring across videos).

For "which video showed X" (locate, not synthesize), plain search is the right tool; then ask the hit video.

Batches build memory fast

A playlist or a folder of recordings goes in as one call — watch-skill batch "<playlist-or-folder>" — and the whole set becomes searchable memory (see watching-videos).

---name: video-memorydescription: The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a question that spans several videos. Use this to search and answer from the persistent cross-video index instead of saying you don't remember.license: MIT---# Video memoryEvery video ever watched on this machine is still here — frames, OCR,transcripts, and past answers, in one persistent index under`~/.watch-skill/`. You never have to say "I don't remember that video."Sessions don't expire it; watching more videos makes it more useful.## What's in the library?```bashwatch-skill list```Every indexed video: id, title, duration, when it was analyzed. Checkhere before watching anything — it may already be in memory from aprevious session.## Find something across all of it```bashwatch-skill search "<phrase or keywords>"```Hybrid keyword + semantic search across every video, any language(Arabic folding, CJK and Thai segmentation are handled). Hits come backwith video + timestamp; follow up on a hit with:```bashwatch-skill ask <video_id> "<the user's actual question>"watch-skill ask <video_id> "what is on screen at <timestamp>?"```## Questions that span videos"What did we decide about the pricing page across those meetings?" —questions no single video answers go to the library synthesizer:```bashwatch-skill library ask "<the question>"```It answers from distilled notes across every indexed video, drills intoreal evidence, and cites video + timestamp for each finding. When itsays the library does not clearly answer, trust that — do not stitch aguess together from weak search hits. `watch-skill library overview`shows what the library knows (videos, note counts, entities recurringacross videos).For "which video showed X" (locate, not synthesize), plain `search` isthe right tool; then `ask` the hit video.## Batches build memory fastA playlist or a folder of recordings goes in as one call —`watch-skill batch "<playlist-or-folder>"` — and the whole set becomessearchable memory (see `watching-videos`).

Frequently asked questions