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

88%

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

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.

An operationally excellent runbook: fully executable commands, a well-sequenced workflow with explicit checkpoints and expected-state validation, and disciplined conciseness. The only structural gap is the complete absence of a progressive-disclosure layer for a 300+ line skill.

Suggestions

Split the failure-patterns table and/or the output JSON schema into a references/ file (e.g. references/failure-patterns.md) referenced with a clear 'See ...' link from the body, keeping SKILL.md as a lean overview.

Trim the explanatory lead-ins (e.g. the 'A snapshot of the current state is hard to read without a baseline' paragraph in Step 8 can collapse to one line) and drop the closing Notes that restate guidance already given in Steps 1, 5, and 6.

Add one or two natural trigger synonyms to the description (e.g. 'agents offline', 'builds stuck waiting for agents') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands, tables, and short annotations with essentially no explanation of concepts Claude already knows. Minor over-explanation remains ('A snapshot of the current state is hard to read without a baseline' lead-in, and the closing Notes partially restating earlier steps). Not 5: a few passages could be trimmed; not 3: there is no substantial unnecessary explanation or padding.	4 / 5
Actionability	Every step ships a copy-paste-ready AWS CLI command with concrete --region/--profile flags, JMESPath projections, computed timestamps, and clearly marked placeholders (<ASG_NAME>, <REGION>), plus a complete output JSON schema. Fully executable and covering the common investigation cases, matching the top anchor.	5 / 5
Workflow Clarity	Eight explicitly sequenced steps with decision logic ('Use whichever stack has instances... for the remaining steps'), expected-state checkpoints and problem indicators in Step 2, a symptom-to-cause mapping table, and a hypothesis-enumeration step feeding alternative_hypotheses output. The one capacity-changing command is constrained by MaxSize and carries an override warning, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), so all content is inline in a ~310-line SKILL.md with clear, navigable section headers. Not 5: there is no reference layer at all, and for a skill this size content like the failure-patterns table or output schema could be offloaded to well-signaled reference files; not 3: the inline content is cohesive runbook material, well-organized and not buried.	4 / 5
	Total	18 / 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: third-person voice, concrete domain and output contract, and an explicit trigger clause with natural symptom phrases. Only minor headroom in action specificity and trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the concrete domain ('AWS infrastructure issues affecting Buildkite build agents (EC2, AutoScaling, Lambda)') and an explicit output contract ('Returns structured JSON to the parent'), giving several specific capabilities with only minor gaps. Not 5: 'Investigates ... issues' is a single action verb covering the work rather than multiple distinct concrete actions; not 3: coverage goes well beyond 1-2 actions via component enumeration and the structured-return behavior.	4 / 5
Completeness	Clearly answers both what ('Investigates AWS infrastructure issues affecting Buildkite build agents... Returns structured JSON') and when ('Triggers when users ask about...') with concrete trigger phrases. Matches the top anchor exactly; the 'when' clause is explicit and symptom-specific, not merely present.	5 / 5
Trigger Term Quality	'Triggers when users ask about build agents not running, EC2 issues, ASG scaling problems, or infrastructure health' provides natural, user-voiced symptom phrases. Not 5: common variations users would actually say ('agents offline', 'builds stuck', 'build agents not connecting') are missing; not 3: keyword coverage is good and symptom-oriented rather than generic.	4 / 5
Distinctiveness Conflict Risk	Clear niche at the intersection of Buildkite build agents and specific AWS services (EC2, AutoScaling, Lambda) with distinct, unlikely-to-collide triggers. Minimal conflict risk with any generic AWS or CI skill.	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: f66c975

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.