Agent skill

Local Review

by IvanWng97 in IvanWng97/pixtuoid

Run pixtuoid's review locally at either scope — a DIFF review (one lens per matching REVIEW.md local escalation row; the correctness and design lenses are the automatic CI review's, never re-run…

MITAuto-check passedGame Development

Install Local Review

skills CLI
$ npx skills add IvanWng97/pixtuoid --skill local-review -a claude-code

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

GitHub CLI
$ gh skill install IvanWng97/pixtuoid local-review --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/IvanWng97/pixtuoid.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/local-review .claude/skills/local-review && 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
local-review
GitHub stars
491
Token cost
~1.4k tokens
SKILL.md length
500 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Run pixtuoid's review locally at either scope — a DIFF review (one lens per matching REVIEW.md local escalation row; the correctness and design lenses are the automatic CI review's, never re-run…

  • Works in 7 steps: Isolate the branch in a worktree (two… → Dispatch one lens per matching local… → Collect and verify. A one-word or… → …
  • A diff touches a local-only row
  • SKILL.md covers When to run, Diff scope, Whole-codebase scope and Red flags
  • Calls gh and rg

What it does

Local Review is an agent skill from IvanWng97/pixtuoid. Run pixtuoid's review locally at either scope — a DIFF review (one lens per matching REVIEW.md local escalation row; the correctness and design lenses are the automatic CI review's, never re-run locally) or a whole-codebase AUDIT (subsystem × factor fan-out). Use when a diff touches a local-only row, on 'is this ready to merge', or on 'whole-codebase review' / pre-release / periodic audit.

Its SKILL.md is about 1.4k 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 Game Development. The repository describes itself as: Terminal pixel-art office for AI coding agents. The licence is MIT.

When your agent uses it

  • A diff touches a local-only row
  • On is this ready to merge
  • On whole-codebase review / pre-release / periodic audit

Example prompts

  • “is this ready to merge”
  • “whole-codebase review”
  • “/local-review”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Isolate the branch in a worktree (two sessions on one tree race on
  2. Dispatch one lens per matching local row, in parallel, in the
  3. Collect and verify. A one-word or placeholder return is a STUB, not a
  4. Fold accepted findings into ONE commit, with a plan-miss: line per
  5. Disposition each finding in a review thread. The bots open theirs; open
  6. Record each row's run as
  7. Before merge, judge against the gate.

What it can do on your machine

Read from SKILL.md and the folder at commit 413c70c. 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

    Shell commands in SKILL.md call:

    • gh
    • rg

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

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    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

Local Review loads about 1.4k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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

The full file from IvanWng97/pixtuoid at commit 413c70c, republished under its MIT licence (© IvanWng97). 500 words, ~1,410 tokens.

Download SKILL.mdSave it as .claude/skills/local-review/SKILL.md (or your agent's skills folder).
name
local-review
description
Run pixtuoid's review locally at either scope — a DIFF review (one lens per matching REVIEW.md local escalation row; the correctness and design lenses are the automatic CI review's, never re-run locally) or a whole-codebase AUDIT (subsystem × factor fan-out). Use when a diff touches a local-only row, on 'is this ready to merge', or on 'whole-codebase review' / pre-release / periodic audit.
version
3.0.0
metadata.scope
pixtuoid repo only

local-review — local orchestration of REVIEW.md

Every rule is REVIEW.md's; fill briefs from it, never a paraphrase here.

When to run

  • Diff scope: the diff matches a REVIEW.md escalation row marked local. The correctness and design lenses are the automatic review's; never re-run them here.
  • Whole-codebase scope: "audit the repo", a pre-release or periodic sweep.

Diff scope

  1. Isolate the branch in a worktree (two sessions on one tree race on HEAD). Note path, branch, base and head sha.

  2. Dispatch one lens per matching local row, in parallel, in the background: model: sonnet for a lens that reads evidence or runs a mechanical check (test lists, mutations, renders, a walk), opus only for a design gate. Each briefed:

    You are the <row> lens for <PR/branch> on pixtuoid.
    Worktree: <path> (branch <name>, base <sha>, head <sha>), read-only;
    stop if HEAD is not that head.
    Diff: git -C <path> diff <base>..<head>.
    Read AGENTS.md, then apply REVIEW.md's <row> and its Common
    section.
    <change-specific claims (from the PR body's impl-plan answers) or design
    questions, one per line>
    Run the applicable gates; report each exit code as observed, never through
    a pipe. Each finding carries an integer confidence 0–100. Your final
    message is the report, ending in one verdict: APPROVE or
    REQUEST-CHANGES.

