CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bad-case-to-dpo

把生产 bad case / 失败轨迹转成训练数据时使用——从失败归因、轨迹前缀截取、DPO 偏好对构造、LoRA 训练到边界集与保留集双集验证的完整链路;也用于判断某类问题该走 SFT、DPO、RL 还是先修 Harness/工具/tokenizer,以及如何从运行轨迹中提取带证据的结构化学习信号。触发词:bad case、失败归因、DPO、偏好对、轨迹前缀、拒绝采样、过度矫正、边界集、保留集、过早结束、reward hacking、LoRA 微调、训练评估隔离。

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

No evaluations available

This skill hasn't been evaluated yet

Log in to request
tessl scenario generate
tessl eval run
Read the evals guide
Repository

bojieli/ai-agent-book

Path

skills/bad-case-to-dpo/SKILL.md

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.