autoreview

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

Quality

65%

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 ./templates/plate-playground-template/.agents/skills/autoreview/SKILL.md

Quality

Content

70%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 skill body is highly actionable and workflow-clear with concrete commands and explicit feedback loops, but it suffers from verbosity and duplication, and it monolithically inlines reference material that could be split into separate files.

Suggestions

De-duplicate the engine-isolation prose against the Helper bullets and the Models/thinking tables so each flag/env var is stated once; consolidate repeated env-var and thinking-mapping text.

Move the large engine-isolation, model/thinking reference tables, and release-process rules into separate reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Trim over-explanation (e.g., restating which engines reject --thinking or how each maps thinking) to a single concise reference rather than repeating it across sections.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the engine-isolation section, the Helper bullets, and the Models/thinking tables restate the same flags, env vars, and model IDs multiple times, with substantial duplication that could be trimmed.	2 / 5
Actionability	It provides fully executable, copy-paste-ready invocations ('"$AUTOREVIEW" --mode branch --base origin/main'), real flag combinations, and concrete per-engine examples covering the common cases.	5 / 5
Workflow Clarity	The process is clearly sequenced (pick target -> run helper -> verify findings -> fix -> rerun) with explicit validation checkpoints and feedback loops ('rerun focused tests and rerun the structured review helper', 'stop as soon as the helper exits 0').	5 / 5
Progressive Disclosure	Section headers give it some structure and the bundle scripts are referenced by path, but large blocks that belong in separate reference files (engine isolation details, model/thinking tables, release-process rules) are inlined rather than split out.	3 / 5
	Total	15 / 20 Passed

Description

61%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.

The description is clear and reasonably specific about a structured closeout code review with named engines, but it lacks an explicit 'Use when' trigger clause, which limits completeness. Trigger-term quality and distinctiveness are solid.

Suggestions

Add an explicit 'Use when ...' clause listing natural trigger phrases (e.g., 'before commit/ship', 'second-model review', 'after non-trivial edits') to raise completeness.

Name one or two concrete review actions beyond 'code review' (e.g., 'verifies findings, reruns focused tests, returns structured results') to improve specificity.

Include common synonyms or aliases a user might say (e.g., 'pre-push review', 'second opinion review') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Pre-commit/ship code review') and enumerates concrete engines (Codex, Claude, Pi, etc.), but the action itself is generic ('code review') without breaking down what the review does.	3 / 5
Completeness	It gives a clear 'what' (closeout code review with a default and optional engines) but provides no explicit 'Use when' clause; 'when' is only weakly implied by 'Pre-commit/ship', which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	It includes natural user terms ('code review', 'second-model review', 'Pre-commit/ship') and concrete engine names; a few natural synonyms are missing, so it sits above the midpoint but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	The structured-closeout framing plus the explicit engine enumeration carves a distinct niche with minimal conflict risk versus generic review skills, with only minor overlap.	4 / 5
	Total	14 / 20 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: templates/plate-playground-template/.agents/skills/autoreview/SKILL.md
Commit: 9ec2c8e

Reviewed: 3 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.