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.

81

4.84x
Quality

73%

Does it follow best practices?

Impact

92%

4.84x

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

93%

73%

Agent Greeting Test

Test structure and mock-llm configuration

Criteria
Without context
With context

Required directory files

40%

100%

Manifests subfolder

100%

100%

Alphanumeric manifest prefixes

0%

100%

Resource ordering

0%

50%

terminationGracePeriodSeconds

0%

100%

mock-llm ark.model config

0%

100%

Echo pattern in mock-llm

0%

100%

Short assert timeouts

0%

62%

Catch block with events

0%

100%

Catch block with describe

100%

100%

JMESPath contains assertion

0%

100%

Correct API version

0%

100%

84%

58%

Dynamic Parameter Injection Test

Helm install steps and manifest ordering

Criteria
Without context
With context

mock-llm OCI chart URL

0%

100%

mock-llm chart version

0%

100%

ark-tenant RBAC install

0%

100%

Manifest alphanumeric prefixes

0%

100%

Model before Agent in manifests

0%

0%

Model availability assertion

0%

100%

Glob pattern for manifest chunks

0%

0%

Query parameter in Agent prompt

100%

100%

Query supplies parameter value

100%

100%

JMESPath response validation

100%

100%

Correct Ark API version

0%

100%

100%

88%

Ark Test Suite Runbook

Test execution and debug workflows

Criteria
Without context
With context

Standard suite selector flag

0%

100%

Standard suite run from tests dir

0%

100%

Specific test fail-fast flag

0%

100%

Debug skip-delete flag

0%

100%

Debug pause-on-failure flag

100%

100%

Real LLM key env var

0%

100%

Real LLM endpoint env var

0%

100%

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.