    The filled slots are the quality lever; a lazily filled one turns every lens generic.

  3. Collect and verify. A one-word or placeholder return is a STUB, not a review: re-run that lens alone (#455). Verify every finding's premise yourself before coding a fix — read the comments on the item it names first — and REFUTE deliberate design with its mechanism.

  4. Fold accepted findings into ONE commit, with a plan-miss: line per finding the plan never named.

  5. Disposition each finding in a review thread. The bots open theirs; open each local finding the same way, then reply and resolve:

    sh
    pr=<N>; head=$(gh pr view $pr --json headRefOid -q .headRefOid)
    # Off the diff's lines: `-f subject_type=file` instead of line + side; a path
    # outside the diff (or removed by it) goes on the first surviving changed file,
    # its location in the body.
    gh api repos/{owner}/{repo}/pulls/$pr/comments -f commit_id=$head \
      -f path=<path> -F line=<n> -f side=RIGHT -F body=@<finding file>
    threads='query($owner:String!,$name:String!,$n:Int!){repository(owner:$owner,name:$name){pullRequest(number:$n){reviewThreads(first:100){totalCount nodes{id isResolved isOutdated path line comments(first:50){nodes{body}}}}}}}'
    gh api graphql -F owner='{owner}' -F name='{repo}' -F n=$pr -f query="$threads"
    gh api graphql -f t=<thread id> -F b=@<disposition file> \
      -f query='mutation($t:ID!,$b:String!){addPullRequestReviewThreadReply(input:{pullRequestReviewThreadId:$t,body:$b}){comment{id}}}'
    gh api graphql -f t=<thread id> \
      -f query='mutation($t:ID!){resolveReviewThread(input:{threadId:$t}){thread{isResolved}}}'
  6. Record each row's run as the gate defines, naming the head the lens judged; a push the gate does not carry over needs the lens run again at the new head.

  7. Before merge, judge against the gate.

Show full SKILL.md (243 more words)Show less

Whole-codebase scope

Population = the tree, where the aggregate-only classes live (cross-PR interaction, drift, debt accretion, coverage-topology gaps, invariant erosion, orphaned surface). Prefer a Workflow, else parallel Agents; scale to the ask. Scout the work-list → subsystem finders (site and Raycast RENDERED) plus per-factor finders (arch invariants · concurrency/liveness · security threat model · performance · mutation depth on hot logic · silent failure · drift · deep modules) plus a SYSTEM lens (decomposition, dependency directions) and a DRY census → adversarial verify, default REFUTE, one skeptic per finding and 2–3 differentiated ones for security/concurrency, majority confirms → loop until two consecutive rounds come back empty → a completeness critic ("what modality did we NOT run?" seeds the next round) → dedup and rank, keeping the refuted-as-deliberate list → dispositions plus a stale-phrase sweep (rg --hidden) at 0. Involved refactors land in-arc; each bigger item the owner keeps becomes a FOLLOW-UP PR.

Red flags

ThoughtReality
"CI is green, that's enough"CI can't see design, blast radius, drift, or a deliberate-looking real bug.
"The bots will render it"A bot reads the diff and the base tree; a local row's run is yours.
"I'll note the finding and move on"Every finding needs a terminal state.
"The diff looks clean, we're done" (audit)Drift, debt accretion and erosion accumulate between PRs; only the audit sees them.
"The finder found it, report it" (audit)A separate skeptic tries to REFUTE each survivor first.
"Just unify the duplication"Some duplication is documented deliberate separation; read the item's comments first.

© IvanWng97, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/local-review of IvanWng97/pixtuoid.

Open the folder on GitHubat commit 413c70c

Compare with similar skills

Local Review 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.

