Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4...
cat ~/Neu
Durchsuchen Sie neueste Skills, die dem Marktplatz hinzugefügt wurden
17,526 Skills
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models...
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks,...
Break a goal into subgoals, constraints, and acceptance criteria. Use when planning complex work, creating work...
Execute the Debug Code Change workflow end-to-end with safety gates. Use when debugging code changes, investigating...
Find failure modes, edge cases, ambiguities, and exploit paths in plans, code, or designs. Use when reviewing...
Enforce policies, guardrails, and permission boundaries; refuse unsafe actions and apply least privilege. Use when...
Compare multiple alternatives using explicit criteria, weighted scoring, and tradeoff analysis. Use when choosing...
Assign labels or categories to items based on characteristics. Use when categorizing entities, tagging content,...
Create a safety checkpoint marker before mutation or execution steps. Use when about to modify files, execute plans,...
Identify capability gaps and propose new skills with prioritization. Use when analyzing missing capabilities,...
Produce a comprehensive audit trail of actions, tools used, changes made, and decision rationale. Use when recording...
Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies,...
Connect to Sytex platform API. Use when user mentions Sytex, app, claro, ufinet, dt, adc, atis, exsei, integrar,...
|
Interact with Slite knowledge base - search, read, create, and manage notes. Use when user wants to work with Slite...
Monitor errors and issues from Sentry. Supports multiple organizations. Use when user asks about errors, exceptions,...
Manage deals, contacts, organizations, and activities in Pipedrive CRM. Use when user asks about deals, sales,...
Manage Linear issues, projects, and cycles. Use when user asks about issues, tasks, tickets, sprints, or Linear.
End-to-end workflow for resolving/fixing problems/bugs. Use when someone reports an issue, error, bug, or problem -...
Read and search Gmail messages. Use when user wants to check email, search inbox, or read messages.
Generate charts and graphs from data for reports. Use when user wants to visualize data, create charts, graphs,...