agents-build

Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: "add memory", "remember across sessions", "call agent from app", "invoke agent from code", "agent auth", "streaming", "VPC", "VPC connectivity", "can't reach from VPC", "multi-agent", "A2A", "A2A auth", "orchestrator not delegating", "specialist not called", "migrate Bedrock Agent", "migration issue", "change model", "browser tool", "code interpreter", "delete agent", "tear down", "agentcore remove", "cross-account memory", "add payments capability to my agent", "wire payments plugin", "integrate x402 payments with the agent I'm building", "add MPP payments", "Machine Payments Protocol". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI/dev-server errors: use agents-debug. Runtime x402/MPP payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.

Quality

96%

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

Quality

Content

92%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 body is a well-structured orchestrator that concisely routes developers to capability-specific references while embedding concrete validation steps and executable guidance for the cross-cutting concerns it handles directly. The only mild weakness is the somewhat long inline model-change section.

Suggestions

Consider moving the "Changing the model" section into its own reference file (e.g. references/model.md) and linking to it from the routing table, keeping SKILL.md a pure overview.

Trim the cross-region inference profile explanation in the model section to a one-line pointer to the Bedrock inference profiles docs, since the prefix behavior is documented elsewhere.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and avoids explaining concepts Claude already knows, but the inline "Changing the model" section (three code blocks plus cross-region profile explanation) is content that could be trimmed or moved to a reference, keeping it just below the lean/efficient anchor.	4 / 5
Actionability	Provides concrete commands ("agentcore --version"), specific file paths ("agentcore/agentcore.json", "app/<AgentName>/model/load.py"), executable model-change code, and a copy-paste name-validation table with push-back scripts, covering the common orchestration cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced (Step 0 → Step 1 → Step 2) with explicit validation checkpoints (CLI version check, project-context detection, disambiguation before routing, Pre-flight name validation) and a fix-and-retry feedback loop for invalid names.	5 / 5
Progressive Disclosure	A clear overview routes to eleven real one-level-deep reference files via an intent→reference table, with content appropriately split out; the single inline "Changing the model" section is a minor, justified deviation.	5 / 5
	Total	19 / 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.

A high-quality description that clearly states what the skill does, when to use it via concrete trigger phrases, and how it differs from sibling skills with explicit routing. It is comprehensive without being padded and uses appropriate third-person imperative voice.

Dimension	Reasoning	Score
Specificity	Lists nine concrete capability domains ("memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal") with comprehensive coverage, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	Explicitly answers both what ("extend an existing agent project with...") and when (a labeled "Triggers:" clause with concrete phrases), plus routing guidance, matching the anchor for clearly answering both what and when.	5 / 5
Trigger Term Quality	Extensive natural trigger phrases ("add memory", "remember across sessions", "can't reach from VPC", "orchestrator not delegating", "integrate x402 payments with the agent I'm building") with synonyms (multi-agent/A2A, payments/x402/MPP), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Defines a clear niche (extending existing projects) and explicitly routes siblings away ("External APIs via Gateway: use agents-connect", "New project: use agents-get-started", "CLI/dev-server errors: use agents-debug"), giving minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: aws/agent-toolkit-for-aws
Path: plugins/aws-agents/skills/agents-build/SKILL.md
Commit: 68d9e85

Reviewed: 3 days 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.