CtrlK
BlogDocsLog inGet started
Tessl Logo

langgraph-agentcore

Production patterns for building LangGraph StateGraph workflows deployed on AWS Bedrock AgentCore. Covers graph design, interrupt-based human-in-the-loop, multi-day checkpointing, 3-tier model routing with fallback chains, confidence calibration implementation, Cedar policy enforcement for agent authorization, cost-aware pipeline design, AgentCore Runtime deployment, Bedrock Foundation Models and Guardrails, MCP tool integration via AgentCore Gateway, and observability with LangSmith and CloudWatch. Use when building agentic AI workflows with LangGraph, deploying agents on AWS Bedrock AgentCore, or implementing interrupt-based HITL workflows.

72

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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, code-rich overview that earns high marks for actionability and progressive disclosure. It is slightly long for conciseness and its validation feedback loops could be made more explicit, which caps workflow clarity and conciseness just below the top anchor.

Suggestions

Tighten or relocate explanatory prose (e.g., the AgentCore session-length and cheap-gates narrative) to reference files to improve token efficiency.

Add explicit validate-then-fix-then-retry checkpoints to the HITL and checkpoint-recovery workflows rather than relying on implicit state checks.

Replace placeholder stubs (get_model fallback, invoke_model_with_cost_tracking) with concrete implementation or a pointer to a reference file to make the examples fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dense and largely actionable with little concept padding, but at ~440 lines there are minor prose passages that could be trimmed, keeping it just below the lean-and-efficient anchor.

4 / 5

Actionability

It provides extensive concrete, executable Python, Cedar, and YAML examples across each section, with only minor gaps such as the stubbed get_model fallback and the placeholder invoke_model_with_cost_tracking call.

4 / 5

Workflow Clarity

Multi-step processes like HITL resume, checkpoint recovery, and model fallback are sequenced clearly with fail-fast spend-cap checks, though validation checkpoints are occasionally implicit rather than explicit validate-fix-retry loops.

4 / 5

Progressive Disclosure

The body is an overview that clearly signals two one-level-deep reference files (references/agentcore-deployment.md and references/production-patterns.md), both confirmed to exist, with content appropriately split for easy navigation.

5 / 5

Total

17

/

20

Passed

Description

100%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.

This is a strong, comprehensive description that clearly states a niche set of production capabilities and provides explicit, natural-language trigger guidance. It avoids fluff and verbosity while covering both the what and the when concretely.

DimensionReasoningScore

Specificity

The description enumerates many concrete capabilities — graph design, interrupt-based HITL, multi-day checkpointing, 3-tier model routing with fallback chains, Cedar policy enforcement, AgentCore Runtime deployment, and observability — giving comprehensive coverage rather than vague language.

5 / 5

Completeness

It explicitly answers both what (the enumerated production patterns and 'Covers…') and when ('Use when building agentic AI workflows with LangGraph, deploying agents on AWS Bedrock AgentCore, or implementing interrupt-based HITL workflows') with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes natural trigger phrases a user would say such as 'agentic AI workflows with LangGraph', 'deploying agents on AWS Bedrock AgentCore', and 'interrupt-based HITL workflows', with good synonym coverage around the deployment domain.

5 / 5

Distinctiveness Conflict Risk

The LangGraph + AWS Bedrock AgentCore niche is specific and distinct, with triggers unlikely to fire for unrelated skills, giving minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
provectus/awos-recruitment
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.