Name: llm-application-dev-langchain-agent
Rating: 48.8 (1 reviews)
Author: administrakt0r

llm-application-dev-langchain-agent

You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.

Quality

53%

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/llm-application-dev-langchain-agent/SKILL.md

The canonical home for this skill is llm-application-dev-langchain-agent in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

57%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 rich with concrete, mostly executable code examples, but it over-explains familiar concepts, presents work as a flat checklist without validation checkpoints, and inlines content that should be split into reference files. The one external reference also points to a non-existent file.

Suggestions

Cut explanatory taxonomy of memory types, agent types, and RAG patterns down to actionable essentials; assume Claude knows the concepts.

Convert the implementation checklist into a sequenced workflow with explicit validation checkpoints (e.g. validate graph compiles, run eval suite, confirm health checks) before proceeding.

Move detailed memory/RAG/deployment sections into separate reference files under references/ and link to them from SKILL.md; fix or remove the broken 'resources/implementation-playbook.md' link.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy and mostly efficient, but explains concepts Claude already knows (memory types, RAG patterns, agent-type taxonomies) and redundantly repeats the frontmatter 'You are an expert...' line, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides multiple concrete, mostly executable code blocks (StateGraph setup, StructuredTool, FastAPI streaming, tenacity retry, LangSmith eval) with only minor gaps such as missing imports (TypedDict, Annotated), matching 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	The implementation checklist is a flat task list rather than a sequenced workflow, and it lacks explicit validation checkpoints for a multi-step build/deploy process, fitting 'steps listed but validation gaps; checkpoints missing'.	3 / 5
Progressive Disclosure	Section headers give some structure, but ~240 lines of memory/RAG/deployment detail that could live in separate files are inlined, and the single reference to 'resources/implementation-playbook.md' points to a path with no corresponding bundle file present, fitting 'some structure but references not clearly signaled and content that should be separate is inline'.	3 / 5
	Total	13 / 20 Passed

Description

48%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 establishes a clear domain niche but reads as a role statement rather than an action/trigger description: it lacks concrete actions and any 'Use when' guidance. Adding explicit verbs and a natural trigger clause would raise specificity and completeness.

Suggestions

Replace the role framing with concrete actions, e.g. 'Builds, deploys, and observes production-grade LangChain/LangGraph agents'.

Append an explicit 'Use when...' clause with natural trigger phrases users would say (e.g. 'Use when building multi-agent LangGraph workflows, RAG pipelines, or async agent services').

Add natural synonyms and version/extension cues (e.g. 'LangGraph', 'ReAct agents', 'LangSmith tracing') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph') but states a role rather than listing concrete actions like 'build', 'deploy', or 'orchestrate'; it sits between vague (1) and naming 1-2 actions (3), noticeably below the midpoint.	2 / 5
Completeness	It gives a clear 'what' (expert developer for production-grade LangChain/LangGraph systems) but provides no 'when' trigger guidance; per the rubric a missing 'Use when' clause caps completeness at 3, which is the best-fit anchor.	3 / 5
Trigger Term Quality	It includes relevant domain keywords ('LangChain', 'LangGraph', 'agent', 'production-grade') a user might say, but offers no synonyms or natural variations and lacks a 'Use when' phrase, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The LangChain/LangGraph agent niche is fairly specific and distinguishable from most other skills, with only minor overlap risk against general coding skills, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	12 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/llm-application-dev-langchain-agent/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.