Name: langchain-architecture
Rating: 47.2 (1 reviews)
Author: administrakt0r

langchain-architecture

Master the LangChain framework for building sophisticated LLM applications with agents, chains, memory, and tool integration.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/langchain-architecture/SKILL.md

The canonical home for this skill is langchain-architecture in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

40%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 strong on executable code examples but weak on conciseness (concept explanations Claude already knows), workflow sequencing, and progressive disclosure — the latter undermined by missing bundle files and inlined detail.

Suggestions

Remove the 'Core Concepts' definitions and exhaustive type lists (what agents/chains/memory are); assume Claude's competence and keep only the project-specific guidance.

Replace the boilerplate 'Instructions' with a concrete sequenced workflow with validation checkpoints (e.g. define tools -> build chain -> add memory -> validate output -> add callbacks -> production checklist), since the skill touches batch and production contexts.

Either create the referenced files (references/*.md, assets/*) and move the detailed pattern code into them, or remove the broken references and fix the resources/ vs references/ inconsistency.

Dimension	Reasoning	Score
Conciseness	The 'Core Concepts' section explains what agents/chains/memory/callbacks are ('Autonomous systems that use LLMs...', 'Sequences of calls to LLMs...') plus exhaustive one-line type listings — concepts Claude already knows — constituting several padded sections.	2 / 5
Actionability	Provides concrete, mostly copy-paste-ready Python across RAG, custom agents, chains, memory, callbacks, testing, and caching, but examples have minor gaps (undefined llm/tools/retriever across snippets and placeholder logic comments).	4 / 5
Workflow Clarity	The 'Instructions' are generic boilerplate ('Clarify goals...', 'Apply relevant best practices and validate outcomes') with no real task-specific sequence, and validation checkpoints are absent for batch/destructive contexts (document processing, production LLM apps).	2 / 5
Progressive Disclosure	Detailed pattern code is inlined in SKILL.md rather than split into the referenced files, and the 8 referenced bundle files (references/.md, assets/, resources/implementation-playbook.md) do not exist; the directory name is also inconsistent (resources/ vs references/).	2 / 5
	Total	10 / 20 Passed

Description

61%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.

The description is specific to LangChain and uses natural domain keywords, but it is missing an explicit 'Use when...' trigger clause, which caps completeness at 3 and weakens distinctiveness.

Suggestions

Append an explicit trigger clause, e.g. 'Use when building LangChain applications, wiring up agents/chains/memory, or integrating LLMs with external tools and APIs.'

Replace the generic framing 'building sophisticated LLM applications' with discrete actions (e.g. 'Compose agent and chain pipelines, manage conversation memory, integrate external tools') to lift specificity toward anchor 4-5.

Add common synonyms/variations (e.g. 'LangChain agents', 'LangChain tools', 'RAG', 'retrieval') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capability areas ('agents, chains, memory, and tool integration'), but the framing 'building sophisticated LLM applications' is generic and lists component categories rather than discrete actions, fitting just below anchor 4.	3 / 5
Completeness	Clearly states what the skill does ('Master the LangChain framework...') but provides no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural terms a LangChain user would actually say ('LangChain', 'LLM applications', 'agents', 'chains', 'memory', 'tool integration') with good coverage, missing only minor synonyms.	4 / 5
Distinctiveness Conflict Risk	Naming the specific 'LangChain framework' carves a clear niche with only minor overlap risk against general LLM/agent skills, though the absence of explicit trigger phrases keeps it below a 5.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/langchain-architecture/SKILL.md
Commit: 57c135b

Reviewed: 4 days 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.