troubleshooting-application-failures

Troubleshoots failing applications by discovering and analyzing CloudWatch log groups to identify error patterns, root causes, and actionable solutions. Use when an application is experiencing failures and log-based diagnosis is needed.

Quality

86%

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

72%

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

A clean, well-disclosed overview that delegates detail to a single real, non-nested reference with no concept padding. Its weakness is that the main procedure is delegated rather than surfaced, so the body itself offers only moderate actionability and no inline sequenced workflow.

Suggestions

Add a brief inline numbered outline of the troubleshooting procedure (discover log groups → search errors → analyze stack traces → recommend remediation) so the body conveys the workflow sequence even before the reader opens the reference.

Surface at least one concrete executable command in the body (e.g., the `aws logs describe-log-groups` query) to lift actionability beyond the troubleshooting tips.

Tighten or repurpose the Overview, which restates the frontmatter description, to avoid mild redundancy with the description field.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids teaching concepts Claude already knows; it does not over-explain what CloudWatch or logs are. The Overview briefly restates scope but stays tight.	3 / 3
Actionability	Troubleshooting subsections give concrete specifics (log group patterns, exact IAM permission names), but the core procedure is delegated to the reference rather than given as inline executable guidance, leaving the body's central instruction indirect.	2 / 3
Workflow Clarity	The body points to a sequenced procedure ("follow the procedure exactly. See...") but does not present the multi-step sequence or validation checkpoints inline; structure is implied via the reference rather than shown.	2 / 3
Progressive Disclosure	The body is a concise overview with a single, clearly signaled, one-level-deep reference (references/application-failure-troubleshooting.md) that exists and contains no nested references, matching the well-organized, easy-navigation anchor.	3 / 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 names concrete actions and provides an explicit Use-when trigger, clearly answering both what and when. It is concise without fluff and occupies a distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "discovering and analyzing CloudWatch log groups", "identify error patterns, root causes, and actionable solutions" — specific rather than vague.	3 / 3
Completeness	Explicitly answers both what (discover/analyze log groups, identify patterns, root causes, solutions) and when ("Use when an application is experiencing failures and log-based diagnosis is needed").	3 / 3
Trigger Term Quality	Uses natural user-facing terms ("failing applications", "application is experiencing failures", "log-based diagnosis", "error patterns") alongside the technical CloudWatch anchor, giving good coverage of phrasings a user would say.	3 / 3
Distinctiveness Conflict Risk	The CloudWatch log-based failure diagnosis niche is clearly scoped with distinct triggers, making overlap with unrelated skills unlikely.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/operations-skills/troubleshooting-application-failures/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.