prime-rl SKILL.md skillB

prime-rl from svngoku/coding-agents-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add svngoku/coding-agents-skills/prime-rl@git:20261013.5def5e6

Pins git:20261013.5def5e6 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
svngoku/coding-agents-skills
Path
skills/prime-rl/SKILL.md
Versions recorded
1
Latest version
git:20261013.5def5e6, committed Oct 13, 2026
Size
15,146 bytes
Repository stars
12
License
MIT

Post-train LLMs with PrimeIntellect's prime-rl (async RL, SFT, distillation, evals). Use this skill whenever the user mentions prime-rl, wants to write an rl.toml or sft.toml, run `uv run rl` / `uv run sft` / `uv run eval` / `uv run inference`, pick GRPO, MaxRL, OPD or ECHO, tune IPO loss, or monitor and resume a run. Also trigger for verifiers environments, Prime Intellect post-training, reverse-text, and pydantic-config TOML overrides.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# prime-rl Post-Training

[prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) is Prime Intellect's framework for
asynchronous RL and SFT post-training at scale. One launch (`uv run rl`) starts a vLLM inference
server, a CPU-only orchestrator that collects rollouts from
[verifiers](https://github.com/PrimeIntellect-ai/verifiers) environments, and an FSDP trainer that
pushes new weights back to inference. This skill teaches how to install it, write configs, choose
an algorithm, launch and monitor runs, evaluate checkpoints, and export weights.

Facts are checked against upstream commit `dd72f0f` (2026-10-13, v0.9.0). When the docs and the
code disagree, this skill follows the code (see [Doc Drift](#doc-drift)).

## Quick Reference

| Topic | Reference | When to read |
|-------|-----------|--------------|
| Install, uv sync, extras, env packages | [references/install.md](references/install.md) | Fresh machine, missing env package, DeepEP/kernels |
| Config system (TOML + CLI) | [references/configs.md](references/configs.md) | Writing or overriding any config, config errors |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add svngoku/coding-agents-skills/prime-rl@sha256:df5c8b61238faeb1

The line at the top of this page pins the label git:20261013.5def5e6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_evmhf3wnhow77ear.svg)](https://markdownregistry.com/a/art_evmhf3wnhow77ear)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 13, 2026.

versioncommittedcommitsizeaudit
git:20261013.5def5e6 latest2026-10-13 5def5e6 15,146 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No curl or wget piped into a shell (matched: curl -sSL https://raw.githubusercontent.com/PrimeIntellect-ai/prime-rl/main/scripts/install.sh | bas)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15146 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

svngoku/coding-agents-skills · 12 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_evmhf3wnhow77ear
GET https://markdownregistry.com/api/v1/resolve?ref=svngoku/coding-agents-skills/prime-rl
GET https://markdownregistry.com/api/v1/blob/df5c8b61238faeb16cd29501cb36c3ecc22df611306dcb7895f2e4d169f440c8

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from svngoku/coding-agents-skills

AGENTS.md AGENTS.md file
svngoku/coding-agents-skills · AGENTS.md
git:20261019.1a0654c · audit A · 12 stars
adaption-ai SKILL.md skill
svngoku/coding-agents-skills · skills/adaption-ai/SKILL.md · Adaption AI SDK for synthetic data augmentation and dataset adaptation. Use when building data pipelines with the…
git:20261013.980e7e1 · audit A · 12 stars
api-design SKILL.md skill
svngoku/coding-agents-skills · skills/api-design/SKILL.md · Design and review intuitive, scalable, maintainable HTTP APIs. Use this skill whenever the user wants to design a new…
git:20260813.4b33420 · audit A · 12 stars
database-design SKILL.md skill
svngoku/coding-agents-skills · skills/database-design/SKILL.md · Design relational database schemas (and choose when to go NoSQL) that stay maintainable and fast. Use this skill…
git:20260813.4b33420 · audit A · 12 stars
ddd SKILL.md skill
svngoku/coding-agents-skills · skills/ddd/SKILL.md · Domain-Driven Design system for software development. Use when designing new systems with DDD principles, refactoring…
git:20261013.980e7e1 · audit A · 12 stars
genai-tk SKILL.md skill
svngoku/coding-agents-skills · skills/genai-tk/SKILL.md · Build GenAI and agentic apps with genai-tk (tclatos/genai-tk), a YAML-driven IoC toolkit over LangChain, DeepAgents…
git:20261013.09dd77b · audit A · 12 stars
langchain SKILL.md skill
svngoku/coding-agents-skills · skills/langchain/SKILL.md · Build AI agents with LangChain v1 and LangGraph in Python. Use this skill whenever the user mentions LangChain…
git:20261018.63db2d6 · audit A · 12 stars
microservices-patterns SKILL.md skill
svngoku/coding-agents-skills · skills/microservices-patterns/SKILL.md · Decompose systems into microservices and apply canonical distributed-systems patterns. Use this skill whenever the user…
git:20260813.4b33420 · audit A · 12 stars
performance-optimization SKILL.md skill
svngoku/coding-agents-skills · skills/performance-optimization/SKILL.md · Systematically find and fix performance problems in applications, frontend and backend, by measuring first. Use this…
git:20260813.4b33420 · audit A · 12 stars
scalingo SKILL.md skill
svngoku/coding-agents-skills · skills/scalingo/SKILL.md · Scalingo is a European (French) Platform-as-a-Service for deploying and operating web applications, background workers…
git:20261014.c555fef · audit A · 12 stars
security-best-practices SKILL.md skill
svngoku/coding-agents-skills · skills/security-best-practices/SKILL.md · Practical security review and hardening guidance for application code in Python, JavaScript/TypeScript, and Go. Use…
git:20260813.4b33420 · audit A · 12 stars
smolagents SKILL.md skill
svngoku/coding-agents-skills · skills/smolagents/SKILL.md · Build AI agents with Hugging Face's SmolAgents framework. Use when creating code-executing agents, tool-calling agents…
git:20260813.422f18d · audit A · 12 stars

Every file in svngoku/coding-agents-skills

Browse by kind, by grade B, or by owner.