Agent Skills: ai-post-training
Post-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use when adapting an SFT model with preference or verifiable-reward signals.
ID: vasilyu1983/ai-agents-public/ai-post-training
8719
Install this agent skill to your local
Skill Files
The files that make up ai-post-training.
Loading file tree…
More agent skills
- sagElevenLabs text-to-speech with mac-style say UX.
- clickhouse-migrationsClickHouse migration patterns and rules. Use when creating or modifying ClickHouse migrations.
- docs-writeWrite documentation following Metabase's conversational, clear, and user-focused style. Use when creating or editing documentation files (markdown, MDX, etc.).
- data-engineering-data-pipelineYou are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.
- dp-optimizerApply advanced DP optimizations automatically
- ai-analyzerAI驱动的综合健康分析系统，整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。