agents-deploy

Use when deploying your agent to AWS, or when a deploy has failed. Handles pre-flight validation, CDK/IAM/quota error diagnosis, version management, rollback, and canary deployments. Triggers on: "deploy my agent", "agentcore deploy", "deploy failed", "CDK error", "rollback", "canary deploy", "pin version", "redeploy", "deploy stuck". Not for production hardening — use agents-harden. Not for adding capabilities before deploy — use agents-build or agents-connect. Not for VPC configuration errors — use agents-build.

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 highly actionable and well-structured with a clear dual-path workflow, explicit validation checkpoints, and a properly signaled single-level reference to versioning.md. The only weakness is minor over-explanation of Bedrock inference-profile geography that could be trimmed.

Suggestions

Trim the cross-region inference profile paragraph (global./eu./apac. routing detail) to a one-line pointer to the Bedrock docs, since Claude can look up which regions each profile covers.

Consider moving the multi-target aws-targets.json example (staging/production) into references/versioning.md where staging targets are already discussed, to keep the body focused on the deploy/diagnose flow.

The memory provisioning note could be condensed to a single sentence pointing to `agentcore status --type memory` rather than explaining that 2–5 minutes is normal.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable commands throughout, but the Bedrock cross-region inference profile explanation (geographic prefixes, global./eu./apac. routing) over-explains a topic Claude can look up, and the memory provisioning note is mildly padded.	4 / 5
Actionability	Fully executable, copy-paste-ready commands for every step (agentcore validate, aws sts get-caller-identity, cdk bootstrap, ecr login, deploy --target) with concrete error-message patterns matched to specific fixes.	5 / 5
Workflow Clarity	Clear two-path sequence (pre-flight vs diagnose) with explicit validation checkpoints (Checks 1–5 before deploy) and a fix→re-run feedback loop in Path B ('After fixing, re-run' with status checks), appropriate for a destructive/batch deploy operation.	5 / 5
Progressive Disclosure	Clear overview in SKILL.md with a single, well-signaled one-level-deep reference ('load references/versioning.md and follow its instructions') that genuinely exists and holds the versioning/rollback/canary detail; bulk kept in the body is appropriately scoped.	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.

The description is exemplary: third-person voice, concrete action list, explicit trigger phrases, and clear negative boundaries against sibling skills. It covers what, when, and how-not-to-confuse comprehensively within a concise frame.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'pre-flight validation, CDK/IAM/quota error diagnosis, version management, rollback, and canary deployments' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Handles pre-flight validation, CDK/IAM/quota error diagnosis, version management, rollback, and canary deployments') and when ('Use when deploying your agent to AWS, or when a deploy has failed') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say ('deploy my agent', 'agentcore deploy', 'deploy failed', 'CDK error', 'rollback', 'canary deploy', 'pin version', 'redeploy', 'deploy stuck') including synonyms and the CLI command name.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit negative boundaries ('Not for production hardening — use agents-harden', 'Not for adding capabilities before deploy — use agents-build or agents-connect', 'Not for VPC configuration errors — use agents-build') minimizing 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-deploy/SKILL.md
Commit: d6ad2e4

Reviewed: about 1 hour 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.