CtrlK
BlogDocsLog inGet started
Tessl Logo

chaos-experiment

Create and manage chaos experiments using Harness Chaos Engineering via MCP. Run resilience tests like pod deletion, CPU stress, and network faults. Use when user says "chaos experiment", "chaos engineering", "resilience test", "chaos test", or wants to test system reliability.

63

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude/skills/chaos-experiment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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, concise skill body with clear sequencing and good sectioning, but it falls short on actionability (placeholder-heavy, no concrete experiment definition example) and workflow clarity (destructive operations lack integrated validation checkpoints). Splitting the resource-type and troubleshooting material into referenced files would further improve progressive disclosure.

Suggestions

Provide a concrete, filled-in example of an experiment definition body for the create step so the core action is copy-paste executable rather than a placeholder.

Integrate validation checkpoints directly into the workflow steps (e.g., 'Verify chaos infrastructure is connected before proceeding', 'Confirm the run completed before analyzing results') instead of relegating them to a separate Performance Notes section.

Move the Chaos Resource Types table and/or Troubleshooting into a referenced file (e.g., references/resource-types.md) and link to it from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with no padding about what chaos engineering is; only minor redundancy exists where resource types appear both in the step blocks and the summary table.

4 / 5

Actionability

Steps give concrete MCP tool names and parameter names, but all values are placeholders and the core creation step ('body: <experiment definition>') is underspecified with no concrete filled example, leaving it not copy-paste executable.

3 / 5

Workflow Clarity

Seven steps are clearly sequenced, but chaos experiments are destructive (pod deletion, node drain, EC2 stop) and validation is relegated to a separate 'Performance Notes' section rather than integrated as explicit checkpoints in the workflow, triggering the destructive-operation cap at 3.

3 / 5

Progressive Disclosure

No bundle files exist and all ~133 lines are inline, but content is well-organized into clearly headed sections with easy navigation; the resource-type reference and troubleshooting could be split out, leaving minor organization gaps.

4 / 5

Total

14

/

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 capabilities, gives concrete fault-type examples, and provides explicit user-facing trigger phrases in third-person voice. Minor gaps in fault-type enumeration and synonyms keep specificity and trigger-term quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Create and manage chaos experiments', 'Run resilience tests like pod deletion, CPU stress, and network faults'), with minor coverage gaps since only a few fault types are enumerated.

4 / 5

Completeness

Explicitly answers both what ('Create and manage chaos experiments... Run resilience tests...') and when ('Use when user says...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes several natural trigger phrases users would say ('chaos experiment', 'chaos engineering', 'resilience test', 'chaos test', 'test system reliability'), though a few synonyms like 'fault injection' are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Harness Chaos Engineering via MCP) with distinct, domain-specific triggers, yielding minimal conflict risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
harness/harness-ai
Reviewed

Table of Contents

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.