CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-clean

Identify and safely remove dead code with test verification

Quality

75%

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 ./.agents/skills/moai-clean/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 is a maximally lean, well-scoped single-line delegation to the 'moai' skill, which is efficient and appropriately minimal. However, it delegates a destructive dead-code-removal operation with no validation guidance and leaves the reader without key details about arguments or expected behavior.

Suggestions

Document the arguments 'clean' accepts (e.g., scope, file targets, dry-run flags) or name where they are documented, since $ARGUMENTS alone gives no invocation guidance.

Add an explicit verification step (e.g., 'confirm tests pass after removal before finalizing') — the description promises test verification but the body contains none, and deletion is destructive.

State what output or summary to report after the delegated skill runs (e.g., what was removed and test results) so the invoking agent can follow up.

DimensionReasoningScore

Conciseness

The body is a single delegation line ('Use Skill("moai") with arguments: clean $ARGUMENTS') with zero padding, background explanation, or filler — every token is functional.

5 / 5

Actionability

The delegation command is concrete and copy-paste executable, but key details are missing: it never states what arguments 'clean' accepts, what the operation does, or what to do with the result. Anchor 3 ('missing key details') fits better than anchor 4 because the gaps go beyond minor for an agent deciding how to invoke it.

3 / 5

Workflow Clarity

The single step is unambiguous, but the skill's stated purpose is removing code — a destructive operation — and the body contains no validation or verification steps (despite the description promising 'test verification'), so the rubric's destructive-operation cap limits this to 3.

3 / 5

Progressive Disclosure

This is an under-50-line skill with no need for external references: the one-line body delegates everything to the 'moai' skill, nothing that belongs in separate files is inlined, and no bundle files exist or are referenced.

5 / 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 clearly and concretely states what the skill does using natural language ('identify and safely remove dead code'), and occupies a distinct niche. Its main weaknesses are the complete absence of when-to-use trigger guidance and missing common synonyms like 'unused code'.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user asks to remove dead code, clean up unused functions or imports, or find unreachable code.'

Include common synonyms such as 'unused code', 'unused imports', or 'code cleanup' to broaden natural trigger coverage.

Replace the filler adverb 'safely' with a concrete guarantee (e.g., 'verifies tests pass before deleting') to sharpen specificity.

DimensionReasoningScore

Specificity

Names the domain ('dead code') with concrete actions — 'Identify', 'remove', and a 'test verification' method — which is more than anchor 3's 1–2 bare actions, though coverage is not comprehensive (no mention of what kinds of dead code, languages, or file types).

4 / 5

Completeness

The 'what' is clearly stated ('Identify and safely remove dead code with test verification'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3.

3 / 5

Trigger Term Quality

'dead code' and 'remove' are natural phrases users would actually say, giving good core keyword coverage, but common synonyms such as 'unused code', 'unused functions/imports', or 'cleanup' are missing.

4 / 5

Distinctiveness Conflict Risk

Dead-code removal is a well-defined niche with distinct triggers, carrying only minor overlap risk with closely related general cleanup or refactoring skills.

4 / 5

Total

15

/

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.

Repository

modu-ai/moai-adk

Path

.agents/skills/moai-clean/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.