h3-av SKILL.md skillA
h3-av from banodoco/astrid-agent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add banodoco/astrid-agent/h3-av@git:20261014.71d43e0Pins git:20261014.71d43e0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- banodoco/astrid-agent
- Path
astrid/packs/h3_av/docs/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261014.71d43e0, committed Oct 14, 2026
- Size
- 14,466 bytes
- Repository stars
- 17
- License
- a license file GitHub does not identify
Request-driven MiniMax H3 audiovisual transformations with explicit video/audio scopes, references, and approval evidence.
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
# H3 audiovisual transformations For the short pack contract overview, see [README.md](../README.md). Action-specific notes remain linked beside their v3 entrypoints: [prepare](../actions/prepare/STAGE.md), [compile](../actions/compile/STAGE.md), [compose](../actions/compose/STAGE.md), [verify](../actions/verify/STAGE.md), and [transform](../actions/transform/STAGE.md). Use `h3_av.transform` when the desired result is a generated or edited H3 video/audio candidate. The agent writes one request document; the pack resolves assets and time ranges, compiles the selected H3 workflow, optionally executes it through `vibecomfy.run`, composes protected material, and emits verification evidence. The pack is an abstraction over the existing H3 workflow, not a new media database or scheduler. This is the one canonical path: ```text request → prepare → compile → validate → run → compose → verify → final receipt ``` The `validate` stage checks canonical bundle and graph structure offline, with explicit Python consent. Its `canonical_bundle_structural` report defers runtime and target-schema checks to `vibecomfy.run`; it does not establish runtime …
Read the whole file at its exact version.
How to install
mdr add banodoco/astrid-agent/h3-av@sha256:6670fe3a0ef01161The line at the top of this page pins the label git:20261014.71d43e0, 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_dyyj23imqzdyxnzy)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 14, 2026.
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 (14466 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
banodoco/astrid-agent · 17 stars · license a license file GitHub does not identify · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dyyj23imqzdyxnzy GET https://markdownregistry.com/api/v1/resolve?ref=banodoco/astrid-agent/h3-av GET https://markdownregistry.com/api/v1/blob/6670fe3a0ef01161e37e5fd3c4702f18ad4563052f47d5186c17366f7c2f7845
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.