Loading...
Loading...
Found 1,203 Skills
Use when synthesizing multiple sources into coherent knowledge bases, performing multi-source analysis, or creating topic expertise from URLs and files. Also use when encountering content integration tasks requiring connections across disparate materials.
This skill should be used when the user asks to "integrate GitHub Copilot into an app", "use the Copilot SDK", "build a Copilot-powered agent", "embed Copilot in a service", or needs guidance on the GitHub Copilot SDK for Python, TypeScript, Go, or .NET.
Use when entering orchestrator mode to manage agents via Paseo CLI
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
Audit your Claude Code setup for prompt caching efficiency. Measures prefix size, hook patterns, rule duplication, dynamic injection sizes, and tool stability. Use when asked to 'check caching', 'optimize prompt cache', or 'audit setup efficiency'. Returns a scored report with fixes ranked by token savings.
Human-led curation of accumulated metis and guardrails. Surface patterns across sessions, propose what to promote, compact, or dismiss. Use after multiple sessions, before a new phase, or when search results feel noisy.
Use when the user needs prompt design, optimization, few-shot examples, chain-of-thought patterns, structured output, evaluation metrics, or prompt versioning. Triggers: new prompt creation, prompt optimization, few-shot example design, structured output specification, A/B testing prompts, evaluation framework setup.
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
Framework for automated search over task-specific model harnesses — the code around a fixed base model that decides what to store, retrieve, and show while the model works.
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.
Expert knowledge of agentic AI design patterns for autonomous agent development
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.