Skip to content
Agentmart
Submit a tool

ae-review

Review code or another requested artifact for material problems.

Skill by AndreaCatalucci

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying ae-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/andreacatalucci-ae-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 code or another requested artifact for material problems. Use for code review, document review, browser QA, and Xcode verification; apply fixes when requested.

Use cases: documents, testing

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/ae-review

What's inside

Skill name
ae-review
Description
Review code or another requested artifact for material problems. Use for code review, document review, browser QA, and Xcode verification; apply fixes when requested.
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Files (5)

  • SKILL.md
  • browser.md · recipes/
  • document.md · recipes/
  • perspectives.md · recipes/
  • xcode.md · recipes/

SKILL.md (first lines)

# Review

1. Resolve the target, intended change, and concrete review question. Reuse current review evidence for unchanged scope; review changes and unresolved risks. For a diff-only request with an empty diff, report no changes and stop; that does not establish product correctness.
2. Load at most one matching recipe:

- [`document.md`](recipes/document.md) for an Opportunity Brief, Concept Notebook, Implementation Plan, Delivery Map, or other specification;
- [`browser.md`](recipes/browser.md) for a real web flow;
- [`xcode.md`](recipes/xcode.md) for an Apple project;
- [`perspectives.md`](recipes/perspectives.md) for code, including the current diff.

The loaded recipe is the charge. `perspectives.md` may name several; every other recipe names one.

3. Select the smallest set of perspectives that answers the review question. On `perspectives.md`, use one perspective when it covers the question; add another only for a separate material risk. For an open-ended code review, use correctness plus any materially distinct perspective triggered by the target. A request for a thorough review takes every materially matching row. Name the trigger for each selection. On any other recipe, take its charge as the one perspective.
4. Inspect directly for a bounded single-perspective review unless independent review is requested or a separate reviewer would materially improve confidence. Delegate perspectives when independence or parallel inspection justifies the overhead. Each delegated packet contains the intended change, target paths, charge, and finding format below, with no inherited conversation. If required independence is unavailable, report that limitation; direct inspection is not an independent pass.
5. Complete each direct inspection and collect every delegated finding list or clean pass. A failed spawn or missing return is a failed perspective. Confirm each kept finding at the cited location. Keep findings that name a consequence and a correction. Collapse duplicates. Style survives only when it hides a defect.
6. Report findings ordered by severity, perspectives covered, whether review was direct or independent, and any failed or unavailable perspectives. A clean review states that plainly. Apply fixes when requested. Wording fixes run the `unslop` skill.

Each finding contains:

- severity;
- precise location (file and line, passage, or page) when applicable;
- the concrete consequence;
- the smallest useful correction.

Each perspective reports findings and leaves the tree unchanged.

From AndreaCatalucci/andrea-engineering, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 6, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from AndreaCatalucci

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 ae-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 ae-review?

CallGet help
Cite this page

ae-review skill. Agent Mart. https://agentmart.dev/skills/andreacatalucci-ae-review (last updated 2026-10-24)