investigating-incidents-with-aws-devops-agent

Run a deep root-cause investigation on the AWS DevOps Agent. Use when the user describes an incident, alarm, outage, or unexplained behavior — keywords like "5xx", "503", "OOM", "latency spike", "deployment failure", "rollback", "sev1", "investigate", "root cause", "debug", "alarm fired", "service down". Polls and streams progress, then surfaces recommendations.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 well-structured, highly actionable investigation workflow with concrete tool calls, a streaming loop, error-recovery edge cases, and a security gate. Its main weakness is a broken reference to a non-existent REFERENCE.md.

Suggestions

Add the missing REFERENCE.md file referenced at the end of the body, or remove the reference and inline the polling cadence / journal record types / error recovery details.

Trim rhetorical flourishes such as "This is the killer feature..." to keep the body token-lean.

Consider moving the emoji-prefix journal-record mapping into REFERENCE.md to further slim the overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and efficient with concrete tool calls and command lists, but includes minor flourishes that could be trimmed ("This is the killer feature — the DevOps Agent knows your AWS cloud; you know the user's local workspace") and a full emoji-prefix mapping, placing it just below the every-token-earns-its-place anchor.	4 / 5
Actionability	Fully executable guidance: copy-paste-ready tool calls with parameters and return shapes (investigate, get_task, list_journal_records, list_recommendations) plus a concrete CLI fallback with flags covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (Pre-flight → Start → Stream loop → On COMPLETED → Fallback) with explicit feedback loops for error recovery in the Edge cases section and an explicit approval gate before applying IaC changes; this is a read-only investigation so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	Well-organized into clear sections with a one-level-deep reference signaled at the end ("See [REFERENCE.md](REFERENCE.md) for polling cadence, journal record types, and error recovery"), but the referenced REFERENCE.md file is not present in the bundle, a notable gap that prevents a top score.	4 / 5
	Total	18 / 20 Passed

Description

95%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 states both capability and trigger conditions with a rich set of natural incident keywords. It is concrete, third-person, and clearly distinguishable from sibling skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Run a deep root-cause investigation", "Polls and streams progress", "surfaces recommendations" — covering the core capability with only minor gaps in coverage, matching the anchor for several specific actions.	4 / 5
Completeness	Explicitly answers both what ("Run a deep root-cause investigation... Polls and streams progress, then surfaces recommendations") and when ("Use when the user describes an incident, alarm, outage, or unexplained behavior — keywords like...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural keywords users would say during incidents — "5xx", "503", "OOM", "latency spike", "deployment failure", "rollback", "sev1", "alarm fired", "service down" — matching the anchor for comprehensive coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — AWS DevOps Agent deep root-cause investigation — with distinct incident-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: plugins/aws-agents-for-devsecops/skills/investigating-incidents-with-aws-devops-agent/SKILL.md
Commit: 8ea26bd

Reviewed: 2 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.