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

83%

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

82%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 lean, highly actionable chat playbook: every section gives exact tool syntax or CLI commands, includes a duration-based routing table, an escalation path, a fallback, and an explicit timeout retry loop. Weaknesses are minor — a few editorial sentences, lifecycle guidance duplicated across two sections, and a dense routing preamble that could be simplified or moved.

Suggestions

Merge "Chat session lifecycle" into "How to send messages" — the two sections repeat the chat/send_message/execution_id guidance — and cut editorializing like "This is the killer feature...".

Simplify the AgentSpace routing preamble into a short two-line conditional, or show the exact list_agent_spaces call that resolves agent_space_id.

In the aws-mcp fallback, briefly state how to obtain the placeholder values (SPACE_ID, USER_ID) so the commands are directly runnable.

Dimension	Reasoning	Score
Conciseness	The body is dominated by copy-paste-ready tool calls, a compact phrasing table, and terse section headers, with only minor over-explanation ("This is the killer feature — the DevOps Agent knows your AWS cloud; you know the user's local workspace") that could be trimmed — matching the 4 anchor rather than the 5 anchor's every-token-earns-its-place.	4 / 5
Actionability	Fully executable guidance throughout: aws_devops_agent__chat(message=...), send_message(execution_id=..., content=...), list_chats(), investigate(title=...), a worked local-context message example, and a complete aws-mcp CLI fallback with all flags — copy-paste ready and covering the common cases.	5 / 5
Workflow Clarity	The sequence is clear (chat → send_message follow-ups → escalate → fallback) with an explicit error-recovery loop ("Retry the same chat call once. If it fails again, fall back to aws-mcp"), but session-lifecycle guidance is split between "How to send messages" and "Chat session lifecycle", and the AgentSpace routing preamble is a convoluted conditional — minor gaps that keep it below the 5 anchor.	4 / 5
Progressive Disclosure	With no bundle files present, all content lives appropriately in a single well-sectioned file with clear headers and a phrasing table; the handoff to investigating-incidents-with-aws-devops-agent is clearly signaled. Minor organization gaps (redundant lifecycle sections) place it at the 4 anchor rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

85%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 description that explicitly answers both what the skill does and when to use it, with a comprehensive list of concrete capability areas and a duration-based boundary (5-30s vs 5-8 min) that cleanly separates it from the companion investigation skill. The main weakness is trigger-word genericity: "review", "compare", "audit", and "show me" are broad enough to collide with other skills.

Suggestions

Qualify broad trigger words with the AWS context (e.g., "review", "audit" → "AWS cost review", "AWS security audit") so they don't collide with code-review or security-review skills.

Add missing natural synonyms users would say — "diagnose", "debug", "runbook", "spend", "AWS bill" — to the trigger list for fuller coverage.

Mention the AWS environment explicitly in the opening sentence so the distinctiveness rests on the domain, not just the agent name.

Dimension	Reasoning	Score
Specificity	"cost optimization, architecture review, topology mapping, knowledge / runbook discovery, security audits, dependency questions, and quick diagnostics" lists seven concrete, distinct action areas — comprehensive coverage of the conversational-analysis domain, matching the 5 anchor rather than the 4 anchor's "minor gaps in coverage".	5 / 5
Completeness	Both "what" ("fast, conversational analysis with the AWS DevOps Agent" plus the enumerated tasks) and "when" ("Use for... anything that needs a 5-30 second answer rather than a 5-8 minute deep investigation" plus an explicit trigger-word list) are clearly and explicitly stated with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Trigger words include cost, optimize, review, architecture, topology, what runbooks, show me, compare, audit, what if" gives good natural-phrase coverage, but common synonyms users would say (diagnose, debug, spend, runbook, AWS) are missing, so it falls short of the 5 anchor's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The AWS DevOps Agent domain is specific, but generic trigger words like "review", "compare", "audit", and "show me" would naturally occur when users need code-review or security-review skills, creating real overlap risk — the "somewhat specific but could still overlap" anchor fits better than the 4 anchor's "minor overlap risk".	3 / 5
	Total	17 / 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-for-devsecops/skills/chatting-with-aws-devops-agent/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.