chaos-engineer

Designs chaos experiments, creates failure injection frameworks, and facilitates game day exercises for distributed systems — producing runbooks, experiment manifests, rollback procedures, and post-mortem templates. Use when designing chaos experiments, implementing failure injection frameworks, or conducting game day exercises. Invoke for chaos experiments, resilience testing, blast radius control, game days, antifragile systems, fault injection, Chaos Monkey, Litmus Chaos.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

This is a strong skill with excellent actionability — three complete, executable examples covering different chaos engineering tools with real commands and manifests. The workflow is clear with proper validation checkpoints and safety controls. The main weaknesses are the missing bundle files that the reference table points to, and the somewhat heavy inline content that could benefit from being split into the referenced files for better progressive disclosure.

Suggestions

Create the referenced bundle files (references/experiment-design.md, references/infrastructure-chaos.md, etc.) and move the detailed concrete examples into them, keeping only one brief example in SKILL.md as a quick-start illustration.

Consider moving the toxiproxy and Chaos Monkey examples into references/chaos-tools.md to keep the main SKILL.md leaner as an overview document.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and avoids explaining basic concepts Claude already knows. However, there's some redundancy between the 'Output Templates' section and the reference table, and the Chaos Monkey config example includes comments that are somewhat obvious. The safety checklist and workflow are tight, but overall it could be trimmed slightly.	2 / 3
Actionability	The skill provides fully executable, copy-paste-ready examples across three different tools (Litmus Chaos, toxiproxy, Chaos Monkey) with complete YAML manifests, bash commands, and specific configuration values. The examples cover the full lifecycle from setup through monitoring to rollback.	3 / 3
Workflow Clarity	The core workflow is clearly sequenced in 5 steps, and the concrete Litmus example demonstrates explicit validation checkpoints: verify baseline first, monitor during experiment, check ChaosResult verdict, and a clear rollback/abort procedure with confirmation step. The safety checklist enforces automated rollback ≤ 30 seconds and steady-state verification, providing strong feedback loops.	3 / 3
Progressive Disclosure	The reference table with 5 topic-specific files is well-structured and clearly signaled with 'Load When' guidance. However, no bundle files were provided, meaning all referenced files (references/experiment-design.md, etc.) are missing. The inline content is also fairly long with three full examples that could potentially be in reference files, making the SKILL.md heavier than ideal for an overview document.	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.

This is a strong skill description that clearly defines its domain (chaos engineering), lists specific concrete actions and deliverables, provides explicit 'Use when' guidance, and includes a comprehensive set of natural trigger terms. The description is well-structured, uses third person voice correctly, and occupies a distinct niche that minimizes conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: designs chaos experiments, creates failure injection frameworks, facilitates game day exercises, and specifies concrete outputs (runbooks, experiment manifests, rollback procedures, post-mortem templates).	3 / 3
Completeness	Clearly answers both 'what' (designs chaos experiments, creates failure injection frameworks, produces runbooks/manifests/rollback procedures/post-mortem templates) and 'when' (explicit 'Use when' clause plus 'Invoke for' with specific trigger terms).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'chaos experiments', 'resilience testing', 'blast radius', 'game days', 'fault injection', 'Chaos Monkey', 'Litmus Chaos', 'antifragile systems'. These cover both conceptual and tool-specific terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche — chaos engineering is a well-defined domain that is unlikely to overlap with other skills. Terms like 'Chaos Monkey', 'Litmus Chaos', 'blast radius control', and 'game days' are very specific to this domain.	3 / 3
	Total	12 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: Jeffallan/claude-skills
Commit: e8be415

Reviewed: 4 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.