yt-ingestion skillA
yt-ingestion is agent-read markdown (skill) from naveedharri/benai-skills: Fetch a YouTube video's raw artifacts (video file, transcript, word-level timestamps, thumbnail, metadata) without committing to a downstream workflow. Use when the user wants just the ingestion output for debugging, scratch work, or feeding into another tool. Triggers on phrases like "get me the transcript", "download this video", "fetch artifacts for", "ingest this YouTube URL"..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# yt-ingestion: standalone artifact fetcher
When triggered, invoke the `yt-ingestion-agent` sub-agent with:
- `youtube_url`: the URL from the user's message
- `output_dir`: by default, `Team/BenAI/Profiles/Milan/Daily/{today}/yt-ingestion-{video-id}/`. If the user specifies an output directory, use theirs.
Surface the resulting manifest path to the user when done. If the agent surfaces a 3-option choice (e.g., 1080p blocked), present those options to the user and pass their selection back.
## Profile boundary
Output writes to `Profiles/Milan/`. See [[yt-pipeline SPEC|SPEC.md]] for the full invariant.
## When NOT to use this skill
- The user wants a full course package: use `yt-to-course` instead.
- The user wants a community announcement post: use `yt-to-community` instead.
For details on the fallback chain, see [[fallback-strategies]].Read the whole file at its exact version.
How to install
mdr add naveedharri/benai-skills/yt-ingestion@git:20260916.a3b1e15mdr add naveedharri/benai-skills/yt-ingestion@sha256:fa5a77af1ebed774Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_lkruj4liayftkshe)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260916.a3b1e15 latest | 2026-09-16 | a3b1e15 | 1,312 B | A | view · diff |
| git:20260911.3860544 | 2026-09-11 | 3860544 | 1,281 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 (1312 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
naveedharri/benai-skills · 65 stars · license MIT · pushed 2026-09-16 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_lkruj4liayftkshe GET https://markdownregistry.com/api/v1/resolve?ref=naveedharri/benai-skills/yt-ingestion GET https://markdownregistry.com/api/v1/blob/fa5a77af1ebed774866601a1e03248f98f52e689b8a2d9ce4837598941802386
Your agent 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.