mason

Produces clean, functional code that matches the architecture and checklists.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, actionable role definition with a clear build workflow, explicit validation checkpoints, and feedback loops. It is largely lean, with only minor tightenings possible in the intro narrative and Limitations boilerplate.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean directive content that assumes Claude's competence and avoids explaining basic programming concepts, but the intro narrative about Luna/Quinn and the boilerplate 'Limitations' section ('AI agents may occasionally hallucinate...') could be tightened, so it is not a 3.	2 / 3
Actionability	It gives concrete, specific guidance (named tools like 'bcrypt/argon2', 'helmet.js', a copy-paste-ready MASON PROGRESS report template, explicit do/don't rules), which is appropriately actionable for an instruction-only skill; it is above 2 because the guidance is specific and copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	It sequences the build clearly ('Implement features in checklist order — complete and verify each item before moving to the next', deliver 'one file at a time') with explicit validation checkpoints (per-file DoD status, milestone gating, blocker escalation) and feedback loops (check resolved Luna/Quinn findings before continuing), matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the single self-contained SKILL.md is organized into clearly labeled sections (Responsibilities, Output Format, Handoff Protocol, Interaction Style, Limitations) with no nested references, so it earns a 3 for well-organized structure.	3 / 3
	Total	11 / 12 Passed

Description

35%

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 states what the skill does but is generic and lacks any explicit trigger for when to use it, which caps completeness and weakens trigger-term quality. It would conflict with other general coding skills.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when implementing code from an architecture blueprint and a Definition-of-Done checklist during the build phase'.

Replace generic phrasing with concrete actions the builder performs, e.g. 'Scaffolds projects, implements features in checklist order file-by-file, and reports DoD status'.

Add distinguishing trigger terms tied to the squad workflow (blueprint, checklist, milestone, code review handoff) to separate it from general coding skills.

Dimension	Reasoning	Score
Specificity	It names a domain ("code") and a few actions ("Produces clean, functional code", "matches the architecture and checklists"), but the actions are generic and not comprehensive, matching the score-2 anchor rather than the multi-action list required for a 3.	2 / 3
Completeness	It states what the skill does ("Produces clean, functional code") but never says when to use it, so it caps at 2 per the missing-trigger guideline; it is above 1 because the 'what' is clearly stated.	2 / 3
Trigger Term Quality	The phrasing relies on generic technical jargon ("architecture", "checklists") with no natural keywords a user would actually say when needing this skill and no "Use when..." triggers, fitting the score-1 anchor; it is not a 2 because there are no relevant common variations present.	1 / 3
Distinctiveness Conflict Risk	"Produces clean, functional code" is generic and would overlap with many coding skills, but "matches the architecture and checklists" adds some narrowing, placing it at the 'somewhat specific but could overlap' anchor rather than the fully generic 1.	2 / 3
	Total	7 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 6e69f00

Reviewed: 5 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.