CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-fix

Auto-detect and fix LSP errors, linting issues, and type errors

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-fix/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 maximally lean and perfectly structured as a delegation wrapper — one clearly signaled hop to the moai skill. However, its extreme minimalism leaves actionability thin (unexplained $ARGUMENTS, no examples) and provides no verification guidance for the batch code-fixing it triggers.

Suggestions

Add one or two example invocations showing typical "fix" arguments so the $ARGUMENTS placeholder is actionable rather than opaque.

State the expected outcome of "fix" (e.g. edits applied to the current file/project) so the wrapper conveys what the delegated skill will do.

Include a brief post-fix verification step (e.g. re-run diagnostics or tests to confirm errors are resolved) to satisfy the workflow-clarity requirement for batch fix operations.

DimensionReasoningScore

Conciseness

The body is a single lean line — "Use Skill("moai") with arguments: fix $ARGUMENTS" — with zero padding and no explanation of concepts Claude already knows, fully matching anchor 5 ('Lean and efficient; every token earns its place').

5 / 5

Actionability

The line is a concrete, specific invocation command naming the exact skill and argument format, but it is incomplete per anchor 3: "$ARGUMENTS" is never explained, no example invocations are given, and there is no detail on what "fix" does or what happens on failure. It is not anchor 4 because these are key details, not minor gaps — the command cannot be confidently executed beyond blind forwarding.

3 / 5

Workflow Clarity

The single delegation step is unambiguous, but the skill drives batch auto-fixing of code (LSP/lint/type errors across files) and the body contains no validation or verification guidance (e.g. re-checking diagnostics or running tests after fixes), which caps workflow clarity at 3 per the judging guidelines. It stays at 3 rather than lower because the one step that is present is clearly sequenced.

3 / 5

Progressive Disclosure

This is a pure forwarder: all detail lives exactly one level deep in the "moai" skill, clearly signaled by the invocation line, and nothing that belongs elsewhere is inlined. For a minimal wrapper under 50 lines with no bundle files, this matches anchor 5's clear one-level-deep reference structure.

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 is concise and concrete, clearly naming what the skill does across three well-chosen error categories, with natural trigger terms. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness and limits its value for skill selection.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to fix lint errors, type errors, LSP diagnostics, or code errors, or mentions squiggles/warnings in the editor."

Include common synonyms such as "diagnostics", "compiler errors", and "warnings" so natural variations of the request match the description.

Briefly state the fix scope (e.g. current file or whole project) to sharpen specificity and reduce overlap with related code-fixing skills.

DimensionReasoningScore

Specificity

"Auto-detect and fix LSP errors, linting issues, and type errors" names concrete actions (detect, fix) across three specific problem categories, matching anchor 4 ('Lists several specific actions; minor gaps in coverage'). It falls short of anchor 5 because scope is unspecified — no mention of languages, tools, file vs project range, or how fixes are applied.

4 / 5

Completeness

The "what" is clear (auto-detect and fix three categories of code errors) but there is no "Use when..." clause or equivalent trigger guidance, which the judging guidelines cap at 3. It does not fall to anchor 2 because the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

"LSP errors", "linting issues", and "type errors" are phrases users naturally say when they need this skill, giving good keyword coverage per anchor 4. It is not anchor 5 because common synonyms and variations are missing — e.g. "diagnostics", "compiler errors", "warnings", "lint", "quickfix".

4 / 5

Distinctiveness Conflict Risk

The LSP/lint/type-error fixing niche is mostly distinct from document, data, and writing skills, matching anchor 4 ('Mostly distinct; minor overlap risk'). It is not anchor 5 because "fix errors" requests could also route to closely related coding skills (e.g. code review or refactoring helpers).

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-fix/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.