CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/knip-dead-code

Use after a feature or route is deleted and the project still compiles, or when package.json has dependencies nobody can explain. Runs Knip on a JS/TS project to find unused files, dependencies, exports and class or enum members, aware of test entry points through its framework plugins.

Quality

90%

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

Overview
Quality
Evals
Security
Files

Quality

Content

82%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 highly actionable, well-structured skill with concrete commands and thoughtful triage/anti-pattern guidance for a destructive-adjacent workflow. Weaknesses are minor: some repeated link phrasing, no explicit re-run verification after cleanup, and opportunities to offload detail into reference files.

Suggestions

Add an explicit verification step after triage (e.g., 'Re-run npx knip after deletions; exit code 0 confirms clean') to close the feedback loop for this deletion workflow.

Remove the repeated 'Per the [Knip docs]' filler phrases and the redundant References section that re-lists links already used inline.

Consider moving the framework-plugin configuration examples and the anti-patterns table into a references/ file to reduce the main SKILL.md footprint.

DimensionReasoningScore

Conciseness

Largely lean and free of concept explanations Claude already knows, but 'Per the [Knip docs]' is repeated three times and the References section re-lists links already referenced inline — minor redundancy that could be trimmed.

4 / 5

Actionability

Fully executable throughout: 'npm init @knip/config', 'npx knip', a complete knip.json example, '--max-show-issues 5', the CI YAML snippet, and the baseline command 'npx knip --no-exit-code > knip-baseline.txt' are all copy-paste ready.

5 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced with a per-issue triage table and anti-patterns guarding against destructive false-positive deletion, but there is no explicit feedback loop of re-running Knip after cleanup to confirm zero remaining findings — a relevant checkpoint for a deletion workflow.

4 / 5

Progressive Disclosure

Well-organized single-file skill (no bundle files exist) with clearly signaled one-level-deep external references to the Knip docs and plugins page; minor gap in that plugin configuration detail and the anti-patterns table could be split into a reference file to keep the overview slimmer.

4 / 5

Total

17

/

20

Passed

Description

92%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 with explicit and concrete trigger conditions, third-person voice, and comprehensive enumeration of capabilities. The only gap is missing common synonyms like 'dead code' that a user might naturally say.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions comprehensively: 'find unused files, dependencies, exports and class or enum members, aware of test entry points through its framework plugins' — this covers Knip's full finding taxonomy rather than just a few actions.

5 / 5

Completeness

Explicitly answers both: 'when' via 'Use after a feature or route is deleted... or when package.json has dependencies nobody can explain' and 'what' via 'Runs Knip on a JS/TS project to find unused files, dependencies, exports...'.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say ('feature or route is deleted', 'project still compiles', 'dependencies nobody can explain', 'unused dependencies'), but misses common synonyms like 'dead code' or 'orphaned files'.

4 / 5

Distinctiveness Conflict Risk

Names the tool (Knip) and a distinct niche (JS/TS dead-code detection) with trigger scenarios unlikely to overlap with other skills.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

On this page