CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is highly actionable with executable, modern code and good progressive disclosure to a real reference file. Its weaknesses are minor redundant concept restatements and the absence of explicit validation/feedback loops in build workflows.

Suggestions

Trim the Memory Systems and Callbacks & Tracing sections to drop basic restatements of what each component does; keep only the LangChain-1.x/LangGraph-specific guidance Claude would not already know.

Add an explicit validation checkpoint (e.g., verify the agent invokes the expected tool and checkpointer persists state across thread_id invocations) into the main agent-build workflow rather than relegating verification to a separate testing section.

Consolidate the package-structure block and per-integration list into the references file so the overview stays a lean entry point.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concise bullets and executable code, but sections like Memory Systems and Callbacks restate concepts Claude already knows (e.g., "ConversationBufferMemory: Stores all messages", "LangSmith is the standard for observability" with a generic logging/tracking list) that could be trimmed.

2 / 3

Actionability

Quick Start and later sections provide complete, executable, copy-paste-ready code (a working ast-based calculator tool, MemorySaver checkpointer, Redis cache, async batch, Pinecone vector store, pytest tests) with specific import paths and runnable examples.

3 / 3

Workflow Clarity

Build steps and patterns are present and sequenced, but agent-construction workflows lack explicit validation checkpoints or validate→fix→retry feedback loops; the Testing Strategies section provides some verification but core workflows keep checkpoints implicit.

2 / 3

Progressive Disclosure

The body is a clear overview that defers deeper material to a single well-signaled, one-level-deep reference ("Detailed pattern documentation lives in references/details.md"), and that referenced file exists, giving easy navigation without nested indirection.

3 / 3

Total

10

/

12

Passed

Description

100%

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 provides explicit, natural trigger guidance scoped to LangChain/LangGraph. It answers both what and when without verbosity.

DimensionReasoningScore

Specificity

"Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration" lists several concrete actions (designing agents, memory, tool integration) tied to a specific framework, matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

It explicitly answers both "what" (Design LLM applications ... for agents, memory, and tool integration) and "when" (Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows) with an explicit trigger clause.

3 / 3

Trigger Term Quality

"Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows" uses natural phrasings a user would actually say, giving good coverage of the skill's core triggers.

3 / 3

Distinctiveness Conflict Risk

The description is anchored to LangChain 1.x and LangGraph with distinct, framework-specific triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
wshobson/agents
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.