Skill Bundles

Read the source. Install what you trust.

Each skill bundle packages a reusable agent behavior — a prompt, supporting files, and evaluation criteria. Browse the public catalog, review the full source, then install a private copy you can edit and experiment with.

Published bundles
108
Total installs
0
Average quality
70/100

Browse bundles

108 published bundles ready to inspect and install

Skill bundlev1.0.0

Implement Constitutional AI

Self-critique and revision loops using model-generated feedback

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Implement RLHF Pipeline

End-to-end: collect preferences → train reward model → optimize policy

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Online VS Offline RL Tradeoffs

When to use online rollouts vs. offline datasets, and how to blend

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Implement Rejection Sampling

Best-of-N sampling with a reward model; simplest "RL" that actually works

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Implement Reinforce With Baseline

Classic REINFORCE with variance reduction, the foundation of policy gradient methods

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Implement GRPO

Build Group Relative Policy Optimization as used in DeepSeek-R1

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Implement DPO

Build Direct Preference Optimization, understand when it outperforms PPO

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Implement PPO

Build Proximal Policy Optimization from scratch, understand clipping and advantage estimation

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Eval From Production Failures

Convert real production failures into new eval cases automatically

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Multi Model Eval Harness

Run the same eval suite across Haiku/Sonnet/Opus (or GPT-4/Claude/Gemini) and compare

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Eval Versioning And Regression

Track eval suite changes over time, detect regressions when evals are updated

0 installs
70/100 quality
Compatibility not listed
Inspect bundle
Skill bundlev1.0.0

Domain Specific Eval Design

Build evals for specialized verticals (legal, medical, finance, engineering)

0 installs
70/100 quality
Compatibility not listed
Inspect bundle