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.

82

1.66x
Quality

79%

Does it follow best practices?

Impact

83%

1.66x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/langchain-architecture/SKILL.md

The canonical home for this skill is langchain-architecture in wshobson/agents

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A code-rich, highly actionable reference that covers LangChain/LangGraph patterns thoroughly, but it is overlong for a SKILL.md and inlines content that should be split into separate reference files. Tightening tangential examples and adding validation checkpoints would lift the weaker dimensions.

Suggestions

Move the four architecture patterns, memory management, testing, and performance sections into separate reference files (e.g., ARCHITECTURE_PATTERNS.md, MEMORY.md, TESTING.md) and keep SKILL.md as a concise overview with one-level-deep links.

Trim tangential code such as the full AST-based calculate evaluator and reduce redundant prose so the body respects token budget; replace time-sensitive claims ('standard in 2026', pinned 1.2.x versions) with version-agnostic guidance or a deprecated/old-patterns section.

Add explicit validation/verification checkpoints to the workflows (e.g., assert the compiled graph handles unknown routes, validate tool schemas before compile, test checkpoint round-trips) to strengthen feedback loops.

DimensionReasoningScore

Conciseness

The body is mostly code-driven and efficient, but at ~660 lines it pads in tangential detail (a full AST math evaluator, time-sensitive claims like "LangGraph is the standard for building agents in 2026" and pinned "langchain (1.2.x)" versions not placed in a deprecated section) that could be tightened.

3 / 5

Actionability

Provides fully executable, copy-paste-ready code across the common cases — ReAct agent, RAG, structured tools, multi-agent orchestration, memory, callbacks, streaming, tests, and caching — with concrete imports and runnable snippets.

5 / 5

Workflow Clarity

Pattern code shows clear sequences (define state → add nodes → add edges → compile) and a Production Checklist gives ordered guidance, but explicit validation checkpoints and feedback loops are only implicit rather than called out per pattern.

4 / 5

Progressive Disclosure

Section headers give reasonable structure, but with no bundle files the entire 660-line body — four full architecture patterns, memory, testing, and performance sections that clearly belong in separate reference files — is inlined rather than split into one-level-deep references.

3 / 5

Total

15

/

20

Passed

Description

87%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, third-person description that concretely states capabilities and provides an explicit 'Use when' trigger clause with natural phrases. Minor specificity gains are possible by enumerating a few more concrete actions.

DimensionReasoningScore

Specificity

Lists several specific capability areas — "agents, memory, and tool integration" — under a concrete verb ("Design LLM applications"), but stops short of the comprehensive multi-action coverage of a 5.

4 / 5

Completeness

Explicitly answers both what ("Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and 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

Natural phrases users would say appear ("building LangChain applications", "implementing AI agents", "complex LLM workflows"), with good coverage though a few synonyms/variations are missing.

4 / 5

Distinctiveness Conflict Risk

Niche is clearly scoped to LangChain 1.x / LangGraph with distinct triggers, minimal overlap risk with unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (667 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
Dicklesworthstone/pi_agent_rust
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.