CtrlK
BlogDocsLog inGet started
Tessl Logo

langgraph

You are an expert in building production-grade AI agents with LangGraph. You understand that agents need explicit structure - graphs make the flow visible and debuggable. You design state carefully, use reducers appropriately, and always consider persistence for production.

52

Quality

58%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/langgraph/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 content is a well-structured, actionable reference of LangGraph patterns with executable code and useful anti-patterns. Its main weakness is mild verbosity from a repeated persona intro and generic boilerplate sections that assume little of Claude's knowledge.

Suggestions

Remove the body's opening paragraph that duplicates the frontmatter description, and tighten the generic 'Capabilities'/'Requirements' bullet lists or fold them into the relevant patterns.

Replace the filler 'When to Use' line with concrete trigger conditions (e.g. 'Use when wiring conditional routing, multi-agent shared state, or human-in-the-loop checkpoints').

Complete the truncated 'State with Reducers' example (fill in the edges) and replace the search-tool '# Implementation here' placeholder so all patterns are fully runnable.

DimensionReasoningScore

Conciseness

Mostly efficient executable code, but the opening paragraph repeats the frontmatter description verbatim and the generic 'Capabilities', 'Requirements', and filler 'When to Use' line ('applicable to execute the workflow...') add padding that could be trimmed.

3 / 5

Actionability

Three full, mostly copy-paste-ready code patterns plus 'Instead' code for anti-patterns provide concrete executable guidance, with only minor gaps such as the '# Implementation here' search placeholder and the '# ... add edges' truncation.

4 / 5

Workflow Clarity

The basic-agent pattern is sequenced with numbered steps (1-7) and each pattern carries a 'When to use' header; no destructive or batch operations are present that would require validation feedback loops, so the minor gap is the absence of explicit error-recovery guidance.

4 / 5

Progressive Disclosure

The body is well-organized with clear section headers (Capabilities, Requirements, Patterns, Anti-Patterns, Limitations, Related Skills) and is self-contained with no nested references; it stops short of 5 because no bundle files exist and three full code patterns are inlined rather than split into reference files.

4 / 5

Total

15

/

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 LangGraph niche but reads as a second-person persona statement rather than a trigger-rich skill description. It lacks an explicit 'when to use' clause, capping completeness and weakening trigger guidance.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases, e.g. 'Use when building LangGraph state graphs, designing agent state with reducers, or adding checkpointers/persistence to a multi-agent workflow.'

Reframe in third person with concrete actions ('Builds LangGraph StateGraphs, defines reducers for shared state, wires conditional routing') instead of the second-person persona ('You are an expert... You design...').

Add natural user-facing terms and synonyms ('agent framework', 'state machine', 'checkpointing', 'human-in-the-loop') to broaden trigger coverage.

DimensionReasoningScore

Specificity

Phrases like 'design state carefully, use reducers appropriately, and always consider persistence' describe abstract role posture rather than concrete actions, only naming the LangGraph domain; additionally the second-person voice ('You are an expert... You design...') triggers the specificity penalty.

2 / 5

Completeness

It clearly states what the skill does ('building production-grade AI agents with LangGraph') but provides no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Relevant keywords appear ('LangGraph', 'AI agents', 'graphs', 'state', 'reducers', 'persistence') but they lean technical and miss common user variations such as 'agent framework', 'state machine', or 'checkpointing'.

3 / 5

Distinctiveness Conflict Risk

Naming 'LangGraph' carves a clear niche with minimal conflict risk, though there is minor overlap with related agent-framework skills (crewai, autonomous-agents).

4 / 5

Total

12

/

20

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

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
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.