agentleFS
michaelnealemichaelneale/mesh-llm/.agents/skills/skippy-model-package/SKILL.md

skippy-model-package

Skill3.8k starsChanged 20 days agoApache-2.0View on GitHub

Use this skill when inspecting GGUF models, planning layer ranges, generating or validating skippy package artifacts, fake packages for direct GGUFs, materialized stage cache behavior, or GGUF writer integration.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for model inspection, package planning, stage materialization, and cache behavior.

    line 10
  2. Distinctive:

    Check current package names before running commands:

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

skippy-model-package

Use this skill for model inspection, package planning, stage materialization, and cache behavior.

Ownership

Rust owns package manifests, topology planning inputs, cache policy, and mesh model-storage integration. The patched llama/skippy ABI owns GGUF tensor inspection and GGUF artifact writing.

The native package ABI is declared in include/skippy/model_package.h and implemented in src/skippy/model_package.cpp. Keep model inspection, tensor filtering, metadata copying, and package writing in that module; do not grow src/skippy.cpp with package behavior.

Direct GGUF loading in mesh should materialize as a fake package identity in the skippy runtime so the split-serving path can use the same package-backed stage machinery as Hugging Face packages.

Commands

Check current package names before running commands:

just with-lld cargo metadata --no-deps --format-version 1 | jq -r '.packages[].name' | sort

Useful current checks in this repo:

just with-lld cargo test -p skippy-runtime --lib
just with-lld cargo test -p skippy-topology --lib
just with-lld cargo test -p mesh-llm-host-runtime --lib inference::skippy

For a published layer package, prefer package-local diagnostics before a live split smoke. On macOS or Linux, just release-runtime-build cpu builds the skippy-package-builder Cargo binary and packages it with its native libraries. Replace <runtime-id> with the generated directory under dist/native-runtimes:

just with-lld cargo test -p skippy-package-builder --bin skippy-package-builder
just release-runtime-build cpu
package_builder="dist/native-runtimes/<runtime-id>/tools/skippy-package-builder"
"$package_builder" preflight <package-dir> --stages 2

Cache Policy

Materialized stages are derived cache. Model storage commands may evict materialized stage artifacts without deleting the source model/package. Preserve pinned materialized artifacts unless the command explicitly asks for a stronger cleanup.

Download now (ZIP)

Trending

Quiet since April.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 4 mentionsApr 2026: 14 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the michaelneale/mesh-llm repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about michaelneale/mesh-llm

The biggest 5 of 18 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 18

Talked about on GitHub, Bluesky and Hacker News (18 times).

On GitHub · 15

10 more on GitHub

On Hacker News · 1

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.