autoreview

Pre-commit/ship code review: Codex default; optional Claude, Pi, Droid, Copilot, or OpenCode.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/autoreview/SKILL.md

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 body is highly actionable with executable commands and a clearly sequenced, validated workflow, but it is overlong and keeps time-sensitive version/model details and large reference tables inline rather than factoring them into separate, one-level-deep reference files.

Suggestions

Move the large engine-isolation, models/thinking, and environment-defaults tables into a separate reference file (e.g., references/engines.md) and link to it one level deep, keeping SKILL.md a lean overview.

Relocate time-sensitive version requirements and model aliases (e.g., 'v2.1.169+', 'v0.79.0+', 'gpt-5.5', 'claude-fable-5') into a dedicated versions/deprecations section so they do not penalize conciseness and are easy to maintain.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational rather than padded with concepts Claude already knows, but at ~340 lines it is verbose and embeds time-sensitive version/model details (e.g., 'v2.1.169+', 'v0.79.0+', 'gpt-5.5', 'claude-fable-5') inline rather than in a deprecated/old-patterns section, which the rubric penalizes.	2 / 3
Actionability	Provides copy-paste-ready bash commands with concrete flags (--mode branch --base origin/main, --reviewers codex,claude, --model, --thinking) and a full flag/env reference, leaving little ambiguous about how to run the helper.	3 / 3
Workflow Clarity	Sequenced from path setup through target selection, parallel closeout, panels, and final report, with explicit validation feedback loops (rerun tests and review until no accepted findings) and a Scope Governor with concrete stop conditions.	3 / 3
Progressive Disclosure	Bundle scripts are real and referenced one level deep, but the skill is a single monolithic SKILL.md with large inline reference-style tables (engine isolation, models, env defaults) that could be split into separate reference files for easier navigation.	2 / 3
	Total	10 / 12 Passed

Description

65%

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 specific and rich in natural trigger terms, but it omits an explicit 'Use when' trigger clause and relies on a generic 'code review' label that risks overlap with adjacent review skills.

Suggestions

Add an explicit 'Use when...' clause naming the concrete situations that should trigger this skill (e.g., 'Use when the user asks for a Codex/Claude/Pi/Droid/OpenCode review, or before committing or shipping non-trivial code changes').

Disambiguate from sibling skills in the description itself (e.g., note it is a structured review closeout gate, not Guardian approval routing) to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ('Pre-commit/ship code review') and enumerates review engines ('Codex default; optional Claude, Pi, Droid, Copilot, or OpenCode'), but describes a single action class rather than multiple distinct concrete actions.	2 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Contains natural terms users would say ('code review', 'Codex', 'Claude', 'Pi', 'Droid', 'Copilot', 'OpenCode', 'pre-commit/ship'), giving good coverage of likely requests.	3 / 3
Distinctiveness Conflict Risk	The engine enumeration and closeout framing give it a niche, but 'code review' is generic and the body itself notes a conflict risk with Guardian 'auto_review', so overlap with similar skills remains.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: udecode/plate
Path: .agents/skills/autoreview/SKILL.md
Commit: 45116fd

Reviewed: about 13 hours 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.