moai-foundation-quality

TRUST 5 quality principles and how MoAI enforces them through agents, the 3-level harness, /moai gate, and sync-auditor scoring. Use for code review, quality gate checks, coverage targets, or TRUST 5 compliance.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/moai-foundation-quality/SKILL.md

Quality

Content

56%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 well-organized with a clear phase/cycle model and concrete commands, but it is held back by philosophical padding and by a progressive-disclosure structure that references module files which are absent from the bundle. Tightening the prose and either shipping or removing the missing module references would lift the score meaningfully.

Suggestions

Ship the referenced modules/*.md files (or remove the links and inline the essential content) so the progressive-disclosure structure is actually navigable; currently 4 of 6 referenced paths 404.

Fix the broken reference.md anchor link ('#language-aware-toolkchains' has no matching heading in reference.md) and verify every body link resolves.

Trim the Common Rationalizations table and the Chesterton's Fence / Shift Left aphorisms, and remove the duplicated 'MoAI does NOT ship a quality-validation library' statement, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's baseline knowledge, but it restates 'MoAI does NOT ship a quality-validation library' twice and includes philosophical padding (the Common Rationalizations table, Chesterton's Fence and Shift Left aphorisms) Claude already knows, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It gives concrete commands (/moai gate, /moai fix, /moai loop), thresholds (zero errors, max 10 warnings, 85%+ coverage), and a language-to-tool table, but the per-cycle and per-principle mechanics are deferred to module files that do not exist, leaving the actionable core incomplete.	3 / 5
Workflow Clarity	The plan/run/sync/audit phase table with owners and checks, the cycle_type breakdown, and the closing Verification checklist give a clear sequence with most checkpoints present, with only minor gaps in explicit per-step validation.	4 / 5
Progressive Disclosure	The overview-to-reference structure is well signaled with load-when labels, but four of six referenced paths (modules/trust5-validation.md, proactive-analysis.md, best-practices.md, integration-patterns.md) do not exist in the bundle, and the reference.md anchor link is a broken typo ('#language-aware-toolkchains'), so the disclosure structure is present but not actually navigable.	3 / 5
	Total	13 / 20 Passed

Description

87%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 strong: it states what the skill covers, names concrete enforcement mechanisms, and provides an explicit 'Use for' trigger clause with natural terms. The only soft spot is trigger-term breadth, where synonyms and extensions would round it out.

Suggestions

Add synonyms and concrete file/extension triggers to the 'Use for' clause (e.g., 'lint errors', 'test coverage', 'pre-commit checks') to lift trigger-term coverage toward comprehensive.

Consider naming a couple more concrete user-facing actions rather than only enforcement mechanisms to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and four concrete enforcement mechanisms (agents, 3-level harness, /moai gate, sync-auditor scoring), but these are conceptual mechanisms rather than a comprehensive list of concrete user-facing actions, fitting the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers both what (TRUST 5 principles and how MoAI enforces them through named mechanisms) and when ('Use for code review, quality gate checks, coverage targets, or TRUST 5 compliance') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('code review', 'quality gate checks', 'coverage targets', 'TRUST 5 compliance'), giving good keyword coverage, but lacks synonyms and file extensions that would push it to the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The TRUST 5 / MoAI / /moai gate / sync-auditor framing is a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 missing	Warning

	Total	13 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/moai-foundation-quality/SKILL.md
Commit: 2213871

Reviewed: 5 hours ago

Table of Contents

Discovery Implementation Validation

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.