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.
74
66%
Does it follow best practices?
Impact
82%
2.34xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/llm-application-dev/skills/langchain-architecture/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly identifies its technology niche (LangChain 1.x / LangGraph) and includes an explicit 'Use when' clause with relevant trigger terms. Its main weakness is that the capability listing is somewhat high-level—it could benefit from more specific concrete actions beyond 'Design'. Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions such as 'create chains, configure retrieval pipelines, set up streaming, define agent tools' to improve specificity beyond the general 'Design' verb.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (LLM applications, LangChain, LangGraph) and mentions some capabilities (agents, memory, tool integration), but doesn't list multiple concrete actions—'Design' is somewhat vague and there are no specific operations like 'create chains', 'configure retrieval', 'set up streaming', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration) and 'when' (explicit 'Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'LangChain', 'LangGraph', 'AI agents', 'LLM workflows', 'memory', 'tool integration'. These cover the main terms a developer would use when seeking help with this technology stack. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to specific technology references (LangChain 1.x, LangGraph) which clearly differentiate it from generic coding skills or other AI framework skills. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent, executable code examples covering a wide range of LangChain/LangGraph patterns, which is its primary strength. However, it is severely bloated—much of the descriptive content (Core Concepts section, feature bullet lists) explains things Claude already knows, and the entire document should be restructured with progressive disclosure into multiple files. It also lacks validation checkpoints and error recovery guidance for complex agent workflows.
Suggestions
Remove or drastically reduce the 'Core Concepts' section (items 1-5)—Claude already knows what StateGraph, memory types, document loaders, and LangSmith are. Keep only project-specific conventions or non-obvious gotchas.
Split into multiple files: keep SKILL.md as a concise overview with Quick Start, then reference separate files like PATTERNS.md (RAG, multi-agent, workflow), MEMORY.md, TESTING.md, and PERFORMANCE.md.
Add validation/error-handling guidance for agent workflows: how to verify tool calls succeeded, how to handle LLM failures mid-graph, how to inspect checkpointer state for debugging.
Remove the 'When to Use This Skill' section—it's meta-information that doesn't help Claude execute tasks and wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Explains concepts Claude already knows (what StateGraph provides, what Document Loaders are, what LangSmith does). The 'Core Concepts' section is largely descriptive bullet points that don't add actionable value. Lists like memory types and document processing components are things Claude already knows well. | 1 / 3 |
Actionability | The code examples are concrete, executable, and copy-paste ready. Patterns include complete StateGraph definitions, tool schemas with Pydantic, memory configurations, streaming implementations, and testing strategies—all with real imports and runnable code. | 3 / 3 |
Workflow Clarity | Multi-step patterns (RAG, multi-agent, workflow) are clearly sequenced with graph definitions showing START→nodes→END flow. However, there are no validation checkpoints, error handling guidance, or feedback loops for when things go wrong in these complex agent workflows. No guidance on debugging failed agent runs or validating outputs. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All patterns, memory management, callbacks, streaming, testing, and performance optimization are inlined in a single massive document. Content like the multi-agent pattern, testing strategies, and performance optimization could easily be split into separate referenced files. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (635 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
27a7ed9
- Reviewed
Table of Contents
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.