video-memory
Video Memory maintains a searchable index of every video watched on your machine, preserving frames, transcripts, and extracted answers in persistent storage. Search across all indexed videos by keyword or semantic meaning, drill into specific moments, or synthesize answers from insights spanning multiple videos. Batch-import playlists or folders to build your video library quickly.
Video Memory searches all previously watched videos in a persistent local index to find specific content, transcripts, and answers across sessions.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-12
Video Memory searches all previously watched videos in a persistent local index to find specific content, transcripts, and answers across sessions. Video Memory maintains a searchable index of every video watched on your machine, preserving frames, transcripts, and extracted answers in persistent storage. Search across all indexed videos by keyword or semantic meaning, drill into specific moments, or synthesize answers from insights spanning multiple videos. Batch-import playlists or folders to build your video library quickly.
Use it when
- Yes.
- Video Memory preserves frames and transcripts for every indexed video.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
oxbshw/watch-skill/video-memory · 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 search my videos for that error message?
Video Memory indexes all your watched videos and their transcripts, letting you search across them by keyword. When you search for an error message, Video Memory scans transcripts and extracted text to find matching videos, then displays results with timestamps so you can jump directly to the relevant moment.
Can Video Memory retrieve information spanning multiple videos?
Yes. Video Memory synthesizes insights across multiple indexed videos, so you can ask questions like "what did we decide about pricing in those meetings" and get answers drawn from relevant moments across all your recorded sessions. It builds connections between related content.
How do I locate a specific timestamp in a video by keyword?
Video Memory preserves frames and transcripts for every indexed video. Search by keyword or topic, and the skill returns matching videos with precise timestamps, letting you jump directly to the moment you're looking for without scrubbing through hours of footage.
What does Video Memory store to make videos searchable?
Video Memory maintains a persistent library of video transcripts, extracted frames, and synthesized answers. It preserves this index locally on your machine, enabling fast recall and semantic search across all your watched videos without needing to re-process them each time.
Can I batch-index multiple recordings or playlists?
Yes. Video Memory supports batch-importing folders or playlists to build your searchable video library quickly. Once indexed, all recordings become instantly searchable by keyword, semantic meaning, or OCR text, letting you find decisions, solutions, and discussions across your entire collection.
Does Video Memory search video transcripts across sessions?
Video Memory is built to search transcripts across all your indexed sessions and recordings. Whether you're looking for a specific discussion, decision, or explanation that happened weeks ago, semantic and keyword search work across your entire persistent video library.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
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 +
(truncated - see the full file via the links below)
File tree — 1 file
adapters/claude-skill/skills/video-memory/SKILL.md
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 › “Search across all previously watched videos to find specific content or answers”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Watch Skill processes any video—URLs, local files, streams, recordings—by extracting frames, running OCR, and transcribing audio into a unified searchable index. Query the index directly instead of re-watching, and batch-process playlists or folders in one pass.
Pull structured data from videos you've already watched: titled chapters with timestamps for long content, pinpointed bug reports with error frames and OCR text, or opening-hook analysis scored across attention, pacing, visuals, and on-screen text. All answers come straight from the persistent index with no extra model calls.
When a video answer goes wrong, report the correction and Watch Skill records it as a lesson stored locally. The system classifies the mistake, injects it into similar future questions, and can re-ask the original question to verify the fix worked. Check what's been learned or review token savings anytime.
Query any video you've already watched to get answers backed by timestamps and confidence scores, drawn from a persistent index rather than re-processing. The skill refuses unclear answers honestly and escalates automatically when uncertain, saving tokens in the process.
Watch Skill processes videos locally by extracting scene-aware frames, running OCR on text within them, and transcribing audio via offline Whisper or captions. It builds a searchable index so follow-up questions are answered without re-processing the video. No API keys required for core features; vision and STT are optional and configurable.
Turn your video analysis into a self-contained HTML file that anyone can open without needing Watch Skill or internet access. The page bundles frames, transcript, OCR text, and all your cached Q&A with timestamped evidence in one shareable document—ideal for bug tickets, code reviews, or handing off findings to teammates.
More skills recovering-from-errors (MIT) · Youtube Summarizer (unlicensed)