mcpField
A
asking-with-evidence

asking-with-evidence

github.com/oxbshwProductivity533532 installsUpdated 7w ago
Repository

About asking-with-evidence

A video-questioning skill for agents that answers from a persistent index of previously analyzed videos. It provides timestamped evidence, confidence scores, and refusals when the video does not support an answer.

Key features

  1. 01Answer from the existing video index
  2. 02Return timestamps and confidence scores
  3. 03Refuse unsupported answers
  4. 04Search videos with hybrid keyword and semantic matching
  5. 05Inspect frames around a requested moment

Use cases

  1. 01Ask follow-up questions without reprocessing a video
  2. 02Find a clip across previously watched videos
  3. 03Check what appears or is said at a given time

MCP support

Agents using MCP can call a dedicated get_moment tool with a timestamp and time window. The CLI provides moment answers through ask.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/oxbshw/watch-skill --skill asking-with-evidence

After installing, type/asking-with-evidencein Claude Code to confirm it loaded.

Details

From the project README

Asking with evidence

Every watched video sits in a persistent index. Questions about it are answered from that index — text first, frames only when needed — with timestamps, a confidence score, and an honest refusal when the video does not show the answer. Never re-run a watch for a follow-up.

Answer a question

watch-skill ask <video_id-or-original-url> "<question>"

Any language works; the answer comes back in the language of the question. The engine escalates on its own when unsure (dense re-sampling, zoom-crop re-OCR, stronger model) and prints a ~N tokens saved line.

Three rules for reading the result:

  • Cite the timestamps it gives you; they are real evidence, not decoration.
  • Trust the refusal. When it says the video does not clearly show the answer, that is the answer. Do not invent one past it.
  • Frame paths are listed only when the engine wants you to look yourself — Read them then (or force with --frames).

"What happens at 2:30?"

Moment questions get a dense window, not a whole-video ask:

watch-skill ask <video_id> "what is on screen around 2:30?"

The answer engine pulls frames, transcript and OCR around the moment it resolves. Agents on MCP have a dedicated get_moment tool that takes an explicit timestamp and window; the CLI answers the same question through ask.

Don't know which video? Search them all

watch-skill search "<phrase>"

Hybrid keyword + semantic search across every video ever watched, with per-script normalization (Arabic folding, CJK segmentation, Thai segmentation). Follow a hit with ask or moment on that video.

When the user corrects you

Report it so the next answer is better — see the learning-from-mistakes skill.

Comments

Markdown supported