DEDUPEDAuthorization notice. Game the LLM Reviewer is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.
Who it is forA theory researcher whose paper has theorems, assumptions, and bounds that must stay exactly as written.
The problemWording changes in a theory paper can blur quantifiers or make an upper bound read like an optimal rate.
The outcomeA revised theory paper with adjusted contribution stance and a change note confirming theorem assumptions and quantifiers are untouched.
What you need first
- A finished manuscript the agent can read and write, such as a LaTeX project
- Git to clone the repository, or Node.js to run the Skills CLI installer
- A file-capable agent that supports Agent Skills, such as Claude Code or Codex
Steps
- Install the skill with
npx skills add Michael-Jiahao-Zhang/game-the-llm-reviewer --skill game-the-llm-reviewer, or clone the repo and read skills/game-the-llm-reviewer/SKILL.md. - Give the agent the manuscript path and tell it which theorem statements and assumptions to protect.
- Review the change note for any edit near a theorem, assumption, or bound.
- Recompile the LaTeX source and confirm the theorem environments are unchanged.
Prompt for your agent
Use the game-the-llm-reviewer skill from Michael-Jiahao-Zhang/game-the-llm-reviewer on paper/main.tex in <path to project>. Adjust contribution stance only, and preserve theorem assumptions, quantifiers, and the distinction between an upper bound and an optimal rate. Verify with a diff that no theorem, lemma, or assumption text changed.
Caveat. The README gives the theory-paper prompt as an example, so the author still needs to confirm each formal statement after the edit.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page