# Skippy Spec Bench

> Skippy Spec Bench 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 testing or benchmarking target/draft GGUF pairs for speculative decoding compatibility, tokenizer agreement, draft acceptance rate, or staged verification behavior.

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

## SKILL.md

# skippy-spec-bench

Use this skill for target/draft speculative compatibility work.

## What It Checks

- Target and draft tokenization agreement.
- Baseline target decode versus draft-verified decode.
- Draft acceptance/rejection behavior.
- Batched verification and checkpoint/restore behavior.
- Recurrent-state implications for rollback.

## Repo Notes

The old source repo used a standalone `llama-spec-bench` crate. It may not be
present in this mesh checkout yet, so verify available packages before running
commands:

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

If the spec bench is imported, keep it as a diagnostics/benchmark tool. Do not
make normal mesh serving depend on it.

---

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