CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

A well-structured, highly actionable skill body that offloads detail to real reference files and provides executable code for the common RL workflow. Main improvement area is trimming inline code verbosity that duplicates referenced materials.

Suggestions

Tighten the body by moving longer inline code examples (e.g., the full callbacks and HER blocks) into the corresponding reference files, keeping only minimal illustrative snippets inline.

Add an explicit validate-then-fix feedback loop for training failures (e.g., 'if check_env fails: fix the listed issues and re-run') to strengthen workflow_clarity.

Cross-check inline code against the reference files to avoid drift, and reference the canonical version from the body to reduce duplication.

DimensionReasoningScore

Conciseness

Code-forward and largely free of padding, but the body is fairly long with several inline code blocks that overlap with the referenced files and could be trimmed further.

4 / 5

Actionability

Provides copy-paste-ready, executable code across training, custom envs, vectorized envs, callbacks, persistence, evaluation, schedules, HER, and TensorBoard, covering the common cases.

5 / 5

Workflow Clarity

An 8-step project sequence includes an explicit validation checkpoint (run check_env() before training) and a troubleshooting section, though error-recovery feedback loops are only lightly specified.

4 / 5

Progressive Disclosure

Clear overview body with well-signaled one-level-deep references (algorithms, callbacks, custom_environments, vectorized_envs) and real script files, with bulk detail offloaded appropriately.

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.

A highly specific, well-scoped description that clearly states capabilities, natural trigger terms, and use conditions while explicitly routing adjacent cases elsewhere. Only minor trigger-term synonym coverage is missing.

DimensionReasoningScore

Specificity

Names the library and six concrete algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) plus several specific use cases, giving comprehensive concrete coverage of capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (production-ready RL algorithms with sklearn-like API) and 'when' ('Use for standard RL experiments, quick prototyping... Best for single-agent RL'), plus an explicit anti-trigger.

5 / 5

Trigger Term Quality

Strong natural terms ('reinforcement learning', 'RL experiments', 'Gymnasium environments', algorithm names) with good synonym coverage, though a few minor variations are absent.

4 / 5

Distinctiveness Conflict Risk

Clear SB3 niche with distinct triggers and explicit boundary guidance directing multi-agent/high-performance cases to pufferlib, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

foryourhealth111-pixel/Vibe-Skills

Path

bundled/skills/stable-baselines3/SKILL.md

Revision

5ce2258

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill