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.

A strong operational skill: fully executable commands, exact error-pattern matching with fixes, and well-structured paths with validation and recovery loops. The only weakness is minor token overhead — a conversational triage quote block and an intro line duplicating the description.

Suggestions

Replace the multi-line quoted 'Are you: 1... 2... 3...' block with a compact decision rule (e.g., 'If the request mentions rollback/pin/canary, go to references/versioning.md; if an error is present, use Path B; otherwise Path A').

Delete the opening sentence 'Deploy your AgentCore agent to AWS, or diagnose why a deploy failed.' — it duplicates the frontmatter description that is already loaded into context.

In Step B2, the 'Memory stuck in CREATING' entry's fix ('try removing and re-adding the memory resource') could name the exact commands to do so, keeping every fix at the same copy-paste-ready standard as the others.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands and error-to-fix pairs with almost no conceptual padding, but the conversational 'Ask (or infer from context)' quoted block and the opening line that restates the description are minor instances that could be trimmed — matching the 'efficient with minor over-explanation' anchor rather than the every-token-earns-its-place anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (agentcore validate, sts get-caller-identity, iam simulate-principal-policy, cdk bootstrap, ECR login, quota guidance), with exact error signatures matched to specific fixes — covering the common failure cases comprehensively.	5 / 5
Workflow Clarity	Clear multi-path sequence (Step 0 CLI version gate, Step 1 situation triage, Path A pre-flight, Path B diagnosis) with explicit validation checkpoints (pre-flight checks, --dry-run/--diff preview, memory status check) and a feedback loop in Step B3 (fix, re-run, and if the error recurs check agentcore status).	5 / 5
Progressive Disclosure	The body stays a concise overview while versioning, rollback, and canary detail is appropriately split into a single clearly-signaled one-level-deep reference (references/versioning.md, verified to exist and cover exactly that scope).	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.

An exemplary description: third-person voice, concrete capability list, explicit use-when guidance with natural trigger phrases, and explicit de-scoping boundaries that prevent conflict with sibling skills. No weaknesses identified.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions — 'pre-flight validation, CDK/IAM/quota error diagnosis, version management, rollback, and canary deployments' — giving comprehensive coverage of the deploy lifecycle, matching the anchor for several specific actions with no coverage gaps.	5 / 5
Completeness	It 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' plus a concrete 'Triggers on:' list).	5 / 5
Trigger Term Quality	Triggers on natural 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 both casual and CLI-specific variations.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit negative boundaries routing sibling cases away ('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 wrong-skill triggering.	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: b8171ad

Reviewed: 5 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.