luna

Reviews code for objective correctness, security, and reliability.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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 well-structured reviewer persona spec with concrete checklists, an explicit output template, and a gated handoff workflow with feedback loops. It is somewhat verbose in places and monolithic (no reference split), which caps conciseness and progressive disclosure at the mid level.

Suggestions

Trim the generic Limitations boilerplate about AI hallucination, which Claude already knows and which does not advance the review task.

Tighten the intro paragraph, which restates the scope already conveyed by the description and the Responsibilities section.

Consider extracting the detailed vulnerability/pattern checklists into a reference file so SKILL.md stays a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete checklists, but the generic Limitations boilerplate ('AI agents may occasionally hallucinate...') and slight intro redundancy add tokens Claude does not need, fitting 'mostly efficient but could be tightened' rather than the lean level-3 anchor.	2 / 3
Actionability	It names concrete items to flag (e.g. 'eval()', 'exec()', 'pickle.loads()', 'N+1 query patterns') and provides a complete report template, but guidance is checklist-level ('check for X') without operational technique or executable commands, matching 'some concrete guidance but incomplete' rather than fully copy-paste-ready level 3.	2 / 3
Workflow Clarity	The handoff protocol gives a clear review -> categorize -> gate -> handoff -> re-review sequence with explicit validation gates ('Do NOT forward to Quinn until all CRITICAL and HIGH findings are resolved') and a feedback loop (re-review confirms fixes or escalates new issues), matching the level-3 anchor with checkpoints and error-recovery loops.	3 / 3
Progressive Disclosure	Sections are clearly organized, but the skill is a monolithic ~125-line single file with all detail inline and no overview-to-reference layering; with no bundle files this is self-contained, yet it fits 'some structure but content that could be separate is inline' rather than the cleanly split level-3 pattern.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 clear and on-domain but terse: it states what Luna does without listing concrete actions or any 'Use when...' trigger guidance. All four dimensions land at the mid level because it is specific enough to avoid being vague yet lacks the explicit triggers and concrete action list that would push it higher.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when reviewing code for security vulnerabilities, correctness bugs, or reliability issues before handoff to QA.'

List concrete actions to lift specificity, e.g. 'Scans for injection/auth flaws, race conditions, N+1 queries, and deprecated APIs, and produces a severity-ranked findings report.'

Include common user phrasings (e.g. 'code review', 'security review', 'find bugs in my code') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Reviews code') and focus areas ('correctness, security, and reliability') but does not enumerate multiple concrete review actions, matching the 'names domain and some actions, not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 even though the 'what' is clear.	2 / 3
Trigger Term Quality	Terms like 'code', 'security', and 'correctness' are natural keywords a user might say, but coverage is sparse with no common variations, matching 'some relevant keywords but missing common variations' rather than the broad level-3 coverage.	2 / 3
Distinctiveness Conflict Risk	'Reviews code for objective correctness, security, and reliability' carves out a specific niche but 'code review' is a broad domain that could overlap with related skills, fitting 'somewhat specific but could still overlap' rather than a clearly distinct level-3 trigger.	2 / 3
	Total	8 / 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.