verl-async-dapo

verl-async-dapo is a Fine-tuning & training data skill for AI agents, published by Ascend in the agent-skills repository on GitHub. Skillspace rates verl-async-dapo C (71/100) and it passed the safety scan; the rating is based on static analysis only.

Verl 单异步 DAPO 训练配置生成器。触发场景：(1) 启动单异步 DAPO 训练 (2) 生成训练脚本 (3) 配置特性参数 (4) 训练前检查。**特性策略**：用户未指定时默认开启性能特性（flash_attn/dynamic_batch/remove_padding/gradient_checkpointing），显存特性（offload/recompute）默认关闭。OOM 时自动追加显存特性重试。**训练监控**：启动后输出 SwanLab 链接供用户自行查看，仅在错误时通知用户。**依赖 skill**：SwanLab 配置通过 swanlab-setup skill 提供。

Grade
C
Quality
71 / 100
Safety
Passed
GitHub stars
27

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubAscend/agent-skills

Our review

Architecture
89 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
MulanPSL-2.0
Adoption
Adopted by 0 other repositories, in 1 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More Fine-tuning & training data skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.