pufferlib
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.
Overview
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.
Source: https://github.com/DenDen047/claude-scientific-skills · MIT LICENSE · © 2025 K-Dense Inc.
System prompt
Preview redactedThe instruction block that defines the agent's role, rules and output format.
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████User prompt template
Fill in the variables and send it to run the skill: {{variables}}
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████
████████████████████████████████████████████████████████████████Variables
| Name | Required | Description | Example |
|---|
Full skill configuration
Redacted previewThe standard .aiskill file in JSON and YAML.
{
"format": "aiskill/v1",
"skill": {
"name": "pufferlib",
"slug": "pufferlib",
"version": "1.0.0",
"description": "High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.",
"category": "Research",
"tags": [
"research-science",
"agents",
"performance"
],
"platforms": [
"chatgpt",
"claude-code",
"cursor"
],
"tested_environment": "Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and compatible agents",
"license": "MIT LICENSE"
},
"prompts": {
"system": "████████████████████████████████████████████████████████████████████████████████████████████████",
"user_template": "██████████"
},
"variables": [],
"install": {
"steps": [
{
"title": "Download & unzip",
"detail": "Download the .zip package from SkillVault and unzip it. The pufferlib/ folder contains SKILL.md plus any companion scripts, references and assets."
},
{
"title": "Copy into your agent skills directory",
"detail": "Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code), .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or reload the session."
},
{
"title": "Use it",
"detail": "Describe the task in natural language; the agent loads the skill automatically when the request matches the skill description."
}
]
},
"usage": {
"steps": []
},
"metadata": {
"author": "SkillVault",
"source": "https://skillvault.top/skills/pufferlib",
"exported_at": "2026-11-03T07:41:23.670Z"
}
}format: aiskill/v1
skill:
name: pufferlib
slug: pufferlib
version: 1.0.0
description: >-
High-performance reinforcement learning framework optimized for speed and scale. Use when you
need fast parallel training, vectorized environments, multi-agent systems, or integration with
game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard
implementations. For quick prototyping or standard algorithm implementations with extensive
documentation, use stable-baselines3 instead.
category: Research
tags:
- research-science
- agents
- performance
platforms:
- chatgpt
- claude-code
- cursor
tested_environment: >-
Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and
compatible agents
license: MIT LICENSE
prompts:
system: ████████████████████████████████████████████████████████████████████████████████████████████████
user_template: ██████████
variables: []
install:
steps:
- title: Download & unzip
detail: >-
Download the .zip package from SkillVault and unzip it. The pufferlib/ folder contains
SKILL.md plus any companion scripts, references and assets.
- title: Copy into your agent skills directory
detail: >-
Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code),
.codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or
reload the session.
- title: Use it
detail: >-
Describe the task in natural language; the agent loads the skill automatically when the
request matches the skill description.
usage:
steps: []
metadata:
author: SkillVault
source: https://skillvault.top/skills/pufferlib
exported_at: "2026-11-03T07:41:23.670Z"
Installation guide
- 1
Download & unzip
Download the .zip package from SkillVault and unzip it. The pufferlib/ folder contains SKILL.md plus any companion scripts, references and assets.
- 2
Copy into your agent skills directory
Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code), .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or reload the session.
- 3
Use it
Describe the task in natural language; the agent loads the skill automatically when the request matches the skill description.
How to use
Platform compatibility
ChatGPT GPTs
OpenAI
Paste the system prompt into the GPT "Instructions" field and keep the user template as your starter message.
Official docsClaude Code
Anthropic
Save the exported .aiskill JSON as a skill file in your project or paste the system prompt into CLAUDE.md / a slash-command markdown file.
Official docsCursor
Anysphere
Copy the system prompt into .cursor/rules/*.mdc (or Project Rules in Settings) and reference the user template in your agent prompts.
Official docsRelated skills
stable-baselines3
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
database-lookup
Search 78 public scientific, biomedical, materials science, and economic databases via their REST APIs and return structured JSON results. Covers physics/astronomy (NASA, NIST, SDSS, SIMBAD, Exoplanet Archive), earth/environment (USGS, NOAA, EPA, OpenWeatherMap), chemistry/drugs (PubChem, ChEMBL, DrugBank, FDA, KEGG, DailyMed, ZINC, BindingDB), materials science (Materials Project, COD), biology/genomics (Reactome, BRENDA, UniProt, STRING, Ensembl, NCBI Gene, GEO, GTEx, PDB, AlphaFold, InterPro, ChEBI, BioGRID, Gene Ontology, QuickGO, NCBI Protein/Taxonomy, dbSNP, SRA, ENA, gnomAD, UCSC Genome, ENCODE, JASPAR, MouseMine, PRIDE, LINCS L1000, Human Protein Atlas, Human Cell Atlas, RummaGEO, Metabolomics Workbench, EMDB, Addgene), disease/clinical (COSMIC, Open Targets, ClinPGx, ClinicalTrials.gov, OMIM, ClinVar, GDC/TCGA, cBioPortal, DisGeNET, GWAS Catalog, Monarch, HPO), regulatory (FDA, USPTO, SEC EDGAR), economics/finance (FRED, BEA, BLS, Federal Reserve, World Bank, ECB, US Treasury, Alpha Vantage, Data Commons), and demographics (US Census, Eurostat, WHO). Use this skill whenever the user wants to look up compounds, drugs, proteins, genes, pathways, enzymes, gene expression, variants, clinical trials, patents, SEC filings, economic indicators, crystal structures, astronomical objects, earthquakes, weather, or any data from a public database API. Also trigger when the user mentions any database by name or asks about molecular properties, drug-target interactions, binding affinities, protein interactions, pathway membership, pharmacogenomics, economic time series, materials properties, commercially available compounds, virtual screening, compound purchasability, chemical libraries, building blocks, cancer genomics, somatic mutations, tumor mutation profiles, nucleotide sequences, genome assemblies, sequencing reads, ENA accessions, INSDC data, or wants to cross-reference entities across sources.
dhdna-profiler
Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks "what's my thinking style", "analyze how this person reasons", "cognitive profile", "thinking pattern", "DHDNA", "digital DNA", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.