ai-agent

Improve LLMs with Awesome-LLM-On-Policy-Distillation

Name: Improve LLMs with Awesome-LLM-On-Policy-Distillation
Author: nick7nlp

Get curated papers and resources on On-Policy Distillation for Large Language Models, ideal for startup founders in AI.

578 stars+19★ this week16 forksPythonGuide quality 9/10 · reviewed Jul 17Updated 10/12/2026100% free · open source

What it does

Awesome-LLM-On-Policy-Distillation provides a curated collection of papers and resources on On-Policy Distillation for Large Language Models, helping startup founders in AI stay updated on the latest research and techniques.

When to use it

•When researching state-of-the-art methods for large language model training
•When looking for resources to implement on-policy distillation in a startup project
•When needing a comprehensive overview of existing research on on-policy distillation for large language models

Ready-to-paste prompt

No specific prompt is required as this tool is a collection of resources, but you can start by exploring the repository and looking for papers related to 'on-policy distillation' and 'large language models'

Heads up: This repository is a curated collection of resources and does not require any specific API keys or paid dependencies, but it does require a basic understanding of Git and Markdown to navigate and contribute to the repository

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/awesome-llm-on-policy-distillation && curl -fsSL https://workflowstacks.com/api/skills/awesome-llm-on-policy-distillation/claude-skill -o ~/.claude/skills/awesome-llm-on-policy-distillation/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

101.5M

source size

MIT

license

Key files

README.md

File tree

.github/

assets/

resources/

scripts/

.gitignore

CHANGELOG.md

CONTRIBUTING.md

LICENSE

README.md

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/awesome-llm-on-policy-distillation && curl -fsSL https://workflowstacks.com/api/skills/awesome-llm-on-policy-distillation/claude-skill -o ~/.claude/skills/awesome-llm-on-policy-distillation/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

nick7nlp

Language

Python

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.