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.

Open My Skills

Browse bundles

109 published bundles ready to inspect and install

Skill bundlev1.0.0

Baseline Agent Benchmarking

Measure current agent performance on the target workflow before RL intervention

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

RL Feasibility Assessment

Determine whether a workflow is actually amenable to RL improvement (clear rewards, sufficient volume, safe to explore)

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

Workflow Audit

Map an enterprise workflow end-to-end: inputs, decisions, tools, outputs, success criteria

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

Model Versioning For RL

Track and switch between reference model, current policy, and reward model versions during training

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

VLLM For RL

Configure vLLM or similar engines for RL workloads (batched generation, multiple completions)

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

High Throughput Rollout Serving

Serve models at high throughput for RL rollout collection (not just user-facing latency)

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

Compute Budgeting For RL

Estimate and optimize GPU hours needed for RL training runs

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

Checkpoint Selection

Choose the best model checkpoint based on eval performance, not just training metrics

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

Training Stability Debugging

Diagnose and fix common RL training failures: reward collapse, mode collapse, KL explosion

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

Kl Divergence Management

Control how far the policy drifts from the reference model during training

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

Reward Model Training

Train reward models from human preference data, handle label noise and distribution shift

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

RL Hyperparameter Tuning

Tune learning rates, KL penalties, reward scaling, batch sizes for RL stability

0 installs
70/100 quality
Compatibility not listed
Inspect bundle

Page 5 of 10

Previous
34567
Next