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.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and highly actionable with executable code, a sequenced workflow including validation, and clean progressive disclosure into verified reference and script files. Minor conciseness padding and a missing explicit fix-retry loop keep two dimensions at 4.

Suggestions

Trim conceptual explanations Claude already knows (e.g., the 'Purpose' paragraph under Vectorized Environments) to lift conciseness toward 5.

Add an explicit fix-and-revalidate feedback loop after the check_env() step (e.g., 'If check_env reports issues, fix them and re-run until it passes') to strengthen workflow_clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable code with brief notes, but a few sections explain concepts Claude already knows (e.g., 'Vectorized environments run multiple environment instances in parallel, accelerating training...'), which could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready code across training, environments, callbacks, evaluation, and advanced features, covering the common cases concretely.	5 / 5
Workflow Clarity	The 'Starting a New RL Project' section gives a clear 8-step sequence with an explicit validation checkpoint (step 4: run check_env()), but lacks an explicit fix-and-revalidate feedback loop, so it sits just below the top anchor.	4 / 5
Progressive Disclosure	The body is a concise overview with clearly signaled one-level-deep references to real bundle files (references/.md, scripts/.py), all of which exist, plus a Resources section for easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and distinctive, with clear what/when guidance and an explicit boundary against a competing skill. Minor fluff ('Production-ready', 'well-documented') keeps trigger term quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — named algorithms (PPO, SAC, DQN, TD3, DDPG, A2C), a scikit-learn-like API, and specific use cases — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly states both what it does ('Production-ready reinforcement learning algorithms ... with scikit-learn-like API') and when to use it ('Use for standard RL experiments, quick prototyping ... Best for single-agent RL with Gymnasium environments').	5 / 5
Trigger Term Quality	Includes natural terms users would say ('reinforcement learning', 'RL experiments', 'PPO', 'quick prototyping', 'Gymnasium environments', 'multi-agent systems') with good coverage, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (single-agent SB3 RL) and gives an explicit redirect ('For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead'), minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/ml-training/stable-baselines3/SKILL.md
Commit: 1d182e9

Reviewed: 8 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.