SKILLEMALL.ai
GitHub ↗ RU Sign in

CD slime-rl-training

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.

Orchestra-Research/AI-Research-SKILLs Agent Skills author: Orchestra-Research MIT 3 files body ≈ 2 648 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework.

As a process D 38/100 · Unfinished process — References files that are not bundled: examples/search-r1/, scripts/models/

ProcedureGitHubDockerAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
71
Run on models
none yet
Process rating
D
38/100
Unfinished process
References files that are not bundled: examples/search-r1/, scripts/models/
Tools and files w 18
0
Result and completion w 14
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: slime-rl-training (davila7/claude-code-templates)

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: examples/search-r1/
  • warning missing-ref reference to a missing file: scripts/models/
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: examples/search-r1/, scripts/models/
  • 0Tools and files. 2 referenced file(s) missing: examples/search-r1/, scripts/models/
  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (slime-rl-training) differs from the folder (slime)
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 26 steps
  • 100Execution cost. Instruction body is 2648 tokens
  • 100Running it twice. No mutating operations
  • low 14 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -42 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +3Description length 223: enough signal without eating the budget
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 26 items
  • +4Has examples (26 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.