CtrlK
BlogDocsLog inGet started
Tessl Logo

langchain-architecture

Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/langchain-architecture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

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 actionable, executable code examples but weaker on conciseness (it explains concepts Claude already knows) and workflow clarity (generic instructions with no validation checkpoints). Progressive disclosure is hampered by referenced bundle files that are not actually present.

Suggestions

Cut the 'Core Concepts' definitional prose (e.g. one-line glosses of agents/chains/memory) and keep only the enumerations Claude can't derive — this directly improves conciseness.

Replace the abstract 'Instructions' with a concrete sequenced build workflow (e.g. choose agent type -> wire memory -> add tools -> validate with a test -> add callbacks) with explicit validation checkpoints, or cap expectations on workflow_clarity.

Create the referenced references/*.md and assets/* files so the signaled progressive-disclosure links resolve, or remove the broken links from the 'Resources' section.

DimensionReasoningScore

Conciseness

The code blocks earn their place, but the 'Core Concepts' section restates well-known LangChain concepts Claude already knows (e.g. 'Autonomous systems that use LLMs to decide which actions to take', 'Sequences of calls to LLMs or other utilities'), so it is mostly efficient with unnecessary explanation that could be trimmed.

2 / 3

Actionability

It provides many concrete, largely copy-paste-ready code examples — Quick Start agent, RAG pattern, custom @tool agent, SequentialChain, memory selection, callback handler, pytest tests, and caching/streaming — matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

The 'Instructions' section is generic and abstract ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') with no concrete sequenced process or validation checkpoints, so a sequence is implied but explicit checkpoints are missing — it does not reach the 'clear sequence with explicit validation steps' anchor.

2 / 3

Progressive Disclosure

The 'Resources' section clearly signals one-level-deep references, but the referenced files (references/*.md, assets/*) do not exist in the bundle, and the bulk of the detail is presented inline as a long monolithic document rather than split into those referenced files.

2 / 3

Total

9

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 well-formed description with explicit 'what' and 'when' clauses, third-person voice, and natural trigger terms tied to a distinct niche. The only weakness is that the capability statement stays at a category level rather than enumerating concrete actions.

DimensionReasoningScore

Specificity

It names the domain and several capability areas ("agents, memory, and tool integration patterns") but the lead verb "Design LLM applications" is category-level rather than a list of concrete actions, matching the 'names domain and some actions' anchor rather than the 'lists multiple specific concrete actions' one.

2 / 3

Completeness

It explicitly answers both 'what' (design LLM apps with agents, memory, tool integration) and 'when' via a clear 'Use when...' clause, matching the anchor that requires explicit triggers for both.

3 / 3

Trigger Term Quality

The 'Use when' clause surfaces natural terms a user would actually say — "building LangChain applications", "implementing AI agents", "creating complex LLM workflows" — giving good coverage of likely trigger phrasing.

3 / 3

Distinctiveness Conflict Risk

LangChain is a clearly scoped niche with distinct, framework-specific triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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

referenced_paths_exist

Referenced path issues: 8 missing

Warning

Total

15

/

16

Passed

Repository
rmyndharis/antigravity-skills
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.