BD verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL).
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, failures and branches
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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
description-long-hermesdescription is 227 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "dependencies"
Process rating: all ten parameters 44/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (verl-rl-training) differs from the folder (verl)
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 30 steps, 1 vague phrases
- 100Execution cost. Instruction body is 2301 tokens
- low 12 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 227: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (18 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.