bedrock-agentcore

Amazon Bedrock AgentCore platform for building, deploying, and operating production AI agents. Covers Runtime, Gateway, Browser, Code Interpreter, and Identity services. Use when building Bedrock agents, deploying AI agents to production, or integrating with AgentCore services.

Quality

77%

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 ./skills/bedrock-agentcore/SKILL.md

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.

Highly actionable content with strong executable examples and a clear quick-start sequence. It is held back by redundancy/marketing padding and by a References section that points to bundle files which are absent, undermining progressive disclosure.

Suggestions

Create the referenced bundle files (references/gateway-configuration.md, references/identity-integration.md, references/troubleshooting.md) or remove the References section, so signaled references resolve to real content.

Move the bulk of the per-service code and the Boto3 Client Reference tables into reference files, leaving SKILL.md a lean overview with one-level-deep pointers.

De-duplicate the agent entry-point example (shown in both the Runtime section and Quick Start) and trim time-sensitive/marketing lines like 'validated by AWS December 2025'.

Dimension	Reasoning	Score
Conciseness	Mostly efficient (bulk is code and reference tables that earn their tokens), but it restates the description in the Overview, duplicates the agent entry-point example in both the Runtime section and Quick Start, and includes padded/time-sensitive marketing ('validated by AWS December 2025', 'enterprise-grade') that could be trimmed; not a 4 due to this redundancy and padding.	3 / 5
Actionability	Abundant copy-paste-ready, executable guidance: boto3 calls, agentcore CLI commands, a local curl test, IAM policy JSON, and error-handling code covering the common create/invoke/deploy/test cases; fully actionable.	5 / 5
Workflow Clarity	Quick Start lays out a clear sequenced path (create file -> configure -> test locally -> deploy -> test deployed -> invoke programmatically) with verification checkpoints at local and deployed stages; not a 5 because there is no explicit 'fix and retry' feedback loop if a test fails.	4 / 5
Progressive Disclosure	Good section headers structure the document, but it inlines substantial content (full per-service implementations, API reference tables, IAM JSON) that belongs in separate files, and the three referenced files (references/gateway-configuration.md, identity-integration.md, troubleshooting.md) do not exist in the bundle, making the signaled references broken; not a 4 due to the missing reference files and heavy inlining.	3 / 5
	Total	15 / 20 Passed

Description

83%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, well-structured description that clearly states both capability and trigger conditions with concrete service names. Minor room to sharpen the action verbs and widen trigger synonyms for maximal distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the platform plus several concrete capabilities ('building, deploying, and operating production AI agents') and enumerates five specific services (Runtime, Gateway, Browser, Code Interpreter, Identity); not a 5 because the actions remain somewhat high-level rather than multiple distinct concrete operations.	4 / 5
Completeness	Explicitly answers both 'what' (platform for building/deploying/operating production AI agents across five services) and 'when' ('Use when building Bedrock agents, deploying AI agents to production, or integrating with AgentCore services'), matching the anchor-5 pattern with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('building Bedrock agents', 'deploying AI agents to production', 'integrating with AgentCore services') plus named services; not a 5 because it lacks broader synonyms and variations beyond the core terms.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly named niche (Bedrock AgentCore) with service-specific triggers, but 'building Bedrock agents' carries minor overlap risk with sibling bedrock-agent/bedrock-runtime skills, keeping it just below 5.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (523 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/bedrock-agentcore/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.