How do I install the Asking With Evidence skill?

Run npx skillmds@latest add oxbshw/asking-with-evidence 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 Asking With Evidence 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 Asking With Evidence?

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 Asking With Evidence free to use?

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

Who published Asking With Evidence?

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

Asking With Evidence by oxbshw — Agent Skill

Name: Asking With Evidence
Author: oxbshw

Asking With Evidence

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.

oxbshw 3ac154e 2.1 KB Updated Sep 17, 2026

File contents

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.

---name: asking-with-evidencedescription: 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.license: MIT---# Asking with evidenceEvery watched video sits in a persistent index. Questions about it areanswered from that index — text first, frames only when needed — withtimestamps, a confidence score, and an honest refusal when the videodoes not show the answer. Never re-run a watch for a follow-up.## Answer a question```bashwatch-skill ask <video_id-or-original-url> "<question>"```Any language works; the answer comes back in the language of thequestion. 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:```bashwatch-skill ask <video_id> "what is on screen around 2:30?"```The answer engine pulls frames, transcript and OCR around the moment itresolves. Agents on MCP have a dedicated `get_moment` tool that takes anexplicit timestamp and window; the CLI answers the same question through`ask`.## Don't know which video? Search them all```bashwatch-skill search "<phrase>"```Hybrid keyword + semantic search across every video ever watched, withper-script normalization (Arabic folding, CJK segmentation, Thaisegmentation). Follow a hit with `ask` or `moment` on that video.## When the user corrects youReport it so the next answer is better — see the`learning-from-mistakes` skill.

Frequently asked questions