Loading...
Loading...
Found 1,066 Skills
Complex migration strategies for LangChain applications. Use when migrating from legacy LLM frameworks, refactoring large codebases, or implementing phased migration approaches. Trigger with phrases like "langchain migration strategy", "migrate to langchain", "langchain refactor", "legacy LLM migration", "langchain transition".
Build LLM applications using Dify's visual workflow platform. Use when creating AI chatbots, implementing RAG pipelines, developing agents with tools, managing knowledge bases, deploying LLM apps, or building workflows with drag-and-drop. Supports hundreds of LLMs, Docker/Kubernetes deployment.
Provides tool and function calling patterns with LangChain4j. Handles defining tools, function calls, and LLM agent integration. Use when building agentic applications that interact with tools.
Use this skill to build, run, deploy, evaluate, and troubleshoot Go agents with Google's Agent Development Kit (`google.golang.org/adk`), including llmagent config, tools/integrations, callbacks/plugins, sessions/state/memory, workflows, streaming, MCP/A2A, and runtime/deployment patterns.
Implement a task with automated LLM-as-Judge verification for critical steps
Performs semantic code intelligence and token optimization through context engineering and automated context packing. Use when reducing token overhead for large codebases, creating repository digests with Gitingest, packaging code context with Repomix, or tracing cross-file dependencies with llm-tldr.
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.
Edit prose to sound more natural, direct, and engaging. Works top-down through four levels (Document → Paragraph → Sentence → Word) with human checkpoints at each stage. Fixes LLM patterns, writerly bad habits, and style deficits. Works for academic papers, reports, memos, essays, blog posts, proposals, and other nonfiction. Use when prose sounds robotic, dull, or inaccessible.
Bridge web search capability for LLM workflows. Use when user asks for latest info, external facts, or source links and the active model/toolchain lacks direct search ability.
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.
Comprehensive prompt and context engineering for any AI system. Four modes: (1) Craft new prompts from scratch, (2) Analyze existing prompts with diagnostic scoring and optional improvement, (3) Convert prompts between model families (Claude/GPT/Gemini/Llama), (4) Evaluate prompts with test suites and rubrics. Adapts all recommendations to model class (instruction-following vs reasoning). Validates findings against current documentation. Use for system prompts, agent prompts, RAG pipelines, tool definitions, or any LLM context design. NOT for running prompts, generating content, or building agents.
Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.