agent-lightning SKILL.md skillA

agent-lightning from coco-research/coco is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add coco-research/coco/agent-lightning@git:20260802.1479e32

Pins git:20260802.1479e32 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
coco-research/coco
Path
skills/agent-lightning/SKILL.md
Versions recorded
2
Latest version
git:20260802.1479e32, committed Aug 2, 2026
First version recorded
Apr 26, 2026
Size
8,106 bytes
Repository stars
796
License
a license file GitHub does not identify

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore, implementing reward functions, or optimizing prompts with RL/APO algorithms.

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

# Agent Lightning

Microsoft's framework for training AI agents with reinforcement learning, automatic prompt optimization, and supervised fine-tuning.

## Quick Start

### Installation

```bash
pip install agentlightning
```

For nightly builds:
```bash
pip install --upgrade --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ --pre agentlightning
```

### Minimal Integration (Zero Code Change)

Add `agl.emit_xxx()` helpers to your existing agent:

```python
import agentlightning as agl

# Your existing agent code
def my_agent(task):
    agl.emit_input(task)  # Track input
    
    response = llm.generate(task)
    agl.emit_output(response)  # Track output
    
    reward = evaluate(response)
    agl.emit_reward(reward)  # Track reward
    
    return response
```

## Core Concepts

### Architecture Flow

```
Agent (your code) → agl.emit_xxx() → Spans → LightningStore → Algorithm → Updated Resources
```

### Key Components

| Component | Purpose |
|-----------|---------|
| `LightningStore` | Central hub for traces, tasks, and resources |
| `Tracer` | Collects spans from agent execution |
| `Algorithm` | Consumes traces, produces improvements |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add coco-research/coco/agent-lightning@sha256:8e29e4f578b91ae4

The line at the top of this page pins the label git:20260802.1479e32, 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_2ll7ygnk5iducikn.svg)](https://markdownregistry.com/a/art_2ll7ygnk5iducikn)

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

Versions

The registry has recorded 2 versions of this file, between Apr 26, 2026 and Aug 2, 2026, about one every 99 days.

versioncommittedcommitsizeaudit
git:20260802.1479e32 latest2026-08-02 1479e32 8,106 BA view · diff
git:20260426.d53cc6c2026-04-26 d53cc6c 8,086 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8106 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 curl or wget piped into a shell
  • 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

Source

GitHub

coco-research/coco · 796 stars · license a license file GitHub does not identify · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2ll7ygnk5iducikn
GET https://markdownregistry.com/api/v1/resolve?ref=coco-research/coco/agent-lightning
GET https://markdownregistry.com/api/v1/blob/8e29e4f578b91ae4a67ef1728b0e92b1090395511a9b77855bc0d89c1bc530b8

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 coco-research/coco

AGENTS.md AGENTS.md file
coco-research/coco · AGENTS.md
git:20261007.61dca6d · audit A · 796 stars
create-rule SKILL.md skill
coco-research/coco · adapters/cursor/skills/create-rule/SKILL.md · Create Cursor rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up…
git:20260426.d53cc6c · audit A · 796 stars
create-skill SKILL.md skill
coco-research/coco · adapters/cursor/skills/create-skill/SKILL.md · Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a…
git:20260426.d53cc6c · audit A · 796 stars
create-subagent SKILL.md skill
coco-research/coco · adapters/cursor/skills/create-subagent/SKILL.md · Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up…
git:20260426.d53cc6c · audit A · 796 stars
migrate-to-skills SKILL.md skill
coco-research/coco · adapters/cursor/skills/migrate-to-skills/SKILL.md · Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent…
git:20260426.d53cc6c · audit A · 796 stars
update-cursor-settings SKILL.md skill
coco-research/coco · adapters/cursor/skills/update-cursor-settings/SKILL.md · Modify Cursor/VSCode user settings in settings.json. Use when the user wants to change editor settings, preferences…
git:20260426.d53cc6c · audit A · 796 stars
_selftest SKILL.md skill
coco-research/coco · evals/skills/_selftest/SKILL.md
git:20261017.31c57de · audit C · 796 stars
agent-self-eval SKILL.md skill
coco-research/coco · skills/agent-self-eval/SKILL.md · Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use…
v0.1.0 · audit A · 796 stars
ai-marketing-videos SKILL.md skill
coco-research/coco · skills/ai-marketing-videos/SKILL.md · Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for…
git:20260914.57d3294 · audit A · 796 stars
ai-product SKILL.md skill
coco-research/coco · skills/ai-product/SKILL.md · Use when building AI features into a product: LLM integration, RAG pipelines, guardrails, streaming, AI UX, prompt…
v0.1.0 · audit A · 796 stars
api-design-principles SKILL.md skill
coco-research/coco · skills/api-design-principles/SKILL.md · Use when designing a new REST or GraphQL API, reviewing an API spec before implementation, setting team API standards…
git:20260914.e75f220 · audit A · 796 stars
pmstudio-arb SKILL.md skill
coco-research/coco · skills/arb-review/SKILL.md · Generate an Architecture Review Board (ARB) presentation in Coco Inc's standard 11-slide format. Use when someone asks…
git:20260802.1479e32 · audit A · 796 stars

Every file in coco-research/coco

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