CtrlK
BlogDocsLog inGet started
Tessl Logo

moyu

Anti-over-engineering guardrail that activates when an AI coding agent expands scope, adds abstractions, or changes files the user did not request.

59

Quality

69%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/moyu/SKILL.md

The canonical home for this skill is moyu in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-structured, actionable anti-over-engineering guardrail with concrete rules, a pre-delivery checklist, and a tiered escalation workflow. Its main weaknesses are redundancy between the two large anti-pattern tables and the inlining of reference material that could be split into a bundled reference file.

Suggestions

Merge or deduplicate the 'Grinding vs Moyu' tables and the 'Anti-Grinding Table' into a single reference table to remove overlapping content and tighten token use.

Move the consolidated anti-pattern reference table into a bundled references/ file (e.g. ANTI_PATTERNS.md) and link to it from SKILL.md, keeping the body as a lean overview plus the checklist and L1–L4 levels.

DimensionReasoningScore

Conciseness

Mostly efficient prescriptive guidance that assumes Claude's competence (no basic-concept padding), but the 'Grinding vs Moyu' tables and the 'Anti-Grinding Table' cover heavily overlapping anti-patterns, creating notable redundancy that could be tightened; not a 4 because the duplication is more than minor.

3 / 5

Actionability

Concrete, specific behavioral rules ('If one line solves it, write one line', 'Touch only the code the user pointed to'), a runnable pre-delivery checklist, and explicit L1–L4 triggers with actions; not a 5 because, as an instruction-only skill, guidance is behavioral rather than copy-paste executable code.

4 / 5

Workflow Clarity

The L1–L4 detection levels give a clearly sequenced escalation (detect → intervene → verify) and the Moyu Checklist is an explicit pre-delivery validation checkpoint; not a 5 because it is a behavioral framework rather than a strict validate→fix→retry loop with error-recovery feedback.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and no nested references, but at ~250 lines the large inline anti-pattern tables (Grinding vs Moyu plus Anti-Grinding Table) are reference material that could live in a separate reference file; not a 4 because content that should be split out is inlined and no references are signaled.

3 / 5

Total

14

/

20

Passed

Description

75%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 focused, third-person description that clearly names its niche and gives three concrete activation triggers. It answers both what and when, though the 'when' is framed as agent behavior rather than an explicit user-facing 'Use when...' clause.

Suggestions

Add an explicit user-facing trigger clause, e.g. 'Use when the AI agent is over-reaching, adding unrequested abstractions, or expanding scope beyond the request.'

Include common synonyms users say ('scope creep', 'YAGNI', 'over-refactoring') to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Names the domain ('anti-over-engineering guardrail') and three concrete trigger actions ('expands scope, adds abstractions, or changes files the user did not request'), matching the 'lists several specific actions' anchor; not a 5 because coverage of what the guardrail actually does is implicit rather than comprehensive.

4 / 5

Completeness

Both 'what' (anti-over-engineering guardrail) and 'when' (activates when an agent expands scope/adds abstractions/changes unrequested files) are present with concrete triggers; not a 5 because the 'when' is framed as agent auto-activation rather than an explicit user-facing 'Use when...' clause.

4 / 5

Trigger Term Quality

Natural terms like 'over-engineering', 'expands scope', 'adds abstractions', and 'changes files the user did not request' are phrases a user would plausibly say; not a 5 because common synonyms (scope creep, YAGNI, refactor) are absent.

4 / 5

Distinctiveness Conflict Risk

The anti-over-engineering/scope-control niche is clearly distinct with specific triggers; not a 5 because there is minor overlap risk with general restraint/code-review skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.