LangChain — agents, RAG and LLM app patterns (short listing)
Short listing (license not verifiable): reference playbook for building LLM apps with LangChain — ReAct agents, tool calling, RAG pipelines, memory, streaming and LangSmith observability
- What
- Short listing (license not verifiable): reference playbook for building LLM apps with LangChain — ReAct agents, tool calling, RAG pipelines, memory, streaming and LangSmith observability
- Cost
- Free
- Needs
- a Python project (3.10+) where you want LLM/agent features; a paid model API key for real runs (OpenAI/Anthropic/Google — free tiers exist, token usage is billed); pip
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — short listing (the frontmatter claims MIT, but the discovery manifest records NOASSERTION, so nothing is reproduced here): @ovachiever's langchain skill, listed here with credit to its creator — a dense reference playbook for building LLM-powered applications with the LangChain framework: ReAct agents with tool calling (built in under 10 lines), RAG pipelines (document loaders, text splitters, Chroma/Pinecone/FAISS vector stores), conversation memory, structured output, parallel tool execution, streaming, and LangSmith observability, plus a LangChain-vs-LangGraph decision guide and alternatives (LlamaIndex, LangGraph, Haystack, Semantic Kernel). Honest caveats: the skill body ships an example calculator tool written as `lambda x: eval(x)` — a code-execution footgun if copied into production, so the safety check in the install prompt matters; it references third-party projects (langchain-ai/langchain) rather than redistributing them, and the framework itself is maintained upstream by LangChain AI, not by this repo's author; running real LLM features requires paid model API keys (OpenAI/Anthropic/Google) — free tiers exist but token usage is billed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a Python project (3.10+) where you want LLM/agent features; a paid model API key for real runs (OpenAI/Anthropic/Google — free tiers exist, token usage is billed); pip Install "LangChain — agents, RAG and LLM app patterns (short listing)" for me. It gives my agent @ovachiever's LangChain reference playbook: ReAct agent patterns with tool calling, RAG pipelines (loaders, splitters, vector stores), conversation memory, structured output, parallel tool execution, streaming, LangSmith observability, and a LangChain-vs-LangGraph decision guide. IMPORTANT: the license was not verifiable (the discovery manifest records NOASSERTION) — fetch from the link only, reproduce nothing beyond the link, and read the terms yourself before use. Extra caution: the skill body contains an example tool written as `lambda x: eval(x)` — never copy that into production code. Repository: https://github.com/ovachiever/droid-tings/blob/master/skills/langchain/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). Flag the eval() example explicitly and make sure no such pattern is installed or executed. This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "langchain". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install langchain packages for my provider, save my model API key in the vault — never paste it into the skill). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.