slime-rl-training
slime-rl-training is a skill in Orchestra-Research/AI-Research-SKILLs, last changed 28 Jan 2026. It can run shell commands, reach the network and name web addresses — read the findings before installing.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
At a glance
What it can touch
How much a skill can do, not whether it is risky.
Pattern check
Nothing flagged
That isn't proof the skill is harmless.
Commit 773a529 · 3 Nov 2026
How the check worksPattern check: nothing flagged
That isn't proof the skill is harmless.
Install
Each tab says whether it installs commit 773a529, the one we checked, or the latest version.
OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.
No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. Orchestra-Research/AI-Research-SKILLs/06-post-training/slime (opens in a new tab)
Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.
Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.
Claude Code
Pinned to commit 773a529, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 773a52944ba4747a18bd4ae9ade53fff041adcbc &&git -C "$tmp" sparse-checkout set -- 06-post-training/slime &&git -C "$tmp" checkout -q 773a52944ba4747a18bd4ae9ade53fff041adcbc &&mkdir -p .claude/skills &&mkdir .claude/skills/slime-rl-training &&cp -R "$tmp"/06-post-training/slime/. .claude/skills/slime-rl-training/ &&rm -rf "$tmp"If Claude Code was already running and this created the skills folder, run /reload-skills.
Claude apps
Pinned to commit 773a529, the one we checked.
Skills in the Claude apps belong to your account rather than to a project.
Make slime-rl-training.zip, with the skill folder at the top level:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 773a52944ba4747a18bd4ae9ade53fff041adcbc &&git -C "$tmp" sparse-checkout set -- 06-post-training/slime &&git -C "$tmp" checkout -q 773a52944ba4747a18bd4ae9ade53fff041adcbc &&out="$(mktemp -d)" &&cp -R "$tmp"/06-post-training/slime "$out"/slime-rl-training &&(cd "$out" && zip -qr - slime-rl-training) > slime-rl-training.zip &&rm -rf "$tmp" "$out"In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose slime-rl-training.zip.
On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.
Codex
Pinned to commit 773a529, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 773a52944ba4747a18bd4ae9ade53fff041adcbc &&git -C "$tmp" sparse-checkout set -- 06-post-training/slime &&git -C "$tmp" checkout -q 773a52944ba4747a18bd4ae9ade53fff041adcbc &&mkdir -p .agents/skills &&mkdir .agents/skills/slime-rl-training &&cp -R "$tmp"/06-post-training/slime/. .agents/skills/slime-rl-training/ &&rm -rf "$tmp"Codex picks up new skills on its own; restart it if this one does not appear.
Cursor
Pinned to commit 773a529, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 773a52944ba4747a18bd4ae9ade53fff041adcbc &&git -C "$tmp" sparse-checkout set -- 06-post-training/slime &&git -C "$tmp" checkout -q 773a52944ba4747a18bd4ae9ade53fff041adcbc &&mkdir -p .cursor/skills &&mkdir .cursor/skills/slime-rl-training &&cp -R "$tmp"/06-post-training/slime/. .cursor/skills/slime-rl-training/ &&rm -rf "$tmp"Copilot & VS Code
Pinned to commit 773a529, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 773a52944ba4747a18bd4ae9ade53fff041adcbc &&git -C "$tmp" sparse-checkout set -- 06-post-training/slime &&git -C "$tmp" checkout -q 773a52944ba4747a18bd4ae9ade53fff041adcbc &&mkdir -p .github/skills &&mkdir .github/skills/slime-rl-training &&cp -R "$tmp"/06-post-training/slime/. .github/skills/slime-rl-training/ &&rm -rf "$tmp"In a running Copilot CLI session, run /skills reload.
Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.
gh skill install Orchestra-Research/AI-Research-SKILLs 06-post-training/slime/SKILL.md@773a52944ba4747a18bd4ae9ade53fff041adcbc --agent github-copilot --scope projectGemini CLI
Pinned to commit 773a529, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 773a52944ba4747a18bd4ae9ade53fff041adcbc &&git -C "$tmp" sparse-checkout set -- 06-post-training/slime &&git -C "$tmp" checkout -q 773a52944ba4747a18bd4ae9ade53fff041adcbc &&mkdir -p .gemini/skills &&mkdir .gemini/skills/slime-rl-training &&cp -R "$tmp"/06-post-training/slime/. .gemini/skills/slime-rl-training/ &&rm -rf "$tmp"In a running session, run /skills reload.
Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.
gemini skills install https://github.com/Orchestra-Research/AI-Research-SKILLs.git --path 06-post-training/slime --scope workspaceAny agent
Pinned to commit 773a529, the one we checked.
OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/Orchestra-Research/AI-Research-SKILLs.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 773a52944ba4747a18bd4ae9ade53fff041adcbc &&git -C "$tmp" sparse-checkout set -- 06-post-training/slime &&git -C "$tmp" checkout -q 773a52944ba4747a18bd4ae9ade53fff041adcbc &&mkdir -p .agents/skills &&mkdir .agents/skills/slime-rl-training &&cp -R "$tmp"/06-post-training/slime/. .agents/skills/slime-rl-training/ &&rm -rf "$tmp"Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.
npx skills@1.7.4 add Orchestra-Research/AI-Research-SKILLs --skill slime-rl-trainingWhat it can touch
From the files and frontmatter at commit 773a529. This is how much a skill can do, not whether it is risky.
Pattern check
Pattern check: nothing flagged · commit 773a529 · 3 Nov 2026
We checked every text file in this skill, at commit 773a529 on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
How the check worksReport an incorrect finding
Outside links we did not follow
- https://github.com/THUDM/slime.git
- https://thudm.github.io/slime/
- https://github.com/THUDM/slime
- https://lmsys.org/blog/2025-07-09-slime/
- https://github.com/THUDM/slime/issues
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specFails
The open format from agentskills.io, held to the strictest version of each rule among the agents we check.
- Error
The name "slime-rl-training" doesn't match its folder "slime". The spec requires them to match. N4
Fix: Set name: slime, or rename the folder to slime-rl-training.
- Warning
The frontmatter uses [ ] or { } values. Most agents accept them, but the spec's validator (skills-ref) rejects the file. F4
Fix: Write lists as "- item" lines and maps as indented key: value lines, without anchors or tags.
- Warning
Fields outside the spec: version, author, tags and dependencies. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1
Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Note
Reference files that SKILL.md doesn't link: references/api-reference.md and references/troubleshooting.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: references/api-reference.md (393 lines) and references/troubleshooting.md (387 lines). B5
Fix: Add a short list of the sections at the top of each.
- Error
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
The name "slime-rl-training" doesn't match its folder "slime". Claude Code shows the skill as /slime-rl-training, and the folder name also invokes it. N4
Fix: Set name: slime, or rename the folder to slime-rl-training.
- Note
Claude Code ignores fields it doesn't know: version, author, tags and dependencies. O1
Fix: Check the spelling against Claude Code's field list, or delete them.
- Note
Reference files that SKILL.md doesn't link: references/api-reference.md and references/troubleshooting.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: references/api-reference.md (393 lines) and references/troubleshooting.md (387 lines). B5
Fix: Add a short list of the sections at the top of each.
- Note
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
The name "slime-rl-training" doesn't match its folder "slime". claude.ai refuses an upload whose folder name doesn't match the skill name. N4
Fix: Set name: slime, or rename the folder to slime-rl-training.
- Error
Upload and packaging fail on fields outside the spec: version, author, tags and dependencies. O1
Fix: Delete them, and keep your own data under metadata as text values.
- Note
The description is 223 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
Reference files that SKILL.md doesn't link: references/api-reference.md and references/troubleshooting.md. Anthropic suggests linking every reference file directly from SKILL.md. B4
Fix: Link each one from SKILL.md and say when to read it.
- Note
Reference files over 100 lines with no table of contents at the top: references/api-reference.md (393 lines) and references/troubleshooting.md (387 lines). B5
Fix: Add a short list of the sections at the top of each.
- Error
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
The name "slime-rl-training" doesn't match its folder "slime". OpenAI's own upload example uses a differently named folder, but the spec it follows says they must match. N4
Fix: Set name: slime, or rename the folder to slime-rl-training.
- Warning
Fields outside the spec: version, author, tags and dependencies. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
Fix: Delete them, or move your own data under metadata as text values.
- Warning
VS Code & CopilotPasses with warnings
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Warning
The name "slime-rl-training" doesn't match its folder "slime". VS Code uses the folder name, slime, instead. N4
Fix: Set name: slime, or rename the folder to slime-rl-training.
- Note
VS Code ignores fields it doesn't support: version, author, tags and dependencies. O1
Fix: Delete them unless another agent you target reads them.
- Warning
SKILL.md
Files
3 files
| Path | Size |
|---|---|
| SKILL.md (opens in a new tab) | 11.3 KB |
| references/api-reference.md (opens in a new tab) | 11.6 KB |
| references/troubleshooting.md (opens in a new tab) | 7.1 KB |
More from Orchestra-Research/AI-Research-SKILLs
Other AI & ML engineering skills
Same category, most repo stars first.