Skip to main content
pufferlibby K-DenseDevelopmentGitHub stars: 47.7k

Pufferlib skill: what it does and how to install it

Guides PufferLib reinforcement-learning work across versions, covering environments, vectorisation, policies, training plans, evaluation and checkpoint review.

Summary generated from the skill's documentation.

Install

$ npx skills add K-Dense-AI/scientific-agent-skills --skill pufferlib

Run it in a terminal. If your agent is already running, start a new session so it picks the skill up.

About this skill

What it does. Selects the appropriate PufferLib 5.0, 3.0 or pinned 4.0 API, then checks environment contracts, vectorisation, policy shapes and resource limits. It generates validated training plans, runs bounded synthetic benchmarks, and hashes checkpoints without deserialising them.

When to use it. Apply it when building, adapting, evaluating or safely reviewing PufferLib reinforcement-learning environments and training workflows. Its bundled planner does not launch training, and synthetic checks do not establish that PufferLib is installed or that learning succeeds.

History

Repo stars

47.7kAbout +18.9k since 9 Jul 2026

Before 1 Oct 2026 the curve is estimated from public event data.

Stars are counted for the whole repository, which holds 74 skills.

Show as a table
Repo stars by day
DateRepo stars
5 Oct 202647,652
4 Oct 202647,541
3 Oct 202647,444
2 Oct 202647,351
1 Oct 202647,271
24 Sept 2026 (estimated)46,976
17 Sept 2026 (estimated)46,257
10 Sept 2026 (estimated)41,836
3 Sept 2026 (estimated)30,545
27 Aug 2026 (estimated)29,347
20 Aug 2026 (estimated)29,160
13 Aug 2026 (estimated)29,027
6 Aug 2026 (estimated)28,947
30 Jul 2026 (estimated)28,894
23 Jul 2026 (estimated)28,894
16 Jul 2026 (estimated)28,841
9 Jul 2026 (estimated)28,708

Installs

1.7k

Tracking since . A chart appears once there are 7 days of data.

Installs via skills.sh

Similar skills