ark-chainsaw-testing

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

1.37x

Quality

71%

Does it follow best practices?

Impact

95%

1.37x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/chainsaw/SKILL.md

Quality

Content

77%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.

The content is highly actionable and concise, with strong executable examples and clear antipattern guidance. Progressive disclosure is the weakest point because the referenced files (examples.md, tests/CLAIDE.md) are not present in the bundle to verify.

Suggestions

Add the referenced examples.md (and a pointer to tests/CLAUDE.md) to the bundle so the signaled navigation actually resolves.

Add an explicit validation/verification step in the running-tests flow (e.g., 'after tests pass, confirm no resources remain with --skip-delete') to strengthen the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable snippets and minimal over-explanation, though the antipattern sections restate some context (e.g., why a watch beats polling) that could be trimmed slightly.	4 / 5
Actionability	It provides copy-paste-ready commands and complete YAML examples covering running tests, debugging, and each antipattern with explicit good/bad contrasts.	5 / 5
Workflow Clarity	Running/debugging/writing flows are clearly sequenced with concrete commands, and the assert-vs-wait guidance includes explicit separate-step sequencing; however the destructive/batch operations cap is respected because test runs lack an explicit validate-then-proceed feedback loop.	4 / 5
Progressive Disclosure	Structure is reasonable with signaled references to tests/CLAIDE.md and examples.md, but those referenced files are absent from the bundle, so navigation cannot be verified and some detail that could live in references is inlined.	3 / 5
	Total	16 / 20 Passed

Description

66%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.

The description is specific and distinct, clearly stating both what the skill does and when to use it. Its main weakness is trigger-term coverage, which leans on technical jargon (Chainsaw, mock-llm) rather than natural user phrases.

Suggestions

Add natural-language trigger phrases a user would actually say (e.g., 'Use when the user mentions Chainsaw tests, Ark e2e tests, or asks to fix a failing test').

Consider listing file extensions or command names (e.g., 'chainsaw test') as explicit triggers to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Chainsaw e2e tests) and lists several concrete actions ('running tests, debugging failures, or creating new e2e tests') with only minor coverage gaps (writing/editing is implied but not all verbs distinct).	4 / 5
Completeness	It states both what (run and write Ark Chainsaw tests with mock-llm) and when ('Use for running tests, debugging failures, or creating new e2e tests'); the 'when' is explicit but could be tied to more specific user phrases.	4 / 5
Trigger Term Quality	It includes 'running tests', 'debugging failures', and 'e2e tests' which a user might say, but misses common synonyms and the explicit 'Chainsaw' trigger term is technical jargon a user may not naturally voice.	3 / 5
Distinctiveness Conflict Risk	The 'Ark Chainsaw' niche with mock-llm is highly specific with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: mckinsey/agents-at-scale-ark
Path: .claude/skills/chainsaw/SKILL.md
Commit: 26d4d0b

Reviewed: 3 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.