Loading...
Loading...
Found 1,280 Skills
View Langfuse trace details. Use when checking specific trace input/output, debugging LLM calls, or analyzing costs.
Improves text for clarity, directness, and engagement following professional writing best practices. Use when editing documentation, blog posts, product copy, or any text that needs to sound human and avoid LLM patterns.
Expert in building comprehensive AI systems, integrating LLMs, RAG architectures, and autonomous agents into production applications. Use when building AI-powered features, implementing LLM integrations, designing RAG pipelines, or deploying AI systems.
Defense techniques against prompt injection attacks including direct injection, indirect injection, and jailbreaks - theUse when "prompt injection, jailbreak prevention, input sanitization, llm security, injection attack, security, prompt-injection, llm, owasp, jailbreak, ai-safety" mentioned.
Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like chain-of-thought, few-shot prompting, and progressive disclosure.
Integrate Portkey AI Gateway into TypeScript/JavaScript applications. Use when building LLM apps with observability, caching, fallbacks, load balancing, or routing across 200+ LLM providers.
Recursive Language Models (RLM) CLI - enables LLMs to recursively process large contexts by decomposing inputs and calling themselves over parts. Use for code analysis, diff reviews, codebase exploration. Triggers on "rlm ask", "rlm complete", "rlm search", "rlm index".
Consult external LLMs (Gemini, OpenAI/Codex, Qwen) for second opinions, alternative plans, independent reviews, or delegated tasks. Use when a user asks for another model's perspective, wants to compare answers, or requests delegating a subtask to Gemini/Codex/Qwen.
Use this skill when crafting, reviewing, or improving prompts for LLM pipelines — including task prompts, system prompts, and LLM-as-Judge prompts. Triggers include: requests to write or refine a prompt, diagnose why an LLM produces inconsistent or incorrect outputs, bridge the gap between intent and model behavior, reduce ambiguity in instructions, add few-shot examples, structure complex prompts, or improve output formatting. Also use when the user needs help distinguishing specification failures (unclear instructions) from generalization failures (model limitations), or when iterating on prompts based on observed failure modes. Do NOT use for general coding tasks, document creation, or non-LLM writing.
创建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。
Inline adversarial plan review — 3 sequential checks (Feasibility, Completeness, Scope & Alignment) performed by the calling LLM in its own context. No subagents spawned. Call after saving a plan. Returns GATE_PASS or GATE_FAIL with blocking issues.
vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. Use for offline batch inference, API server deployment, quantization inference (with msmodelslim quantized models), tensor/pipeline parallelism for distributed serving, and OpenAI-compatible API endpoints. Supports Qwen, DeepSeek, GLM, LLaMA models with Ascend-optimized kernels.