watch
Watch any video (URL, stream, or local path) via Watch Skill. Downloads, extracts scene-aware deduped frames, OCRs them, transcribes (captions first, then local Whisper — offline by default), indexes everything, and hands the result to the agent. Follow-up questions are answered from the persistent index without re-processing.
- Installs
- 615
- Last 24h
- +20
- Trending rank
- #5844
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/oxbshw/watch-skill --skill watch- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads watch automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
/watch (Watch Skill)
You don't have a video input; this skill gives you one. It is a thin wrapper
around the watch-skill CLI — all logic lives in the engine, so this skill
works identically on every harness (Claude Code, Codex, Cursor, ...).
This is a drop-in upgrade of the classic claude-video /watch skill:
same invocation shape, plus a persistent index (ask answers follow-ups
without re-processing), OCR on frames, scene-aware sampling with perceptual
dedup, local Whisper (offline by default, no API key needed), and THE LOOP
(capture -> critique -> fix -> re-capture) for iterating on your own output.
Step 0 — Preflight (first invocation per session)
watch-skill doctor --json
- Exit 0 → proceed silently. Do NOT announce that setup is fine.
- Non-zero → the JSON lists each failing check with a
fix.doctorauto-bootstraps ffmpeg and yt-dlp into a managed bin dir on Windows/macOS/ Linux; re-run once after it reports fixes. Only involve the user when a check still fails after remediation. - If
watch-skillitself is not on PATH:pip install watch-skill(oruv tool install watch-skill), then re-run the doctor.
No API key is required for acquisition, transcription, OCR, indexing, or
search: transcription falls back to local faster-whisper. Visual synthesis
and verification can use the user's existing Anthropic, OpenAI, Gemini, or
OpenRouter key, or an optional local Ollama model. The agent and provider are
independent; see the configuring-vision skill. Cloud STT is opt-in
(--cloud-stt) and only ever uploads extracted mono audio — the video file
never leaves the machine.
Step 1 — Watch
Parse the user input into source + optional question, then:
watch-skill watch "<source>" [--start T --end T] [--max-frames N] [--transcript-only]
- Any yt-dlp-supported site (1800+), direct media URLs, HLS/DASH manifests
(
--duration 60bounds live streams), and local files all work. --start/--end(SS,MM:SS,HH:MM:SS) switch to dense focused sampling of that window — use for "what happens at 2:30?" questions and for any video over ~10 minutes when the user cares about one section.--timestamps T1,T2,...pins frames at transcript-flagged moments ("look here", "as you can see") that visual selection may miss.--transcript-onlyskips frames entirely (fastest; no video download when captions exist).--max-frames Ntightens the token budget (default: duration-tiered, hard cap 100, max 2 fps).
The report prints an Indexed: video_id ... line, frames with t=MM:SS
timestamps, OCR text, and the transcript.
Step 2 — Read the frames
Read every frame path the report lists, in a single message (parallel Read calls), so you see them together in chronological order.
Step 3 — Answer
Answer from frames + OCR + transcript, citing timestamps. No question → summarize structure, key moments, notable visuals, spoken content.
Follow-ups — use the index, not re-processing
The video is already indexed. For any follow-up question in this or a LATER session:
watch-skill ask <video_id> "<question>" # self-healing answer + evidence
watch-skill search "<phrase>" # across every video ever watched
ask (v0.6) answers text-first with timestamped evidence, a confidence
score, and a ~N tokens saved line. It escalates on its own when unsure
(dense re-sampling, zoom-crop re-OCR) and states plainly when the video
does not clearly show the answer — trust that refusal; do NOT invent an
answer past it. Frame paths are listed only when the engine wants you to
look yourself (or pass --frames); Read them then. Never re-run watch
for a follow-up on an already-indexed video.
If the user corrects one of your video answers, report it so the system learns (locally):
watch-skill lessons add <video_id> "<question>" "<your wrong answer>" "<the correction>"
THE LOOP — iterate on your own output
When the user asks you to fix UI/visual output and verify the fix:
watch-skill loop start "<url-or-screen:-or-file>" "<pass criteria>" [--script '<json steps>']
# ... you apply the suggested fixes ...
watch-skill loop iterate <loop_id>
The critique returns structured issues with timestamps and suggested fixes.
YOU change the code; the loop only observes. On pass it renders a
before/after MP4+GIF proof. watch-skill capture "<target>" records without
critiquing.
Security posture
- The video file itself NEVER leaves the machine. Only extracted mono-16kHz
audio may go to a cloud STT API, and only with explicit
--cloud-stt. - No cookies, no logins — only public data is requested.
- API keys live in env vars /
.env; they are never logged or echoed. - Downloads are cached under
~/.watch-skill/cache(LRU, size-capped).
FAQ
What does the watch skill do?
Watch any video (URL, stream, or local path) via Watch Skill. Downloads, extracts scene-aware deduped frames, OCRs them, transcribes (captions first, then local Whisper — offline by default), indexes everything, and hands the result to the agent. Follow-up questions are answered from the persistent index without re-processing.
How do I install watch?
Run npx skills add https://github.com/oxbshw/watch-skill --skill watch in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/watch/ (personal) or .claude/skills/watch/ (project).
Which AI agents can use watch?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is watch safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains watch?
It is published by oxbshw in oxbshw/watch-skill. It has 615 recorded installs.
More from oxbshw/watch-skill
watching-videos
oxbshw/watch-skill
The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's in this recording". Use this to actually watch the video — download, extract frames, OCR, transcribe, and index it — instead of guessing from the title or asking the user to describe it.
video-memory
oxbshw/watch-skill
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.
asking-with-evidence
oxbshw/watch-skill
The user asks a question about a video that was already watched or indexed — "what did they say about X", "what error code appears", "what happens at 2:30", "does the video show Y". Use this to answer from the persistent index with timestamped evidence and a confidence score instead of re-watching or guessing.
extracting-structure
oxbshw/watch-skill
The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is my intro/hook". Use this for deterministic extraction from the index — chapters with timestamps, a fileable bug report with the exact frame, or a scored hook analysis.
the-loop
oxbshw/watch-skill
The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does the animation glitch". Use this to record the running thing, critique the recording against plain-language pass criteria, and iterate until it passes with before/after proof.
recovering-from-errors
oxbshw/watch-skill
A Watch Skill command failed, video download broke, ffmpeg or yt-dlp is missing, a provider returned an error, local vision stopped, or the user asks "why can't it watch this" or "repair my setup". Use this to diagnose and apply the engine's structured fix before retrying the original operation.
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image