Skill All skills & plugins / Scientific Agent Skills (K-Dense)
pufferlib
Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Covers the native 5.0 build and environment API, published 3.0.0 Gymnasium/PettingZoo adaptation, and a pinned historical 4.0 profile.
- Type
- Skill by K-Dense Inc.
- Catalog
- Scientific Agent Skills (K-Dense)
- Source
- K-Dense-AI/scientific-agent-skills/skills/pufferlib (16 files scanned)
- Install and details
- Agent Skills Index entry
- License
- MIT (SKILL.md frontmatter)
- Signals
- Pre-approved shellBundled scripts
Pre-approved tools
Shell (any command). Tools listed in allowed-tools (or an agent's tools) can be used without a permission prompt while the skill is active, depending on your agent and settings.
| Kind | Tools |
|---|---|
| read/search | ReadGrep |
| shell, any command | BashPython |
Declared in pufferlib/SKILL.md.
Hooks
No hooks.
MCP servers and apps
None.
Bundled code
9 code files (Python):
pufferlib/scripts/inspect_checkpoint.pypufferlib/scripts/__init__.pypufferlib/scripts/env_template.pypufferlib/scripts/benchmark_vectorization.pypufferlib/scripts/validate_plan.pypufferlib/scripts/repro_plan.pypufferlib/scripts/_common.pypufferlib/scripts/train_template.pypufferlib/scripts/env_contract_validator.py
Network calls
No HTTP or socket call pattern found in the code.
Starts other programs
No subprocess, exec or eval pattern found.
Credentials referenced
No key, token or secret environment variable found in code or MCP config.
Static scan of commit 5f2bc03 on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.