Skip to content
TrustedSkillsbeta
Back to all skills

Icml Reviewer

Checked
sundial-org·vlatest·other

This AI analyzes research papers to assess their quality and identify potential issues for improved clarity and impact in ICML submissions.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add sundial-org/skills --skill icml-reviewer -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

sundial-org

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned sundial-org/skills at 5a3bf9fdc4.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
5a3bf9fdc4
Manifest
skills/icml-reviewer/SKILL.md
Scanned
4 files, 755 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The icml-reviewer skill empowers AI agents to critically evaluate research papers submitted to the International Conference on Machine Learning (ICML). It analyzes manuscripts against specific academic criteria, identifying strengths, weaknesses, and potential contributions within the machine learning domain.

When to use it

  • You need an automated second opinion on a draft paper before submitting it to ICML or similar top-tier conferences.
  • You want to simulate peer review feedback to identify logical gaps or missing experimental results in your methodology.
  • You are preparing for a job interview involving research and need to practice critiquing recent ML literature.
  • You wish to generate structured summaries of complex papers that highlight their novelty and reproducibility.

Key capabilities

  • Evaluates manuscripts based on ICML-specific review standards.
  • Identifies technical flaws, unclear arguments, or insufficient experimental validation.
  • Assesses the novelty and significance of proposed machine learning methods.
  • Provides structured feedback suitable for peer reviewers.

Example prompts

  • "Act as an ICML reviewer and critique this abstract: [paste abstract]. Focus on clarity and novelty."
  • "Review the following methodology section for logical consistency and reproducibility issues."
  • "Generate a summary of this paper's contributions and rate its potential acceptance likelihood at ICML."

Tips & gotchas

Ensure you provide the full text or relevant sections of the paper, as context is crucial for accurate technical evaluation. While the agent offers expert-level critique, it should be used as a supplement to human review rather than a replacement for final editorial decisions.