langchain

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured reference with executable code and clean progressive disclosure into real bundle files. The main weakness is verbosity from marketing metrics, repeated examples, and explanatory prose Claude already knows.

Suggestions

Remove marketing/statistical content ('119,000+ GitHub stars', '272,000+ repositories', '3,800+ contributors', the performance benchmark table) — these add tokens without aiding execution.

Consolidate the repeated agent-creation snippets (create_agent appears in Quick start, Core concepts, and Advanced patterns) into one canonical example plus short variants.

Cut filler lines that restate the obvious ('The most popular framework for building LLM-powered applications.', '# Add memory to track conversation') to tighten the body.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but retains padding — marketing metrics ('119,000+ GitHub stars', '3,800+ contributors'), a benchmark table, repeated provider-swap blocks, and throwaway lines like 'The most popular framework for building LLM-powered applications' that Claude does not need.	3 / 5
Actionability	It provides fully executable, copy-paste-ready code across all common cases — LLM calls, agents, RAG, structured output, vector stores, loaders, and splitters — with specific, runnable snippets.	5 / 5
Workflow Clarity	Sections are logically sequenced (install → basic → core concepts → RAG → advanced → patterns) and the RAG pipeline is a clear numbered 6-step sequence, though no explicit validation/checkpoint steps are included.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with three well-signaled one-level-deep references (agents.md, rag.md, integration.md), all of which exist as real files, splitting detail appropriately.	5 / 5
	Total	17 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities and provides explicit use-when triggers. Minor gains possible by adding common synonyms and sharper differentiation from adjacent LLM frameworks.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete capabilities — 'agents, chains, and RAG', 'tool calling, memory management, and vector store retrieval' — giving comprehensive coverage rather than vague abstractions.	5 / 5
Completeness	It explicitly answers both 'what' (framework for building LLM-powered applications with agents/chains/RAG) and 'when' via a concrete 'Use for building chatbots, question-answering systems, autonomous agents, or RAG applications' trigger clause.	5 / 5
Trigger Term Quality	It surfaces natural phrases users say ('chatbots', 'question-answering systems', 'autonomous agents', 'RAG applications') but omits some common synonyms and concrete file/extension triggers, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The LangChain niche is distinct and named, but the broad LLM-application framing creates minor overlap risk with closely related skills like LangGraph or LlamaIndex.	4 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/langchain/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.