autoreview

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

Quality

67%

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%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.

An unusually actionable, well-validated closeout workflow with excellent feedback loops and error recovery. Its main weaknesses are redundancy (model/thinking material repeated in four places) and missing progressive disclosure — engine-isolation and env-default details are inlined in SKILL.md instead of split into one-level-deep reference files.

Suggestions

Move the per-engine isolation details (the long paragraph and table under 'Review engine isolation') into a references/engine-isolation.md file and link to it from SKILL.md.

Consolidate the model/thinking/flag guidance repeated across 'Review Panels', 'Models and thinking', 'Environment defaults', and the 'Helper' bullet list into a single section (or a references/model-config.md).

Trim the 'Helper' bullet list to behaviors not already covered by earlier sections, keeping only the exit-status/heartbeat contract details.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely non-obvious operational facts (helper flags, isolation requirements, engine mappings) rather than concepts Claude already knows, but model/thinking flag guidance is repeated across 'Review Panels', 'Models and thinking', 'Environment defaults', and the 'Helper' bullet list, and the 'Review engine isolation' section packs a huge single paragraph that could be tightened. Mostly efficient but with real redundancy.	3 / 5
Actionability	Every workflow step is backed by copy-paste-ready commands with real flags, concrete model IDs, exact env-var names, and engine/flag tables; examples cover local, branch/PR, commit, panel, and Windows cases. Fully executable guidance.	5 / 5
Workflow Clarity	The lifecycle is clearly sequenced (set paths, pick target, optionally parallel tests, run review, verify findings, fix, rerun, final report) with explicit validation checkpoints and feedback loops ('rerun focused tests and rerun the structured review helper', 'Keep going until... no accepted/actionable findings'). Error-recovery guidance is exceptional: heartbeat interpretation, gitcrawl doctor repair, and a scope governor with a two-cycle pause.	5 / 5
Progressive Disclosure	Section headers are clear and navigation is easy, but the ~340-line body inlines deep engine-isolation details (a monolithic paragraph of per-engine flags and version requirements) and duplicated model/env tables that clearly belong in a separate reference file. The bundle has no references/ directory at all, so everything is inline.	3 / 5
	Total	16 / 20 Passed

Description

57%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 concise, concrete, and names a distinct multi-engine review niche with a clear default, but it lacks an explicit 'Use when...' trigger clause and natural trigger variations. Adding explicit trigger phrases would move completeness and trigger-term quality up.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a Codex/Claude/second-model review, or before committing or shipping non-trivial changes.'

Include natural user phrasings such as 'review my code', 'review my changes', or 'second-opinion review' alongside the engine names.

State one or two more concrete capabilities (e.g. 'runs a structured review helper, validates findings, exits clean only when no actionable findings remain') to broaden coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Pre-commit/ship code review') and one concrete action with a concrete engine list ('Codex default; optional Claude, Pi, Droid, Copilot, or OpenCode'), but lists only a single action rather than multiple specific capabilities. It is not vague like 'Helps with code', but coverage is not comprehensive.	3 / 5
Completeness	It states a clear 'what' (pre-commit/ship code review with Codex as default engine) but the 'when' is only weakly implied by 'pre-commit/ship'; there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Strong natural keywords: 'code review', 'pre-commit', 'ship', plus engine names (Codex, Claude, Copilot) users would naturally say. Missing common variations such as 'review my changes', 'second opinion', or 'pre-merge review', so not a 5.	4 / 5
Distinctiveness Conflict Risk	'Code review' is a broadly overlapping phrase that could trigger generic review skills, but the named engines (Codex, Pi, Droid, OpenCode) carve out a specific niche. It is somewhat specific yet still overlaps with sibling code-review skills.	3 / 5
	Total	13 / 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: .agents/skills/autoreview/SKILL.md
Commit: babb3c2

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.