rex

Translates user intent into a precise, unambiguous specification and requirements.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is highly actionable with concrete formats, templates, and a clear sequenced workflow including a re-invocation diff loop. Its main weakness is conciseness/progressive disclosure: it is a long monolithic document with some role narrative that could be tightened or split into referenced files.

Suggestions

Trim the squad-narrative paragraph ('Rex knows the full squad exists...') to a one-line handoff note, since downstream-agent names already appear in the Handoff Protocol section.

Consider moving the full REX REPORT template and per-responsibility detail into a referenced file (e.g. REPORT_FORMAT.md) to slim the overview and improve progressive disclosure.

Cut rhetorical lines like 'Direct and precise. No filler.' that restate behavior already implied by the rules.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence without explaining basics, but the squad narrative ('Rex knows the full squad exists... Alex... Aria... Mason') and some role color add tokens that could be trimmed.	2 / 3
Actionability	It gives concrete, copy-ready guidance: a full REX REPORT template, the 'As a [role], I want [action] so that [outcome]' story format, Given/When/Then acceptance criteria, MoSCoW framing, and a hard 'at most 3 clarifying questions' rule.	3 / 3
Workflow Clarity	Responsibilities are clearly sequenced (intent extraction through constraints/non-goals), the output artifact and handoff protocol are explicit, and a re-invocation path produces a diffed AMENDMENT — a built-in feedback loop; no destructive operation is involved so the validation cap does not apply.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a single ~150-line monolithic file with no bundle files and no references; the detailed responsibility lists and output template are inline content that could be split out for a leaner overview.	2 / 3
	Total	10 / 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 stops short of listing multiple concrete actions and omits any explicit 'Use when...' trigger guidance. It reads more like a role tagline than a discoverable skill description.

Suggestions

Add 2-3 more concrete actions (e.g. 'gathers requirements, writes user stories, flags edge cases and constraints') to lift specificity to a 3.

Append an explicit trigger clause such as 'Use when starting a new project or feature, or when the user asks to gather requirements or write a spec.'

Include natural user phrasings ('requirements', 'spec', 'scope', 'user stories') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Translates user intent into a precise, unambiguous specification and requirements' names the requirements-analysis domain and a concrete action, but only a single action rather than a comprehensive list of capabilities.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2 with only an implied when.	2 / 3
Trigger Term Quality	Terms like 'specification and requirements' are relevant, but the description lacks common natural variations a user would say (e.g. 'gather requirements', 'write a spec', 'define scope'), giving partial coverage.	2 / 3
Distinctiveness Conflict Risk	The requirements-analyst niche is fairly specific, but without explicit triggers it could still overlap with planning or architecture skills in the same squad.	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.