CtrlK
BlogDocsLog inGet started
Tessl Logo

ark-chainsaw-testing

Run and write Ark Chainsaw tests with mock-llm. Use for running tests, debugging failures, or creating new e2e tests.

82

1.37x
Quality

73%

Does it follow best practices?

Impact

95%

1.37x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/chainsaw/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

78%

Add Chainsaw Test for Custom Metrics CRD Installation

CRD readiness anti-pattern

Criteria
Without context
With context

No kubectl wait for CRD

0%

100%

Chainsaw assert for CRD readiness

0%

100%

JMESPath Established condition

0%

100%

Assert checks Established status True

0%

100%

Assert targets CustomResourceDefinition

0%

100%

No shell condition script

100%

100%

Manifests numeric prefix naming

40%

100%

Catch block with events

0%

100%

README.md present

100%

100%

Correct test directory structure

100%

100%

95%

Write an Ark Query Response Validation Test

Query wait vs assert pattern

Criteria
Without context
With context

Uses wait for Query completion

100%

100%

Wait uses Completed condition

100%

100%

Wait condition value True

100%

100%

No assert before wait

100%

100%

Post-completion assert is separate step

100%

100%

JMESPath in response assert

100%

100%

Catch block with events

100%

100%

Catch block with describe

100%

100%

Wait has timeout

100%

100%

Mock-llm short timeout

0%

0%

91%

New Ark Agent Smoke Test with Mock LLM

Test structure and shell script avoidance

Criteria
Without context
With context

chainsaw-test.yaml present

100%

100%

mock-llm-values.yaml present

100%

100%

README.md present

100%

100%

manifests/ subdirectory present

100%

100%

Manifest numeric prefix ordering

100%

100%

Agent manifest before Query manifest

100%

100%

No kubectl get jq script

100%

100%

Chainsaw assert for resource state

100%

100%

Catch block with events

100%

100%

Catch block with describe

100%

100%

Mock-llm assert timeout short

0%

0%

Repository
mckinsey/agents-at-scale-ark
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.