CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-mx

Scan codebase and add @MX code-level annotations for AI context

Quality

74%

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-mx/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is a lean, executable delegation stub that forwards to the moai skill with no wasted tokens. Its only weaknesses are minor: no example invocation and no explanation of what the mx arguments accept.

DimensionReasoningScore

Conciseness

The body is a single delegation line — "Use Skill("moai") with arguments: mx $ARGUMENTS" — with zero padding and no concepts Claude doesn't already know. Every token earns its place, matching anchor 5 exactly.

5 / 5

Actionability

The instruction is a concrete, executable command (an exact Skill invocation with arguments), but there is no example of a typical invocation or argument shape — a minor gap versus anchor 5's copy-paste-ready coverage of common cases. It clearly exceeds anchor 3, which requires pseudocode or missing key details.

4 / 5

Workflow Clarity

The single action — delegate to the moai skill — is unambiguous, which the simple-skill rule could score 5. However, the semantics of the "mx $ARGUMENTS" passthrough are never explained, leaving the minor gap described by anchor 4 rather than a fully self-evident 5.

4 / 5

Progressive Disclosure

Delegation is one level deep and cleanly signaled, and nothing is inlined that belongs elsewhere (no bundle files exist). The under-50-line rule awards 5 only with well-organized sections, and the body has no section structure at all, so anchor 4 fits best; anchor 3 would require content that should be separate being inline, which is not the case.

4 / 5

Total

17

/

20

Passed

Description

53%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 names a distinct, concrete purpose but is bare-bones: no use-when triggers, unexplained "@MX" jargon, and an unspecified outcome for "AI context". It sits just above the midpoint — serviceable but leaving triggering to chance.

Suggestions

Add a "Use when..." clause with concrete trigger phrases (e.g., "Use when the user asks to add MX annotations, annotate the codebase for AI, or prepare code for AI context").

Replace or unpack the opaque "@MX" jargon with a plain-language gloss so users and Claude can recognize when it applies.

Specify the outcome of the scan/annotation step — what the annotations look like and where they land — so the "what" is fully concrete.

DimensionReasoningScore

Specificity

"Scan codebase" and "add @MX code-level annotations" name the domain plus two concrete actions, but coverage stops there — no output format, annotation types, or explanation of "AI context". It does not reach anchor 4's 'several specific actions' and exceeds anchor 2's minimal/generic actions.

3 / 5

Completeness

The "what" is stated (scan and annotate code), but no "when" guidance exists at all, which the judging guidelines explicitly cap at 3. Not anchor 4, which requires both what and when; not anchor 2, since the what is concrete rather than vague.

3 / 5

Trigger Term Quality

"codebase", "annotations", and "scan" are relevant keywords a user might echo, but common variations and synonyms ("annotate code", "code comments", file types) are absent and "@MX" is opaque jargon. Anchor 4's good keyword coverage is not met, but it offers more than the one or two generic keywords of anchor 2.

3 / 5

Distinctiveness Conflict Risk

"@MX code-level annotations" carves a fairly distinct niche unlikely to trigger for unrelated skills, with only minor overlap risk against generic code-documentation skills. It falls short of anchor 5's clear niche with distinct triggers because the trigger vocabulary is too thin.

4 / 5

Total

13

/

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-mx/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.