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 + OMO oracle + Gemini-3-pro). Reports bugs, security issues, false assumptions, and plan deviations only; refactor/perf/restructure are opt-in passes

Quality

76%

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 ./skills/x-review/SKILL.md

Quality

Content

60%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, actionable process guidance and a clear sequenced workflow. Its main weakness is progressive disclosure: the body points to step/shared files that are missing from the bundle, and the actual reference files present are orphaned (never linked from the body).

Suggestions

Make the body's references resolve: either include the referenced steps/, gotchas.md, and ../x-shared/ files in the bundle, or link the existing references/review-passes.md and references/scope-guard.md explicitly from the body (e.g., a References section pointing to them).

Tighten the repeated scope/role-boundary statements — the in-scope/out-of-scope contract and the 'reviewers don't fix' rule each appear 2-3 times; consolidate into one authoritative block and reference it.

Surface the existing reference files where they belong: scope-guard.md is the verbatim reviewer-prompt block, so the body should link it at the dispatch point rather than leaving it orphaned.

Dimension	Reasoning	Score
Conciseness	Mostly specific and not padded with concepts Claude already knows, but the scope contract / role boundary is restated several times (Scope Contract, the gitnexus fence re-explaining in/out-of-scope, MUST NOT, and the Self-check block), which could be tightened.	3 / 5
Actionability	Concrete guidance throughout — explicit file reads ('Read config.json', 'Read ../x-omo/SKILL.md'), specific tool invocations (Agent subagent_type, Bash '<omo_agent> oracle'), and a numbered bootstrap — though the core executable detail is delegated to step files.	4 / 5
Workflow Clarity	Clear sequence (Bootstrap 0-3, then Workflow steps 1-4) with explicit checkpoints (halt at verdicts, human-input menu, self-check before mutating tool calls) and critical rules; minor validation gaps live in the delegated step files.	4 / 5
Progressive Disclosure	The body references steps/step-01..04.md, gotchas.md, and ../x-shared/*.md that are absent from the bundle, while the two files that DO exist (references/review-passes.md, references/scope-guard.md) are not linked from the body — cross-file navigation is broken in practice.	2 / 5
	Total	13 / 20 Passed

Description

92%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 description that clearly states both what the skill does and when to use it, with concrete actions and a distinctive narrowed scope. Slightly more trigger-term variation (full phrases like 'pull request', 'code review') would round it out.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'auto-detects target, runs cross-model review (Claude + OMO oracle + Gemini-3-pro)' and 'Reports bugs, security issues, false assumptions, and plan deviations' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (cross-model review reporting specific finding types, opt-in passes) and 'when' ('Use when the user asks to review code, a plan, a PR, or a directory') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural trigger coverage ('review code, a plan, a PR, or a directory') with several synonyms, but misses common variations like 'code review', 'pull request', 'diff', or 'review my changes'.	4 / 5
Distinctiveness Conflict Risk	The narrowed scope ('Reports bugs, security issues, false assumptions, and plan deviations only; refactor/perf/restructure are opt-in passes') carves a clear niche with distinct triggers and minimal conflict risk against general code skills.	5 / 5
	Total	19 / 20 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
Path: skills/x-review/SKILL.md
Commit: f17a69e

Reviewed: 6 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.