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

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/agents/langchain/SKILL.md

Quality

Content

63%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 dense, code-rich overview that is highly actionable but carries too much reference-style content inline alongside dedicated reference files, weakening token efficiency and progressive disclosure. Tightening the body to defer detail to the existing reference files would lift the weakest dimensions.

Suggestions

Move the Vector stores, Document loaders, and Text splitters catalogs into references/integration.md and keep only a one-line pointer plus one example in SKILL.md to reduce inline bulk.

Fix API inaccuracies in examples (e.g., WebBaseLoader takes the URL in its constructor, not via .load(url)) and replace eval()-based tool examples with a safer implementation.

Add a brief validation/checklist step to the RAG pipeline (e.g., verify retriever returns expected chunks before querying) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~470-line body is mostly code and largely avoids explaining basics Claude already knows, but it inlines substantial reference-style catalog content (vector stores, document loaders, text splitters, multiple agent patterns) that overlaps with the provided reference files and could be tightened.	3 / 5
Actionability	Abundant copy-paste-ready code examples cover the common cases, but minor inaccuracies (e.g., WebBaseLoader invoked with .load(url) instead of constructing with the URL, eval() in a tool) introduce small gaps.	4 / 5
Workflow Clarity	Quick start is clear and the RAG pipeline is laid out as an explicit numbered 6-step sequence, but the skill is largely a feature catalog rather than a guided workflow and lacks validation checkpoints.	4 / 5
Progressive Disclosure	Three real reference files exist and are listed with descriptions in a References section, but the body inlines much of the same material instead of deferring to those files, so content that should be separate remains inline.	3 / 5
	Total	14 / 20 Passed

Description

83%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 description that clearly states both the framework's purpose and explicit use-when guidance with natural trigger terms. It could be sharpened by framing capabilities as actions and noting differentiation from adjacent frameworks.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete capabilities ('agents, chains, and RAG', 'ReAct agents, tool calling, memory management, and vector store retrieval'), though these read as feature enumeration rather than discrete actions, leaving minor gaps versus the comprehensive-action anchor.	4 / 5
Completeness	Explicitly answers what ('Framework for building LLM-powered applications with agents, chains, and RAG') and when ('Use for building chatbots, question-answering systems, autonomous agents, or RAG applications') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'chatbots', 'question-answering systems', 'autonomous agents', and 'RAG applications', giving good keyword coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	LangChain's named niche is mostly distinct, but the broad LLM-application framing creates minor overlap risk with closely related skills like LlamaIndex and LangGraph that the description does not differentiate from.	4 / 5
	Total	17 / 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: OpenLAIR/dr-claw
Path: skills/agents/langchain/SKILL.md
Commit: 01ef795

Reviewed: ~18 hours 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.