Skip to content
Agentmart
Submit a tool

studio-code-review

Review a file or small set of files for standards, architecture, SOLID, performance, testability, and implementation risks, with optional specialist subreviews.

Skill by islee23520

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying studio-code-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/islee23520-studio-code-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review a file or small set of files for standards, architecture, SOLID, performance, testability, and implementation risks, with optional specialist subreviews.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/studio-code-review

What's inside

Skill name
studio-code-review
Description
Review a file or small set of files for standards, architecture, SOLID, performance, testability, and implementation risks, with optional specialist subreviews.
License
MIT
Instructions
159 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Studio Code Review

Use this skill to perform a structured review of implementation quality on a target file, directory, or focused change set.

This skill is read-only unless the user explicitly asks for fixes in a separate step.

## Phase 1 — Load Target Context

Read the target file or files in full.

Also read any nearby coding standards or architecture guidance that exists in the repository, such as:

- `README`
- contributor guides
- architecture docs
- ADRs
- lint or test configuration

If no formal standards are present, infer conventions from neighboring code rather than inventing a style.

## Phase 2 — Identify Relevant Specialists

Determine whether this review would benefit from parallel Task-based specialists.

Examples:

- language or engine specialist for core runtime code
- UI specialist for presentation code
- shader or rendering specialist for graphics code
- QA or testability specialist for logic-heavy changes

Only spawn specialists that clearly fit the target. Avoid project-specific role names when they are not available.

## Phase 3 — ADR and Architecture Intent Check

Look for architecture references in:

- ADR files
- nearby design docs
- story or task files
- code comments or headers

If ADRs or design decisions are referenced, read the relevant parts and compare the implementation against them.

Classify deviations as:

- **Architectural Violation** — contradicts an explicit decision
- **Architecture Drift** — meaningfully diverges without clear justification
- **Minor Deviation** — small difference that does not alter the main design intent

If no references exist, note that the ADR compliance check was skipped.

## Phase 4 — Standards Compliance

Evaluate the implementation against repository conventions and these common checks:

- documentation on public APIs where the codebase expects it
- manageable method size and complexity
- dependency injection or clean dependency boundaries where appropriate
- configuration separated from hardcoded values where the codebase expects that
- interface use versus unnecessary concrete coupling

Do not treat every checklist item as universal law. Match the local codebase style.

## Phase 5 — Architecture and SOLID

Check:

### Architecture

- dependency direction is sensible
- layers are not inverted
- UI does not own core state unless that is the project pattern
- cross-system communication uses the project's preferred coordination pattern
- the code is consistent with established patterns nearby

### SOLID

- single responsibility
- open for extension where appropriate
- subtype substitutability
- interface segregation
- dependency inversion

Call out concrete examples with file and line references when possible.

## Phase 6 — Runtime and Operational Concerns

Check for practical risks relevant to the code under review:

- frame or time-step correctness if real-time logic exists
- unnecessary allocations in hot paths
- null or empty-state handling
- thread-safety or async safety where applicable
- cleanup and lifecycle correctness
- error handling and observability

Tailor this section to the technology involved rather than forcing game-only rules onto every review.

## Phase 7 — Parallel Specialist Reviews

If specialists are useful, spawn them in parallel via Task.

Possible specialist prompts:

- architecture specialist: review dependency boundaries and system fit
- language specialist: review idioms, correctness, and maintainability
- UI specialist: review state ownership, rendering concerns, and accessibility
- QA specialist: review testability, seams, hooks, and acceptance-criteria coverage

Collect all findings before issuing the final review.

## Phase 8 — Output Format

Use this structure:

```markdown
## Code Review: [File or System Name]

From islee23520/lux, MIT.

More from islee23520/lux

Signals

Stars
3
Forks
0
Open issues
16
Last commit (this folder)
Jun 3, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from islee23520

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get studio-code-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying studio-code-review?

CallGet help
Cite this page

studio-code-review skill. Agent Mart. https://agentmart.dev/skills/islee23520-studio-code-review (last updated 2026-10-24)