asking-with-evidence SKILL.md skillA
asking-with-evidence from oxbshw/watch-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add oxbshw/watch-skill/asking-with-evidence@v1.4.3Pins v1.4.3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- oxbshw/watch-skill
- Path
skills/asking-with-evidence/SKILL.md- Versions recorded
- 8
- Latest version
- v1.4.3, committed Sep 8, 2026
- First version recorded
- Aug 19, 2026
- Size
- 2,210 bytes
- Repository stars
- 508
- License
- MIT
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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?" ``` …
Read the whole file at its exact version.
How to install
mdr add oxbshw/watch-skill/asking-with-evidence@sha256:a214879ee6e9e0ecThe line at the top of this page pins the label v1.4.3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_q42wswaq2qsrnda3)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Aug 19, 2026 and Sep 8, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.4.3 latest | 2026-09-08 | f1317c8 | 2,210 B | A | view · diff |
| v1.4.2 | 2026-09-08 | b6ee470 | 2,210 B | A | view · diff |
| v1.4.1 | 2026-09-07 | 8df6d4d | 2,210 B | A | view · diff |
| v1.4.0 | 2026-09-05 | 1a53bae | 2,210 B | A | view · diff |
| v1.4.0rc1 | 2026-09-02 | ab36fc4 | 2,213 B | A | view · diff |
| v1.3.0rc2 | 2026-08-21 | 94c2d16 | 2,213 B | A | view · diff |
| v1.3.0rc2 | 2026-08-19 | db22dfd | 2,034 B | A | view · diff |
| v1.3.0rc1 | 2026-08-19 | ba68f9f | 2,034 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2210 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
oxbshw/watch-skill · 508 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q42wswaq2qsrnda3 GET https://markdownregistry.com/api/v1/resolve?ref=oxbshw/watch-skill/asking-with-evidence GET https://markdownregistry.com/api/v1/blob/a214879ee6e9e0ec11317a7ca62761596de613fb9f101833a6ebb0b7c1ea49ae
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.