Agent skill

Correctness Reviewer

by udecode in udecode/plate

Always-on code-review persona. An agent skill from udecode/plate.

Custom licenceAuto-check passedDevelopment

Install Correctness Reviewer

skills CLI
$ npx skills add udecode/plate --skill correctness-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install udecode/plate correctness-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/udecode/plate.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/correctness-reviewer .claude/skills/correctness-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
correctness-reviewer
GitHub stars
17k
Token cost
~910 tokens
SKILL.md length
465 words
Files
1
Skills in repo
78
Repo updated
First seen
Licence
Custom licence

At a glance

Always-on code-review persona. An agent skill from udecode/plate.

  • Tasks that involve State management
  • SKILL.md covers What you're hunting for, Confidence calibration, What you don't flag and Output format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Correctness Reviewer is an agent skill from udecode/plate. Always-on code-review persona. Reviews code for logic errors, edge cases, state management bugs, error propagation failures, and intent-vs-implementation mismatches.

Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering State management. The repository describes itself as: Rich-text editor with AI and shadcn/ui.

When your agent uses it

  • Tasks that involve State management

Example prompts

  • “/correctness-reviewer”

What it can do on your machine

Read from SKILL.md and the folder at commit 6f3815d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Correctness Reviewer loads about 910 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 465 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~910

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 465 words (~910 tokens).

“You are a logic and behavioral correctness expert who reads code by mentally executing it -- tracing inputs through branches, tracking state across calls, and asking "what happens when this value is X?" You catch bugs that pass tests because…”

— opening of SKILL.md by udecode, Custom licence
name
correctness-reviewer
model
inherit
tools
Read, Grep, Glob, Bash
color
blue

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/correctness-reviewer of udecode/plate.

Open the folder on GitHubat commit 6f3815d

Compare with similar skills

Correctness Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Correctness Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Correctness Reviewer this skilludecode/plate17k—~910Automated safety check: PassCustom licence
JavaScript IO Effects With Sagasparalleldrive/aidd384—~587Automated safety check: PassMIT
Build with TinyBasetinyplex/tinybase5.2k—~1.6kAutomated safety check: PassMIT
Google Agents CLI Adk Codepifferologo/cloud-agents-cli1291 repos~768Automated safety check: PassApache-2.0
Freighter Best Practicesstellar/freighter118—~706Automated safety check: PassApache-2.0
Tanstack Querybskimball/tanstack-hono1191 repos~5.4kAutomated safety check: PassMIT

Similar skills

  • Teaches the saga pattern with call and put so network requests and side effects stay out of the logic and sagas can be tested without mocks.

    384 GitHub stars~587 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Build with TinyBase

    tinyplex/tinybase

    Scaffolds, extends and verifies local-first JavaScript and TypeScript apps built on TinyBase, from create-tinybase through persistence and sync.

    5.2k GitHub stars~1.6k tokensUpdated 9 days ago
    DevelopmentAuto-check passed
  • Google Agents CLI Adk Code

    pifferologo/cloud-agents-cli

    This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…

    129 GitHub starsUsed in 1 repo~768 tokens
    AI & LLM EngineeringAuto-check passed
  • Freighter Best Practices

    stellar/freighter

    Comprehensive best practices for the Freighter browser extension.

    118 GitHub stars~706 tokensUpdated today
    DevelopmentAuto-check passed
  • Tanstack Query

    bskimball/tanstack-hono

    Powerful asynchronous state management, server-state utilities, and data fetching for TS/JS, React, Vue, Solid, Svelte & Angular.

    119 GitHub starsUsed in 1 repo~5.4k tokens
    Frontend & DesignAuto-check passed
  • Frontend Typescript Rules

    shinpr/ai-coding-project-boilerplate

    Applies React/TypeScript type safety, component design, and state management rules.

    232 GitHub stars~1.7k tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed

More from udecode/plate

All 78 skills in this repo
  • React Useeffect

    udecode/plate

    React useEffect best practices from official docs. An agent skill from udecode/plate.

    17k GitHub starsUsed in 6 repos~573 tokens
    Auto-check passed
  • Video Transcripts

    udecode/plate

    Generate structured video transcripts from local files or video URLs using Gemini Files API.

    17k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Build new Plate plugins with Slate-first architecture, sane typing, and explicit React/Plate wrapper boundaries.

    17k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Plate UI

    udecode/plate

    Build new shadcn-style components for Plate's registry and editor surfaces.

    17k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Researches and synthesizes external best practices, documentation, and examples for any technology or framework.

    17k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Frontend Design

    udecode/plate

    Build web interfaces with genuine design quality, not AI slop.

    17k GitHub stars~3.6k tokensUpdated today
    Auto-check passed

Questions about Correctness Reviewer

What does Correctness Reviewer do?

Always-on code-review persona. An agent skill from udecode/plate. Correctness Reviewer is an agent skill from udecode/plate. Always-on code-review persona.

When should I use Correctness Reviewer?

Correctness Reviewer fits situations like: tasks that involve State management.

How do I install Correctness Reviewer in Claude Code?

Run `npx skills add udecode/plate --skill correctness-reviewer -a claude-code`. Or copy the skill folder (.agents/skills/correctness-reviewer in udecode/plate) into .claude/skills/correctness-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Correctness Reviewer in Codex?

Run `npx skills add udecode/plate --skill correctness-reviewer -a codex`. Or copy the skill folder (.agents/skills/correctness-reviewer in udecode/plate) into .agents/skills/correctness-reviewer in your project. Codex loads it when a task matches its description.

Can I use Correctness Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add udecode/plate --skill correctness-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/correctness-reviewer, .gemini/skills/correctness-reviewer, .github/skills/correctness-reviewer and .opencode/skills/correctness-reviewer in your project.

What does Correctness Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Correctness Reviewer is instructions for the agent only.

Does Correctness Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Correctness Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Correctness Reviewer use?

Correctness Reviewer has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Correctness Reviewer use?

About 910 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Correctness Reviewer?

Skills that share tags, products or a category with Correctness Reviewer: JavaScript IO Effects With Sagas (paralleldrive/aidd, 384 stars), Build with TinyBase (tinyplex/tinybase, 5.2k stars), Google Agents CLI Adk Code (pifferologo/cloud-agents-cli, 129 stars) and Freighter Best Practices (stellar/freighter, 118 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Correctness Reviewer?

udecode (a GitHub organization) maintains it in udecode/plate, which has 16,642 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on October 8, 2026.

Source: udecode/plate on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.