Skip to content

Beta: real launches, updated every morning. Rankings may change while we tune them.

inference-optimisation-skill

Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization

62Today’s rankDown 16 places since yesterday

inference-optimisation-skill launched on 16 November 2026. It ranked #62 on Daily Launch on 20 November 2026 with a Launch Score of 34, from +118 stars today on GitHub. It moved down 16 places from the day before.

Visit site118 stars on GitHub today
Share

What is Inference Optimisation Skill?

It works under a memory cap, and every result has to survive a full-context stability check. It works with Claude Code and any agent that loads SKILL.md-style skills. Any model can also follow it from PROMPT.md. Results from the hill-climbs this skill was distilled from. Every number was measured on the hardware named; see the linked sources for methods and raw data.

From its README on GitHub

Inference Optimisation Skill (inference-optimisation-skill) is a repo by sybil-solutions on GitHub. It is written in Python and released under the MIT license.

How to get Inference Optimisation Skill

Get it from its repository on GitHub.

Daily Launch card for inference-optimisation-skill

Launch timeline

  1. GitHubRepository created

  2. GitHub981 stars in 1 day, ranked #12 on Daily Launch

  3. GitHub+178 stars, ranked #46 on Daily Launch

  4. GitHub+118 stars, ranked #62 on Daily Launch

Launch Score, last 7 days

05010014 Nov: 014 Nov15 Nov: 015 Nov16 Nov: 016 Nov17 Nov: 017 Nov18 Nov: 6818 Nov19 Nov: 3919 Nov20 Nov: 3420 Nov34 today
Launch Score, 0 to 100. Days it was not ranked show 0.

#34 of 226 in the roundup for the week of 16-22 November 2026.

Similar new launches