moai-foundation-core

Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window optimization.

Quality

70%

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-core/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-structured with concrete commands, templates, and validation checkpoints, but it is padded with explanatory rationale Claude already knows and repeats token-budget figures multiple times. The bigger structural issue is that the bulk of its Detailed-Reference pointers target modules/*.md files that are absent from the bundle, undermining the progressive-disclosure navigation it advocates.

Suggestions

Trim the 'why it matters' rationale sentences from each TRUST 5 pillar (e.g. 'High coverage ensures code reliability...') and de-duplicate the 30K/180K/40K/250K budget so it appears in one canonical place rather than three.

Either add the missing modules/*.md files to the bundle or rewrite the 'Detailed Reference:' pointers to point at the references/ files that actually exist, so no deep-dive link is a dead path.

Inline a brief delegation/SPEC failure-recovery feedback loop (detect → fix → re-validate) instead of deferring all error handling to the named-but-absent advanced module.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: each TRUST 5 pillar appends rationale Claude already knows ("High coverage ensures code reliability and reduces production defects", "Consistency eliminates style debates and merge conflicts"), and the 30K/180K/40K/250K token budget is restated multiple times across section 4, the Token Budget table, and the examples.	2 / 5
Actionability	Concrete actionable elements are present throughout — exact commands (/moai plan, /clear), the agent-selection matrix (1 file → 1-2 agents sequential, 10+ files → 5+ mixed), GEARS pattern templates, the 85% coverage threshold, and the progress.md resume-message code block — with only minor gaps where executable code is deferred to references.	4 / 5
Workflow Clarity	The SPEC-First Phase 1/2/3 workflow is clearly sequenced with /clear checkpoints and an 85% coverage validation gate, the multi-agent handoff gives numbered steps with a 120K-token checkpoint, and a Verification checklist closes the body; minor gaps remain since delegation/SPEC error-recovery feedback loops are only named as deferred advanced topics.	4 / 5
Progressive Disclosure	Sectioning and one-level-deep "Detailed Reference:" pointers are consistent and clearly signaled, but scoring against the actual bundle reveals that the nine referenced modules/*.md files do not exist in the bundle — only references/examples.md and references/reference.md are present — so most deep-dive references resolve to dead paths.	3 / 5
	Total	13 / 20 Passed

Description

83%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 strong, specific description that explicitly covers both what the skill provides and when to use it, anchored in distinctive MoAI-ADK terminology. The main weakness is that the 'when' triggers cover only three of the six listed capabilities and the capability list leans on framework nouns rather than concrete actions.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete capabilities ("TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management"), but these are named frameworks/objects rather than verb-driven actions, leaving minor abstraction short of fully concrete action coverage.	4 / 5
Completeness	It clearly states what it provides ("Provides MoAI-ADK foundational principles including...") and gives explicit "Use when..." trigger guidance with concrete trigger phrases, matching the anchor that requires both what AND when with concrete triggers.	5 / 5
Trigger Term Quality	The "Use when referencing TRUST 5 gates, SPEC workflow, or context window optimization" clause supplies natural domain trigger phrases a MoAI-ADK user would say, with good keyword coverage, though common synonyms and variations are missing.	4 / 5
Distinctiveness Conflict Risk	The MoAI-ADK-specific named frameworks (TRUST 5, SPEC-First DDD, GEARS) carve a clear niche, but the mention of absorbed context and sibling foundation skills (moai-foundation-cc, moai-foundation-thinking) creates minor overlap risk with closely related skills.	4 / 5
	Total	17 / 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: 1 missing	Warning

	Total	13 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/moai-foundation-core/SKILL.md
Commit: 4100d87

Reviewed: 2 days 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.