Agent skill

Update Review Rules

by imbue-ai in imbue-ai/sculptor

Add a new issue type to one of Sculptor's review-rule docs. An agent skill from imbue-ai/sculptor.

MITAuto-check passedTesting & QA

Install Update Review Rules

skills CLI
$ npx skills add imbue-ai/sculptor --skill update-review-rules -a claude-code

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

GitHub CLI
$ gh skill install imbue-ai/sculptor update-review-rules --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/imbue-ai/sculptor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/update-review-rules .claude/skills/update-review-rules && 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
update-review-rules
GitHub stars
238
Token cost
~1.4k tokens
SKILL.md length
610 words
Files
1
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

Add a new issue type to one of Sculptor's review-rule docs. An agent skill from imbue-ai/sculptor.

  • Works in 9 steps: Read all the review docs listed above to… → Decide which file the new rule belongs in → Determine whether an existing rule… → …
  • Youve encountered a class of bugs
  • SKILL.md covers Input and Steps
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Update Review Rules is an agent skill from imbue-ai/sculptor. Add a new issue type to one of Sculptor's review-rule docs. Use when you've encountered a class of bugs, anti-patterns, or flaky test patterns that should be caught in future reviews.

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 Testing & QA, covering Failing and flaky tests. It works with React. The repository describes itself as: Build product with grounded, parallel coding agents. The licence is MIT.

When your agent uses it

  • Youve encountered a class of bugs
  • Flaky test patterns that should be caught in future reviews

Example prompts

  • “s review-rule docs. Use when you”
  • “/update-review-rules”

Workflow steps

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

  1. Read all the review docs listed above to understand the existing rules, their format, and their naming conventions.
  2. Decide which file the new rule belongs in
  3. Determine whether an existing rule already covers the issue (check all the docs). If it does, tell the user which rule covers it and ask…
  4. Draft a new rule following the exact format of existing rules in the chosen file.
  5. Choose a clear snake_case name that describes the problem (not the fix). Follow the naming conventions
  6. Write the rule to be generic — it should describe a class of issues, not a single instance. Strip out details specific to the user's…
  7. Only include code examples when absolutely necessary. Lean on the description, explanation, and "What to look for" patterns to convey the…
  8. Place the new rule near related rules in the chosen file. Use your judgement — group it with rules about similar topics (effects, state…
  9. Show the user the new rule (and which file you're adding it to) and ask for confirmation before writing it to the file.

What it can do on your machine

Read from SKILL.md and the folder at commit f847102. 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 markdown).

    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

Update Review Rules loads about 1.4k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 610 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
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 imbue-ai/sculptor at commit f847102, republished under its MIT licence (© imbue-ai). 610 words, ~1,380 tokens.

Download SKILL.mdSave it as .claude/skills/update-review-rules/SKILL.md (or your agent's skills folder).
name
update-review-rules
description
Add a new issue type to one of Sculptor's review-rule docs. Use when you've encountered a class of bugs, anti-patterns, or flaky test patterns that should be caught in future reviews.

Add a Review Rule

Add a new issue type to one of Sculptor's review-rule docs to prevent a class of issues from recurring.

The review-rule docs:

  • docs/development/review/react.md — generic React rules that would apply in any React codebase: effects, state, refs, render purity, performance, props, lists.
  • docs/development/review/sculptor.md — Sculptor-specific frontend conventions: backend data hooks (WS-pushed atoms, HTTP-pulled TanStack queries), Jotai atom usage, component-level invariants tied to our codebase.
  • docs/development/review/design.md — design quality judgments a linter can't make: Radix-first component usage, correct token selection, reuse of shared components, consistent UI copy.
  • docs/development/review/file_structure.md — file placement, feature layout, and naming: code located with its feature, kind-directory anatomy, helper/subfeature thresholds, component naming and domain vocabulary.
  • docs/development/review/integration_tests.md — Sculptor integration test rules: Playwright assertion patterns, test isolation, POM usage, flaky-pattern avoidance.

