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

88%

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

77%

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

A highly actionable, well-sequenced investigation workflow with strong validation and safety checkpoints. Its main weakness is a dangling reference to REFERENCE.md that is not present in the bundle, and minor conciseness padding.

Suggestions

Create references/REFERENCE.md (or move the file into a bundle dir) so the cited reference for polling cadence, journal record types, and error recovery actually exists, or remove the reference and inline the essential details.

Tighten the Pre-flight intro by dropping the "killer feature" commentary and merging the title-packing Tip into the preceding instructions to avoid restating the same guidance twice.

Consider moving the full record-type/emoji mapping table into REFERENCE.md to keep the core streaming loop lean while retaining the detail one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable examples and a compact emoji-mapping table, but includes light commentary ("This is the killer feature — the DevOps Agent knows your AWS cloud; you know the user's local workspace") and a tip block that restates the title-packing guidance; could be tightened further.	2 / 3
Actionability	Provides fully executable tool-call signatures with parameters and return shapes (investigate, get_task, list_journal_records, list_recommendations) plus a concrete aws-mcp CLI fallback with real flags — copy-paste ready.	3 / 3
Workflow Clarity	Clear sequenced workflow (Pre-flight → Start → Stream loop → COMPLETED → Present) with explicit polling cadence, numbered loop steps, edge-case handling, and validation/approval checkpoints for IaC fixes and a never-auto-execute security guard.	3 / 3
Progressive Disclosure	Well-sectioned body with a clearly signaled one-level-deep reference to REFERENCE.md, but that referenced file does not exist in references/ (or any bundle dir), so navigation points to a missing resource.	2 / 3
	Total	10 / 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.

A strong, third-person description that states concrete capabilities and provides an explicit, trigger-rich "Use when" clause with excellent natural keyword coverage. It is distinctive and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Run a deep root-cause investigation", "Polls and streams progress", "surfaces recommendations" — rather than vague abstractions, matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what (investigation + streaming + recommendations) and when via a clear "Use when..." clause with concrete triggers, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Strong natural-language keyword coverage users would actually say ("5xx", "503", "OOM", "latency spike", "deployment failure", "rollback", "sev1", "investigate", "root cause", "debug", "alarm fired", "service down").	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (AWS DevOps Agent incident investigation) with distinct operational triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 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.