chatting-with-aws-devops-agent

Have a fast, conversational analysis with the AWS DevOps Agent. Use for cost optimization, architecture review, topology mapping, knowledge / runbook discovery, security audits, dependency questions, and quick diagnostics — anything that needs a 5-30 second answer rather than a 5-8 minute deep investigation. Trigger words include cost, optimize, review, architecture, topology, what runbooks, show me, compare, audit, what if.

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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concrete, executable, and well-sequenced with clear failure and escalation paths. Its only weakness is structure: it is a monolithic single file that could offload reference material (CLI fallback details, intent-to-phrasing mapping) into bundled files.

Suggestions

Move the aws-mcp fallback CLI command reference and the intent-to-phrasing table into a bundled reference file (e.g. references/fallback-and-phrasing.md) and link to it from the body, keeping SKILL.md as a tighter overview.

Split the local-context injection templates (per-intent: cost, architecture, topology, diagnostics) into references/context-templates.md so the main body stays lean.

Add a brief 'See also' line linking the sibling investigating-incidents skill explicitly where escalation is discussed, to reinforce the one-level-deep reference pattern.

Dimension	Reasoning	Score
Conciseness	The body is lean and action-oriented, built around code blocks, a phrasing table, and concrete templates; it assumes Claude's competence with only minor editorializing ('killer feature') that does not materially pad it.	3 / 3
Actionability	Provides fully executable MCP tool calls (chat, send_message, list_chats) and CLI fallback commands with realistic parameters and a copy-paste local-context template, matching the top anchor.	3 / 3
Workflow Clarity	The single primary action (chat) is unambiguous, and the failure path is explicitly sequenced ('1. Retry the same chat call once. 2. If it fails again, fall back to aws-mcp') with escalation and security checkpoints clearly marked.	3 / 3
Progressive Disclosure	The skill is a single ~134-line file with no external references; it is well-sectioned but everything is inline (phrasing table, fallback CLI details, context template) with no one-level-deep pointers to split material, fitting the mid anchor better than the top.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, trigger-rich, and clearly distinguishes the skill from the deeper investigation alternative. It answers both what the skill does and when to use it without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete use cases — 'cost optimization, architecture review, topology mapping, knowledge / runbook discovery, security audits, dependency questions, and quick diagnostics' — matching the anchor for naming several specific actions.	3 / 3
Completeness	Explicitly answers what ('Have a fast, conversational analysis with the AWS DevOps Agent') and when ('Use for ... anything that needs a 5-30 second answer rather than a 5-8 minute deep investigation'), with an explicit trigger clause, satisfying the top anchor.	3 / 3
Trigger Term Quality	'Trigger words include cost, optimize, review, architecture, topology, what runbooks, show me, compare, audit, what if' gives broad coverage of natural terms a user would actually say, matching the top anchor.	3 / 3
Distinctiveness Conflict Risk	Scoped to a specific agent and explicitly contrasts with the sibling skill ('rather than a 5-8 minute deep investigation'), carving a clear niche; a few triggers like 'review'/'compare' are generic but the framing keeps conflict risk low.	3 / 3
	Total	12 / 12 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-for-devsecops/skills/chatting-with-aws-devops-agent/SKILL.md
Commit: 222ce56

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.