langchain-architecture

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/llm-application-dev/skills/langchain-architecture/SKILL.md

Quality

Content

61%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.

The body is actionable and reasonably well-structured with real executable examples and a clear pointer to references/details.md. It is held back by conceptual padding and the absence of explicit validation/feedback steps in its workflows.

Suggestions

Trim conceptual filler (the 'Key Features', 'Components', and 'When to Use' lists) and move detailed patterns entirely into references/details.md so SKILL.md stays a lean overview.

Add explicit validation/verification steps to any multi-step workflow (e.g., assert agent tool selection and check pointer state before relying on memory) so workflows have feedback loops.

Make code examples fully self-contained by defining or stubbing undefined variables like `text_splitter` and `embeddings_model` in the async batch example.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with substantial executable code, but includes conceptual padding ('LangGraph is the standard for building agents in 2026', enumerated feature/component lists) and a 'When to Use' section that repeats the frontmatter, so it could be tightened.	3 / 5
Actionability	Provides concrete, mostly executable code (ReAct agent with a complete safe-math tool, tests, Redis caching, async batch) with only minor gaps such as undefined `text_splitter`/`embeddings_model` in the batch example.	4 / 5
Workflow Clarity	As an architecture/reference skill it presents patterns rather than a sequenced procedure, and the Quick Start lacks explicit validation or feedback checkpoints for the operations shown.	3 / 5
Progressive Disclosure	Good structure with section headers and a clearly signaled one-level-deep reference ('Detailed pattern documentation lives in references/details.md'), though a fair amount of content that could live in details.md remains inline in SKILL.md.	4 / 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 capabilities and explicit 'Use when' triggers with natural phrasing. It is mostly specific and distinct, with only minor abstraction and overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities — 'Design LLM applications', 'agents, memory, and tool integration' — but the actions are slightly more abstract than the level-5 'extract/fill/merge' style, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (Design LLM applications using LangChain 1.x and LangGraph for agents, memory, tool integration) and 'when' (Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — 'building LangChain applications', 'implementing AI agents', 'complex LLM workflows' — with good coverage but missing common synonyms or variations.	4 / 5
Distinctiveness Conflict Risk	The LangChain 1.x / LangGraph niche is clearly distinct, but the broad triggers ('LLM applications', 'AI agents', 'LLM workflows') create minor overlap risk with other LLM-agent skills.	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
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: wshobson/agents
Path: plugins/llm-application-dev/skills/langchain-architecture/SKILL.md
Commit: d6837ae

Reviewed: about 11 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.