“LangChain”

Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives…

Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF.

Use for creating publication-quality charts and multi-panel analysis summaries.

Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing.

Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries.

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback —…

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database.

Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images.

Capture a Textual terminal UI as an SVG using its headless test harness.

Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents.

Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding…

Perform a market analysis for a product category or segment.

Analyze competitors in a given market segment.

Write structured long-form blog posts with research, SEO optimization, and cover image generation.

Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.

Create social media content including Twitter/X threads, LinkedIn posts, and short-form updates.

Build Python agents with Google ADK, LangChain, LangGraph, and agents-cli.

Crie ou corrija um ambiente local de desenvolvimento Python com uv, LangChain, LangGraph Dev, Google Gemini e Tavily.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Expert-level AI Application Engineer with deep knowledge of RAG systems, LangChain, LlamaIndex, vector databases, prompt engineering, LLM API integration, and…

维护供未来分阶段装配的 OopsNote 学科方法资料；当前不属于 LangChain 运行时 skill pack。

Use to specify, build or review AI agents, LangGraph or LangChain systems, RAG, tool calling, memory, structured extraction, multi-agent workflows…