Loading...
Loading...
Found 1,203 Skills
Step-by-step guide to building AI agents from simple chat loops to autonomous multi-agent systems with tools, memory, and event-driven architecture
Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint.
Teach AI agents how to query data warehouses accurately using ktx - an executable context layer with skills, memory, and a semantic layer
A-share multi-agent investment research framework with 7 AI analysts, bull/bear debate, and risk assessment adapted for Chinese stock market
A meta-skill that establishes a 'One Brain' portable memory folder (.agent/). It persists context, user preferences, identity rules, and execution history across different AI harnesses (Claude Code, Cursor, Windsurf, OpenClaw).
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent actions.
Verify claims in generated output against sources. Use as a separate pass AFTER content generation to catch hallucinations. Critical constraint - cannot be reliably combined with generation in a single pass.
Create a Mastra project using create-mastra and smoke test the studio in Chrome
Create or update Langfuse prompt with development label. Use when creating new prompts, updating existing prompts, or improving prompt content.