x-review

Use when the user asks to review code, a plan, a PR, or a directory — auto-detects target, runs cross-model review (Claude + GPT + Gemini-3-pro). Reports bugs, security issues, false assumptions, and plan deviations only; refactor/perf/restructure are opt-in passes

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.

A well-structured orchestration body with concrete scope guidance, clear sequencing, and explicit checkpoints. Its main weaknesses are mild redundancy in the scope/gotchas material and broken or unlinked bundle references.

Suggestions

Add explicit links from the body to references/review-passes.md and references/scope-guard.md (e.g., in the Step-File Architecture or Scope Contract section) so the bundle files that exist are discoverable.

Ensure the referenced steps/step-01..04.md and gotchas.md are present in the bundle, or note their location — currently the workflow points to files that are not in ./steps/.

Tighten the Scope Contract by collapsing the repeated 'drop, do not downgrade to LOW' rule and 'the test' into a single statement, since the same guidance is restated in the gitnexus fence and scope-guard.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept filler, but the scope contract and gitnexus fence repeat the same 'drop, do not downgrade' rule and 'the test' multiple times, and the scope guidance duplicates material in references/scope-guard.md.	2 / 3
Actionability	Concrete and executable for an orchestration skill: named bootstrap reads (config.json, ../x-omo/SKILL.md), explicit allowed/forbidden tool lists, a literal self-check procedure, and a numbered 4-step workflow.	3 / 3
Workflow Clarity	Clear sequence (prepare → review → synthesize → act) with explicit checkpoints — 'Halt at checkpoints for human input' and the 'Self-check before every tool call' gate — plus critical-rules guardrails.	3 / 3
Progressive Disclosure	The step-file architecture is well-signaled and one level deep, but the referenced steps/step-01..04.md and gotchas.md are absent from the bundle, while the present references/review-passes.md and scope-guard.md are not linked from the body.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 tight, third-person description that states concrete capabilities, natural triggers, and a distinctive scope-narrowing position. It answers what and when without padding or over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'auto-detects target, runs cross-model review (Claude + GPT + Gemini-3-pro)' and enumerates exact finding classes (bugs, security issues, false assumptions, plan deviations) plus opt-in passes.	3 / 3
Completeness	Explicitly answers both what (auto-detect + cross-model review + scoped finding types) and when ('Use when the user asks to review code, a plan, a PR, or a directory').	3 / 3
Trigger Term Quality	Natural trigger phrasing a user would actually say — 'review code, a plan, a PR, or a directory' — with good coverage of common review-request terms.	3 / 3
Distinctiveness Conflict Risk	Clear niche — cross-model review with a narrow scope contract and explicit opt-in-only refactor/perf passes — unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 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: quangtran88/x-skills
Commit: 6381b15

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.