Input

The user provides a description of the problem — this could be:

  • A bug they just fixed and want to prevent in the future
  • A code pattern they noticed during review that should be flagged
  • A flaky test or test pattern that should be caught earlier
  • A link to a file/line or diff that demonstrates the issue

Steps

  1. Read all the review docs listed above to understand the existing rules, their format, and their naming conventions.

  2. Decide which file the new rule belongs in:

    • If the rule is about Playwright tests, integration test patterns, or test isolation/structure → integration_tests.md.
    • If the rule is about visual/design quality: design-system usage, tokens, component reuse, UI copy → design.md.
    • If the rule is about where files live, when files/directories are warranted, or how things are named → file_structure.md.
    • If the rule references Sculptor-specific frontend hooks, atoms, file paths, or our data-flow conventions (e.g. useUnifiedStream, BackendQueryResult, workspaceAtomFamily) → sculptor.md.
    • If the rule is purely about React's framework primitives and would apply in any React codebase → react.md.
    • When in doubt for frontend rules, prefer sculptor.md over react.md; revisit if the rule turns out to be more generic than expected.
  3. Determine whether an existing rule already covers the issue (check all the docs). If it does, tell the user which rule covers it and ask if they'd like to refine that rule instead. Do not add a duplicate.

  4. Draft a new rule following the exact format of existing rules in the chosen file.

    For react.md and sculptor.md (flat list, ## rule_name headings):

    markdown
    ---
    
    ## `snake_case_rule_name`
    
    **Question:** A yes/no question that a reviewer can ask about the code.
    
    One or two paragraphs explaining why this is a problem and what the correct approach is.
    
    **What to look for:**
    - Concrete pattern or code smell to search for
    - Another pattern
    
    **Fix:** (optional) Brief description of how to fix it.
    
    **Exceptions:** (optional) Cases where this pattern is acceptable.

    For integration_tests.md (sectioned, ### rule_name inside an existing ## Section):

    markdown
    ---
    
    ### `snake_case_rule_name`
    
    **Question:** ...
    
    [rest is the same as above, but the heading is `###` and the rule lives
    under one of the existing `## Section` groupings — pick the section that
    matches the rule's topic, e.g. "Playwright Assertions", "Test Isolation",
    "Test Structure"]
  5. Choose a clear snake_case name that describes the problem (not the fix). Follow the naming conventions:

    • Use no_ prefix for patterns that should not exist (e.g., no_effect_chains, no_sleep_then_assert)
    • Use use_ prefix for prescriptive positive patterns (e.g., use_derived_atoms, use_expect_not_assert)
    • Use a descriptive noun/adjective for structural issues (e.g., monolithic_component, unstable_list_keys)
  6. Write the rule to be generic — it should describe a class of issues, not a single instance. Strip out details specific to the user's particular bug (component names, variable names, business logic, Linear ticket IDs). For sculptor.md and integration_tests.md rules, naming our codebase concepts is fine (and expected); for react.md rules, the content should apply in any React codebase. The "What to look for" section should describe concrete, recognizable patterns a reviewer can spot in code.

  7. Only include code examples when absolutely necessary. Lean on the description, explanation, and "What to look for" patterns to convey the rule. The rule should be self-contained without code. Test rules sometimes benefit more from a "Bad/Good" pair because Playwright APIs are pattern-heavy.

  8. Place the new rule near related rules in the chosen file. Use your judgement — group it with rules about similar topics (effects, state, atoms, refs, performance, Playwright assertions, test isolation, etc.).

  9. Show the user the new rule (and which file you're adding it to) and ask for confirmation before writing it to the file.

© imbue-ai, 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/update-review-rules of imbue-ai/sculptor.

Open the folder on GitHubat commit f847102

Compare with similar skills

Update Review Rules 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.

Update Review Rules compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Review Rules this skillimbue-ai/sculptor238—~1.4kAutomated safety check: PassMIT
React18 Batching Patternsgithub/awesome-copilot40k1 repos~621Automated safety check: PassMIT
Bug Hunteroctanejs/octane1.5k—~707Automated safety check: PassMIT
Suede Code ReviewJasonColapietro/suede-creator-skills127—~7.1kAutomated safety check: PassMIT
Test Guided Migration AssistantArabelaTso/Skills-4-SE253—~1.8kAutomated safety check: PassApache-2.0
Pester Failure AnalysisPowerShell/PowerShell56k—~5.1kAutomated safety check: PassMIT

Similar skills

  • React18 Batching Patterns

    github/awesome-copilot

    Official

    Provides exact patterns for diagnosing and fixing automatic batching regressions in React 18 class components.

