New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Lightning

by coco-research in coco-research/coco

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning.

Custom licenceAuto-check passedAI & LLM Engineering

Install Agent Lightning

skills CLI
$ npx skills add coco-research/coco --skill agent-lightning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install coco-research/coco agent-lightning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-lightning .claude/skills/agent-lightning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-lightning
GitHub stars
482
Token cost
~2k tokens
SKILL.md length
262 words
Files
2
Skills in repo
57
Repo updated
First seen
Licence
Custom licence

At a glance

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning.

  • Works in 4 steps: Receives trace events from your JS app… → Stores them in LightningStore → Runs training algorithms → …
  • Setting up agent training
  • SKILL.md covers Quick Start, Core Concepts, Instrumentation and LightningStore, plus 5 more sections
  • Calls pip; reaches test.pypi.org and pypi.org

What it does

Agent Lightning is an agent skill from coco-research/coco. 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.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `reference.md`).

It sits in AI & LLM Engineering, covering Reinforcement learning and Observability. The repository describes itself as: CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands…

When your agent uses it

  • Setting up agent training
  • Instrumenting agents with tracing
  • Configuring LightningStore
  • Implementing reward functions

Example prompts

  • “/agent-lightning”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Receives trace events from your JS app via HTTP
  2. Stores them in LightningStore
  3. Runs training algorithms
  4. Returns optimized prompts

What it can do on your machine

Read from SKILL.md and the folder at commit 2ddb559. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • test.pypi.org
    • pypi.org

    Also links to:

    • microsoft.github.io
    • github.com
    • arxiv.org
    • discord.gg

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Lightning loads about 2k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 262 words (~2,024 tokens).

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

— opening of SKILL.md by coco-research, Custom licence
name
agent-lightning
domain
engineering

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/agent-lightning of coco-research/coco.

  • SKILL.md
  • reference.md

Open the folder on GitHubat commit 2ddb559

Compare with similar skills

Agent Lightning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Lightning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Lightning this skillcoco-research/coco482—~2kAutomated safety check: PassCustom licence
Hugging Face LLM Trainerhuggingface/skills11k3 repos~7.2kAutomated safety check: PassApache-2.0
Train RlOpenPipe/ART11k—~2.4kAutomated safety check: PassApache-2.0
Qwopus27b Rl TrainingR6410418/Jackrong-llm-finetuning-guide1.7k—~830Automated safety check: PassApache-2.0
Looperksimback/looper710—~2.7kAutomated safety check: NotesMIT
Fine Tuning With TrlOrchestra-Research/AI-Research-SKILLs13k7 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • Hugging Face LLM Trainer

    huggingface/skills

    Official

    Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.

    11k GitHub starsUsed in 3 repos~7.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Train Rl

    OpenPipe/ART

    RL training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Qwopus27b Rl Training

    R6410418/Jackrong-llm-finetuning-guide

    Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.

    1.7k GitHub stars~830 tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Looper

    ksimback/looper

    Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.

    710 GitHub stars~2.7k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Fine Tuning With Trl

    Orchestra-Research/AI-Research-SKILLs

    Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.

    13k GitHub starsUsed in 7 repos~2.9k tokens
    AI & LLM EngineeringAuto-check passed

  • Optim Agent

    Optim-Agent/optim-agent

    A skill your agent uses when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies…

    801 GitHub stars~1.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from coco-research/coco

All 57 skills in this repo

  • Arch Index

    coco-research/coco

    Build and validate .arch/index.json — a committed map from each architectural component of this repository to the real directories and files that implement it, pinned to a git commit, with every…

    482 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Skill Evolution

    coco-research/coco

    A skill your agent uses when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one…

    482 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Coco Diagram

    coco-research/coco

    A skill your agent uses for architecture, current-state, process, data-flow, medallion, or DP diagrams, including redrawing .drawio and Mermaid sources.

    482 GitHub stars~9.2k tokensUpdated today
    Auto-check passed

  • M0

    coco-research/coco

    A skill your agent uses when the user says 'm0', 'm0 status', 'start m0', 'cross-tool memory', 'operational thread', or 'where is my memory stored', or when the M0 daemon or MCP wiring needs…

    482 GitHub stars~755 tokensUpdated today
    Auto-check passed

  • PR To Video

    coco-research/coco

    A skill your agent uses when the user wants a GitHub PR (URL, owner/repoN, or 'this PR') made into a code-change explainer video from its diff and commits: changelog, feature reveal, fix, or refactor.

    482 GitHub stars~7.8k tokensUpdated today
    Auto-check: notes

  • Website To Video

    coco-research/coco

    A skill your agent uses when the user wants a video of a website (site tour, portfolio, docs or landing-page showcase) captured from a URL.

    482 GitHub stars~3.1k tokensUpdated today
    Auto-check: notes

Categories

Questions about Agent Lightning

What does Agent Lightning do?

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Agent Lightning is an agent skill from coco-research/coco. Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning.

When should I use Agent Lightning?

Agent Lightning fits situations like: setting up agent training; instrumenting agents with tracing; configuring LightningStore; implementing reward functions.

How do I install Agent Lightning in Claude Code?

Run `npx skills add coco-research/coco --skill agent-lightning -a claude-code`. Or copy the skill folder (skills/agent-lightning in coco-research/coco) into .claude/skills/agent-lightning in your project. Claude Code loads it when a task matches its description.

How do I install Agent Lightning in Codex?

Run `npx skills add coco-research/coco --skill agent-lightning -a codex`. Or copy the skill folder (skills/agent-lightning in coco-research/coco) into .agents/skills/agent-lightning in your project. Codex loads it when a task matches its description.

Can I use Agent Lightning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add coco-research/coco --skill agent-lightning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-lightning, .gemini/skills/agent-lightning, .github/skills/agent-lightning and .opencode/skills/agent-lightning in your project.

What does Agent Lightning need to run?

Going by SKILL.md and its folder, Agent Lightning needs the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Agent Lightning access the network?

SKILL.md names 6 domains. In commands or code: test.pypi.org and pypi.org; the agent is likely to contact these when it follows the instructions. As links in the text: microsoft.github.io, github.com, arxiv.org and discord.gg. This is read from the text; nothing was executed.

Is Agent Lightning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Lightning use?

Agent Lightning has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Agent Lightning use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Lightning?

Skills that share tags, products or a category with Agent Lightning: Hugging Face LLM Trainer (huggingface/skills, 11k stars), Train Rl (OpenPipe/ART, 11k stars), Qwopus27b Rl Training (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Looper (ksimback/looper, 710 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Lightning?

coco-research (a GitHub user) maintains it in coco-research/coco, which has 482 GitHub stars. The repository holds 57 skills in this directory. The repository was last updated on October 8, 2026.

Source: coco-research/coco on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.