# Skippy Correctness

> Skippy Correctness is an Agent Skill for testing & quality published in the Mesh-LLM/mesh-llm repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use this skill when validating skippy staged execution against full-model execution, adding model families, changing split boundaries, testing activation wire dtypes, or diagnosing mismatch behavior.

- Skill name: `skippy-correctness`
- Category: [Testing & Quality](https://www.openparable.com/skill/testing-quality/1)
- Source: https://github.com/Mesh-LLM/mesh-llm/blob/HEAD/.agents/skills/skippy-correctness/SKILL.md
- Repository: Mesh-LLM/mesh-llm (2,502 GitHub stars when collected)

## SKILL.md

# skippy-correctness

Use this skill when staged execution must be proven equivalent to full-model
execution.

## What To Check

- Single-stage direct GGUF parity.
- Two-stage boundary parity for representative split points.
- Multi-stage chain parity for package-backed serving.
- Selected-device and pinned-device behavior.
- Activation wire dtype exactness (`f16` by default, `q8` only with evidence).
- Recurrent/hybrid family behavior and topology affinity.
- Multimodal projector handling once native media execution is wired.

## Commands

First check whether standalone correctness crates have been imported:

```bash
cargo metadata --no-deps --format-version 1 | jq -r '.packages[].name' | sort
```

Current mesh-level checks:

```bash
cargo test -p skippy-runtime --lib
cargo test -p skippy-server --lib
cargo test -p mesh-llm-host-runtime --lib inference::skippy
cargo test -p mesh-llm-host-runtime --lib
```

If `skippy-correctness` is imported later, prefer that harness for model-backed
exactness gates instead of adding one-off tests.

---

Source: https://www.openparable.com/skill/testing-quality/skippy-correctness (OpenParable). Cite the canonical URL above.