    40k GitHub starsUsed in 1 repo~621 tokens
    Testing & QAAuto-check passed
  • Bug Hunter

    octanejs/octane

    Find and fix a bug in the octane monorepo. An agent skill from octanejs/octane.

    1.5k GitHub stars~707 tokensUpdated today
    DevelopmentAuto-check passed
  • Suede Code Review

    JasonColapietro/suede-creator-skills

    Suede AI findings-only code review with full context: changed files, callers, contracts, and deploy surface.

    127 GitHub stars~7.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Test Guided Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically updates a codebase to a new language version, framework version, or library update while ensuring all tests still pass.

    253 GitHub stars~1.8k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Pester Failure Analysis

    PowerShell/PowerShell

    Investigates failing Pester tests in PowerShell CI jobs by following a six-step workflow from pull request status to documented fix recommendations.

    56k GitHub stars~5.1k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Guides changes and reviews of the Cucumber and Playwright end-to-end suite under `e2e/`: feature files, step definitions, support code, tags, locators and assertions.

    158k GitHub stars~682 tokensUpdated today
    Testing & QAAuto-check passed

More from imbue-ai/sculptor

All 29 skills in this repo
  • Auto QA Iphone

    imbue-ai/sculptor

    QA the Sculptor mobile web UI on a real iOS Simulator, driven headlessly from a Mac.

    238 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed
  • Measure React Renders

    imbue-ai/sculptor

    Compare React component render counts between origin/main and the current branch during a user-defined UI scenario (e.g.

    238 GitHub stars~603 tokensUpdated yesterday
    Auto-check passed
  • Post PR To Slack

    imbue-ai/sculptor

    Post a one-line PR announcement to a Slack channel, and mark it :merged: when the PR merges.

    238 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Batch Claude Runner

    imbue-ai/sculptor

    Run Claude programmatically against collections of files in the codebase.

    238 GitHub stars~308 tokensUpdated yesterday
    Auto-check passed
  • Build Sculptor Extension

    imbue-ai/sculptor

    Build or modify a Sculptor extension — a runtime ESM module loaded into the Sculptor UI.

    238 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed
  • Code Review Checklist

    imbue-ai/sculptor

    Review a set of code changes against Sculptor's review categories and produce a markdown findings table.

    238 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Update Review Rules

What does Update Review Rules do?

Add a new issue type to one of Sculptor's review-rule docs. An agent skill from imbue-ai/sculptor. Update Review Rules is an agent skill from imbue-ai/sculptor. Add a new issue type to one of Sculptor's review-rule docs.

When should I use Update Review Rules?

Update Review Rules fits situations like: youve encountered a class of bugs; flaky test patterns that should be caught in future reviews.

How do I install Update Review Rules in Claude Code?

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

How do I install Update Review Rules in Codex?

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

Can I use Update Review Rules 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 imbue-ai/sculptor --skill update-review-rules -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-review-rules, .gemini/skills/update-review-rules, .github/skills/update-review-rules and .opencode/skills/update-review-rules in your project.

What does Update Review Rules need to run?

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

Does Update Review Rules 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 Update Review Rules 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 Update Review Rules use?

Update Review Rules 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 Update Review Rules use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 Update Review Rules?

Skills that share tags, products or a category with Update Review Rules: React18 Batching Patterns (github/awesome-copilot, 40k stars), Bug Hunter (octanejs/octane, 1.5k stars), Suede Code Review (JasonColapietro/suede-creator-skills, 127 stars) and Test Guided Migration Assistant (ArabelaTso/Skills-4-SE, 253 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Review Rules?

imbue-ai (a GitHub organization) maintains it in imbue-ai/sculptor, which has 238 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 9, 2026.

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