CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

setup-knip

Install and configure Knip for dead code detection. Use before running dead-code-hunter or dependency-auditor to ensure Knip is available. Handles installation, configuration creation, and validation.

60

Quality

76%

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 ./.claude/skills/setup-knip/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 body delivers highly actionable, well-sequenced setup instructions with strong safety guidance around destructive flags, and the workflow validates its own result. Its weaknesses are redundancy (examples re-printing outputs, notes repeating the command table) and a monolithic structure that should offload examples and the command reference to bundle files.

Suggestions

Move the three Examples walkthroughs and the Knip Command Reference table into a references/ file (e.g., references/examples.md and references/commands.md), keeping SKILL.md as a lean overview with one-level-deep, clearly signaled links.

Consolidate the redundant JSON result outputs: keep the schema once in Step 7 and have the examples show only the fields that differ (config_created, scripts_added, project_type) instead of re-printing full objects.

Drop or deduplicate the Notes section items that restate the command reference table, and replace pinned version strings ("5.73.3", "5.x.x") with a version-agnostic statement so the content does not go stale.

DimensionReasoningScore

Conciseness

The body is mostly lean and free of basic-concept padding, but the three Examples re-print full JSON outputs nearly identical to Step 7's expected output, the Notes section repeats the command reference table, and pinned versions ("5.73.3") sit outside any deprecation section. It could be meaningfully tightened, which matches anchor 3 better than 4.

3 / 5

Actionability

Executable package-manager detection bash, `npm pkg set` commands, complete JSON configs for standard/Next.js/monorepo cases, and `npx knip --help` validation make the guidance largely copy-paste ready. Below 5 because Step 1's block is a comment placeholder ("# Read package.json and check for knip") rather than a runnable command.

4 / 5

Workflow Clarity

Seven well-sequenced steps with check logic and an explicit validation step, plus the destructive-flag safety cap. Not 5 because the anchor requires feedback loops for error recovery — the Error Handling section says to "return error" without a validate-fix-retry loop.

4 / 5

Progressive Disclosure

No bundle files exist and this is a 370-line monolith where the three example walkthroughs and the Knip command reference table clearly belong in separate reference files. Section headers give internal structure, but content that should be separate is inline, matching anchor 3.

3 / 5

Total

14

/

20

Passed

Description

78%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: specific, third-person, with an explicit use-when clause and a distinctive tool name. Its main limitations are the narrow agent-oriented trigger framing and missing common synonyms for dead code detection.

DimensionReasoningScore

Specificity

"Install and configure Knip for dead code detection" and "Handles installation, configuration creation, and validation" list several concrete, domain-specific actions in third-person voice. Not the 5 anchor because coverage is not comprehensive — script setup and project-type detection go unmentioned.

4 / 5

Completeness

The what is clear ("Handles installation, configuration creation, and validation") and the when is explicit ("Use before running dead-code-hunter or dependency-auditor"). Below 5 because the when is scoped to internal agent names rather than user-side trigger phrases (e.g., "when the user mentions dead code").

4 / 5

Trigger Term Quality

"Knip", "dead code detection", "dead-code-hunter", "dependency-auditor" are natural, relevant terms. Below 5 because common user phrasings like "unused dependencies", "unused exports", or "dead code removal" are missing.

4 / 5

Distinctiveness Conflict Risk

"Knip" is a highly distinctive tool name and the niche (setup tooling for dead-code detection) is unambiguous, so it would rarely trigger for the wrong skill.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

maslennikov-ig/claude-code-orchestrator-kit

Path

.claude/skills/setup-knip/SKILL.md

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.