Local Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Local Review this skillIvanWng97/pixtuoid491—~1.4kAutomated safety check: PassMIT
Image to Three.js Modelimg2threejs/img2threejs18k1 repos~8.2kAutomated safety check: PassApache-2.0
Web CloneJane-xiaoer/claude-skill-web-clone1k1 repos~2.7kAutomated safety check: PassMIT
Threejs Game Directormajidmanzarpour/threejs-game-skills2.5k—~2.2kAutomated safety check: PassMIT
Game Asset Generatorhtdt/godogen7.1k—~2.8kAutomated safety check: PassMIT
Threejs Gameplay Systemsvalkor-ai/loom1.2k1 repos~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Image to Three.js Model

    img2threejs/img2threejs

    Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.

    18k GitHub starsUsed in 1 repo~8.2k tokens
    Game DevelopmentAuto-check passed
  • Web Clone

    Jane-xiaoer/claude-skill-web-clone

    网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 /…

    1k GitHub starsUsed in 1 repo~2.7k tokens
    Game DevelopmentAuto-check passed
  • Threejs Game Director

    majidmanzarpour/threejs-game-skills

    Entrypoint for building, upgrading, and finishing Three.js browser games.

    2.5k GitHub stars~2.2k tokensUpdated 13 days ago
    Game DevelopmentAuto-check passed
  • Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.

    7.1k GitHub stars~2.8k tokensUpdated 9 days ago
    Game DevelopmentAuto-check passed
  • Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…

    1.2k GitHub starsUsed in 1 repo~1.4k tokens
    Game DevelopmentAuto-check passed
  • Uloop Execute Dynamic Code

    CyberAgentGameEntertainment/NovaShader

    Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.

    1.6k GitHub starsUsed in 1 repo~1.9k tokens
    Game DevelopmentAuto-check passed

More from IvanWng97/pixtuoid

  • Beautify Decoration

    IvanWng97/pixtuoid

    Iterate on the visual identity of a top-down pixel-art decoration (sprite + layout integration) in pixtuoid.

    491 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Procedural Lofi

    IvanWng97/pixtuoid

    Generate a royalty-free lofi (or rain / typing / chime / any ambient) soundtrack ENTIRELY in code — no sampled audio ships.

    491 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Add Source

    IvanWng97/pixtuoid

    Wire a new agent-CLI Source adapter into pixtuoid (a new coding CLI whose sessions become office sprites).

    491 GitHub stars~443 tokensUpdated today
    Auto-check passed
  • Add Theme

    IvanWng97/pixtuoid

    Add a new color theme to pixtuoid (a full Theme palette, rendered into the office).

    491 GitHub stars~449 tokensUpdated today
    Auto-check passed

Questions about Local Review

What does Local Review do?

Run pixtuoid's review locally at either scope — a DIFF review (one lens per matching REVIEW.md local escalation row; the correctness and design lenses are the automatic CI review's, never re-run…. Local Review is an agent skill from IvanWng97/pixtuoid.md local escalation row; the correctness and design lenses are the automatic CI review's, never re-run locally) or a whole-codebase AUDIT (subsystem × factor fan-out).

When should I use Local Review?

Local Review fits situations like: A diff touches a local-only row; on is this ready to merge; on whole-codebase review / pre-release / periodic audit.

How do I install Local Review in Claude Code?

Run `npx skills add IvanWng97/pixtuoid --skill local-review -a claude-code`. Or copy the skill folder (.claude/skills/local-review in IvanWng97/pixtuoid) into .claude/skills/local-review in your project. Claude Code loads it when a task matches its description.

How do I install Local Review in Codex?

Run `npx skills add IvanWng97/pixtuoid --skill local-review -a codex`. Or copy the skill folder (.claude/skills/local-review in IvanWng97/pixtuoid) into .agents/skills/local-review in your project. Codex loads it when a task matches its description.

Can I use Local Review 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 IvanWng97/pixtuoid --skill local-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-review, .gemini/skills/local-review, .github/skills/local-review and .opencode/skills/local-review in your project.

What does Local Review need to run?

Going by SKILL.md and its folder, Local Review needs the command-line tools its instructions call (gh and rg).

Does Local Review access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Local Review 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 Local Review use?

Local Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Local Review use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 Local Review?

Skills that share tags, products or a category with Local Review: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.5k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local Review?

IvanWng97 (a GitHub user) maintains it in IvanWng97/pixtuoid, which has 491 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 11, 2026.

Source: IvanWng97/pixtuoid on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.