FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Reinforcement learning and LLM alignment v1.0.0
Use this resource to train an agent with reinforcement learning or align an LLM
New
- 355 downloads
- 155 likes
- 100 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install reinforcement-learning-trainingWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent helps you train an agent with reinforcement learning or align an LLM with human feedback: policy gradients, PPO, Q-learning, RLHF and GRPO. You get a training method, reward definition and signs of instability.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- Apache-2.0
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: role and rules for using the references
- references/patterns.md: algorithms and training schemes
- references/sharp_edges.md: causes of instability and reward hacking
Good fit for
- You want to train an agent that learns from a reward
- You must align a language model with human preferences
Not for
Tags
- reinforcement learning
- ppo
- rlhf
- grpo
About
You say
“Train an agent with PPO in a simple grid and plot the reward curve.”
Skill published by omer-metin under the Apache-2.0 license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to train an agent with reinforcement learning or align an LLM
- Review and adjust the result
Content preview
Files
- LICENSE10.1 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/patterns.md3.6 KB
- references/sharp_edges.md5.6 KB
- references/validations.md2.9 KB
- SKILL.md1.1 KB
Origin and licence
Listed unmodified
- Author
- omer-metin
- Source
- github.com/omer-metin/skills-for-antigravity/tree/e8dcf4e8737921a10088bd5c9eb65e81f74c051f/skills/reinforcement-learning
- Licence
- Apache-2.0
Notice
« reinforcement-learning » (omer-metin, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…