aws-investigation

Investigates AWS infrastructure issues affecting Buildkite build agents (EC2, AutoScaling, Lambda). Returns structured JSON to the parent for formatting. Triggers when users ask about build agents not running, EC2 issues, ASG scaling problems, or infrastructure health.

Quality

85%

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.

A well-structured, highly actionable investigation runbook with copy-paste-ready commands and a clear sequenced workflow. Main weaknesses are minor verbosity in the reasoning prose and a fully inline structure that could benefit from splitting reference material into bundle files.

Suggestions

Trim the explanatory prose in 'Enumerate Competing Hypotheses' (e.g. the 'correlation is not causation' aside) to rely on Claude's existing reasoning ability.

Add an explicit post-action validation step to the 'Emergency: Manually Scale Up Agents' section (e.g. re-run the Step 2 health check to confirm instances reached InService).

Consider moving the large structured JSON output schema and/or the failure-pattern table into a reference file under ./references/ to reduce the inline SKILL.md footprint.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean commands and tables assuming Claude knows AWS CLI basics, but includes a few over-explanatory asides (e.g. 'correlation is not causation' in the hypotheses section) that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready AWS CLI commands with real --query/--region/--profile flags and documented placeholders (<ASG_NAME>, <REGION>), plus a failure-pattern table mapping symptoms to investigation steps covering the common cases.	5 / 5
Workflow Clarity	Steps 1-8 are clearly sequenced with decision points and expected-vs-problem indicators as checkpoints, but the mutating 'Emergency: Manually Scale Up' section has a pre-guard yet lacks an explicit post-action validation/feedback loop.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references, but the ~310-line body is entirely monolithic with the large JSON output schema and failure patterns inlined that could be externalized into reference files.	4 / 5
	Total	17 / 20 Passed

Description

87%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 clearly states what the skill does and when it triggers, using third-person voice and concrete domain terms. Minor improvements possible by adding more action verbs and common user synonyms.

Dimension	Reasoning	Score
Specificity	Names the concrete domain (EC2, AutoScaling, Lambda, Buildkite build agents) and two specific actions ('Investigates', 'Returns structured JSON'), with comprehensive service coverage but only two verbs, leaving minor gaps versus the multi-action anchor 5.	4 / 5
Completeness	Explicitly states both what it does ('Investigates AWS infrastructure issues... Returns structured JSON') and when to use it ('Triggers when users ask about...') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	'Triggers when users ask about build agents not running, EC2 issues, ASG scaling problems, or infrastructure health' gives good natural keyword coverage, but misses common synonyms users might say (e.g. 'agents down', 'builds stuck').	4 / 5
Distinctiveness Conflict Risk	The niche is highly specific (AWS infra for Buildkite build agents across EC2/ASG/Lambda) with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	18 / 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: mock-server/mockserver-monorepo
Path: .opencode/skills/aws-investigation/SKILL.md
Commit: 817ee95

Reviewed: 1 day 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.