CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-loop

Iteratively fix issues until all resolved or max iterations reached

Quality

68%

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

Quality

Content

80%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 delegation stub: perfectly concise and cleanly structured, with a concrete invocation command. Its weakness is that the iterative loop it advertises has no stated termination criteria, validation checkpoint, or argument documentation, leaving the workflow dependent entirely on the delegated moai skill.

Suggestions

Add one line defining the loop's termination: what counts as "all resolved" and the default/max iteration count, so the workflow has an explicit checkpoint.

Document the expected form of $ARGUMENTS (e.g. an optional max-iterations value or target scope) so the invocation is copy-paste ready for common cases.

Optionally note how to verify each iteration's outcome (re-run the check that surfaced the issue) to give the loop a validation step.

DimensionReasoningScore

Conciseness

The entire body is one line — "Use Skill("moai") with arguments: loop $ARGUMENTS" — with zero padding and no explanation of concepts Claude already knows, matching "Lean and efficient; assumes Claude's competence; every token earns its place".

5 / 5

Actionability

"Use Skill("moai") with arguments: loop $ARGUMENTS" is a concrete, executable command rather than vague direction, matching "Mostly executable guidance; concrete code or commands with minor gaps". It falls short of anchor 5 because $ARGUMENTS is an unexplained placeholder and there is no coverage of what valid arguments or common invocations look like.

4 / 5

Workflow Clarity

The single delegation action is unambiguous (invoke the moai skill with loop arguments), but the skill's stated purpose — "Iteratively fix issues until all resolved or max iterations reached" — has no sequenced steps, no validation checkpoint for what counts as "resolved", and no definition of the iteration cap, matching "Steps listed but validation gaps; sequence present but checkpoints missing or implicit". Not anchor 2 because the one action it does specify is precise; not anchor 4 because the loop's termination criteria are entirely undefined here.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and its single pointer to Skill("moai") is clearly signaled and exactly one level deep, matching the simple-skill exception where a well-organized minimal structure scores 5. There are no bundle files to misorganize.

5 / 5

Total

17

/

20

Passed

Description

41%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 conveys a clear looping behavior but is held back by a missing "Use when..." trigger clause, generic action language, and high overlap risk with other issue-fixing skills. Adding explicit trigger phrases and naming the target domain would raise most dimensions.

Suggestions

Add a "Use when..." clause with concrete triggers, e.g. "Use when the user asks to loop, retry, or iteratively fix issues until everything passes."

Name the domain of the issues (e.g. build errors, test failures, review comments) to improve specificity and reduce conflict risk with other fixing/debugging skills.

Include natural trigger synonyms such as "loop", "iterate", "retry until fixed" so users' phrasing matches the description.

DimensionReasoningScore

Specificity

"fix issues" is a single generic action and no domain is named (issues of what? code? tests? build errors?), matching "Names the domain but actions are minimal or generic". It does not reach anchor 3 because there is no domain plus 1-2 concrete actions, and it is above anchor 1 because at least one action and a loop condition are stated.

2 / 5

Completeness

The description answers "what" ("Iteratively fix issues until all resolved or max iterations reached") but contains no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is above anchor 2 because the "what" is reasonably clear, and below anchor 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"fix issues", "iteratively", and "max iterations" are relevant keywords a user might say, but common variations like "loop", "retry", "iterate until done", or "keep fixing" are missing, matching "Some relevant keywords but missing common variations or synonyms". Not anchor 2 because the terms are more specific than generic filler like "works with files"; not anchor 4 because coverage is thin with no synonyms.

3 / 5

Distinctiveness Conflict Risk

"fix issues" is very broad and would overlap with virtually any debugging, repair, or code-fixing skill, matching "Very broad; high overlap risk with many similar skills". It is above anchor 1 because the loop/iteration framing is more specific than "helps with code and documents", but below anchor 3 because nothing anchors it to a distinct niche.

2 / 5

Total

10

/

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-loop/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.