spark-local-media-generation SKILL.md skillA
spark-local-media-generation from hojiahao/cineloom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hojiahao/cineloom/spark-local-media-generation@v0.3.0Pins v0.3.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hojiahao/cineloom
- Path
.agents/skills/spark-local-media-generation/SKILL.md- Versions recorded
- 7
- Latest version
- v0.3.0, committed Oct 17, 2026
- First version recorded
- Sep 21, 2026
- Size
- 7,513 bytes
- Repository stars
- 8
- License
- a license file GitHub does not identify
Generate a product hero still, storyboard frames anchored to it, and native-1080p video clips on the local DGX Spark with the cinefoundry CLI (ComfyUI running Qwen-Image, Qwen-Image-Edit, LTX-2.5 Fast NVFP4 by default or Wan2.2, and RIFE interpolation to the delivery frame rate) instead of a cloud API. Use when product shots, storyboard frames or shot clips must be produced, when material is confidential or unreleased, or when choosing between local and cloud generation.
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
# Spark local media generation Hero still first, frames second, clips last, interpolation after. Each step is anchored to the one before it, so product identity is decided where a retry costs seconds, not minutes. The default film is a 30-second master: six storyboard shots, so six frames and six 5-second clips, generated at native 1080p and interpolated to 60 fps. ## Before every GPU phase 1. Check memory with `spark-model-scheduler`. One diffusion family resident at a time; `cinefoundry mem free` when switching between them. The harness does this at every phase boundary (`enterPhase`) and puts the language models to sleep for frames and clips. 2. **Evict the page cache of the model files.** On DGX Spark CUDA can only allocate memory that is truly free (`MemFree`), not what Linux counts as available: `MemAvailable` includes the page cache, and every model file just read from NVMe - tens of GB of safetensors - sits there looking reclaimable. With a warm cache a video model load can fail, or sample with far less room than `cinefoundry mem status` suggests. Compare the two, and drop the cache when the gap is large: ```bash …
Read the whole file at its exact version.
How to install
mdr add hojiahao/cineloom/spark-local-media-generation@sha256:261a1f833aa54839The line at the top of this page pins the label v0.3.0, 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_ot54e2k7xz6obvvy)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 21, 2026 and Oct 17, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.3.0 latest | 2026-10-17 | 99600a5 | 7,513 B | A | view · diff |
| v0.3.0 | 2026-10-17 | c8e035f | 7,186 B | A | view · diff |
| v0.2.0 | 2026-10-17 | 9f7200f | 5,100 B | A | view · diff |
| v0.2.0 | 2026-10-17 | cce7e33 | 5,080 B | A | view · diff |
| v0.2.0 | 2026-10-17 | 18446e4 | 5,080 B | A | view · diff |
| v0.1.0 | 2026-09-21 | 9ca92b5 | 4,315 B | A | view · diff |
| v0.1.0 | 2026-09-21 | d199e79 | 2,710 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 (7513 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
hojiahao/cineloom · 8 stars · license a license file GitHub does not identify · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ot54e2k7xz6obvvy GET https://markdownregistry.com/api/v1/resolve?ref=hojiahao/cineloom/spark-local-media-generation GET https://markdownregistry.com/api/v1/blob/261a1f833aa54839776d5b9bd60a043bd3d205675d3252a437f2e0b33d17367c
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.