asking-with-evidence — Claude Code skill: how to install and use
Answers questions about previously indexed videos using persistent transcripts, OCR, and timestamps. It prevents re-watching and reports clear evidence or honest refusals.
npx skills add oxbshw/watch-skill --skill asking-with-evidence -a claude-codeWhat asking-with-evidence does
This skill queries a persistent index of analyzed videos via the watch-skill CLI. Instead of re-watching the media, the engine inspects text first and loads frames only when needed. It answers in the language of the prompt and cites exact timestamps as evidence. When a video lacks the requested detail, the system returns a direct refusal so the agent will not fabricate facts.
The skill requires Bash and Read permissions to execute commands and view image files. If confidence drops, the CLI automatically escalates by pulling dense frame samples, cropping for OCR, or using a stronger model. Frame paths stay hidden unless the model requests them or the user forces display with --frames.
When the exact video identifier is forgotten, watch-skill search scans across all indexed files using hybrid keyword and semantic retrieval. That prevents wasteful duplicate indexing runs on large video files.
What it helps with
- Retrieve exact timestamps for quotes or events in watched videos
- Read on-screen error codes using targeted moment OCR
- Verify whether a topic appeared without reprocessing the file
- Locate indexed recordings across the local archive via hybrid search
Example prompts for the agent
- Ask
watch-skill ask <video_id>what error code appears on screen - Ask
watch-skill ask <video_id>what was said about database migrations - Search all recordings using
watch-skill searchfor connection timeout errors
How to install asking-with-evidence
1Skills CLI (Vercel)
npx skills add oxbshw/watch-skill --skill asking-with-evidence -a claude-code2Manually: put the files in place
~/.claude/skills/asking-with-evidence/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/asking-with-evidence/
1Skills CLI (Vercel)
npx skills add oxbshw/watch-skill --skill asking-with-evidence -a codex2Manually: put the files in place
.agents/skills/asking-with-evidence/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add oxbshw/watch-skill --skill asking-with-evidence -a cursor2Manually: put the files in place
.cursor/skills/asking-with-evidence/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install oxbshw/watch-skill asking-with-evidence2Manually: put the files in place
.github/skills/asking-with-evidence/SKILL.md1Skills CLI (Vercel)
npx skills add oxbshw/watch-skill --skill asking-with-evidence -a gemini-cli2Platform CLI
gemini skills install https://github.com/oxbshw/watch-skill --path skills/asking-with-evidenceManually: put the files in place
.devin/skills/asking-with-evidence/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add oxbshw/watch-skill --skill asking-with-evidence -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about asking-with-evidence
How do I install asking-with-evidence in Claude Code?
Run npx skills add oxbshw/watch-skill --skill asking-with-evidence -a claude-code.
What does asking-with-evidence do?
It queries a persistent index of previously watched videos to answer questions using timestamps, transcripts, and OCR without re-running the video pipeline.
What permissions does asking-with-evidence require?
It requires Bash and Read permissions to run the watch-skill CLI and read extracted frames from disk.
Source text
SKILL.md · MIT
--- name: asking-with-evidence version: "1.4.3" description: 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 user-invocable: true allowed-tools: Bash, Read --- # 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 ```bash 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: ```bash 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 ```bash 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.
© oxbshw · MIT · oxbshw/watch-skill
