# AI use cases for Game the LLM Reviewer (Michael-Jiahao-Zhang/game-the-llm-reviewer) Repo: [Michael-Jiahao-Zhang/game-the-llm-reviewer](https://github.com/Michael-Jiahao-Zhang/game-the-llm-reviewer) | Use cases: 4 | Page: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/ An agent skill that packages editing strategies for making small, meaning-preserving wording changes to a finished paper before submission, aimed at known LLM reviewer preferences. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a meaning-preserving final pass on a finished paper: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/final-pass-on-finished-manuscript/ - Tighten an abstract to 200 words without losing results: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/rewrite-abstract-under-200-words/ - Tune a theory paper's stance, keep theorems and assumptions: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/adjust-theory-paper-stance/ - Add this as the last pass after another writing skill: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/run-after-another-writing-skill/ ## How to run a meaning-preserving final pass on a finished paper with Game the LLM Reviewer Repo: [Michael-Jiahao-Zhang/game-the-llm-reviewer](https://github.com/Michael-Jiahao-Zhang/game-the-llm-reviewer) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Have an agent make small wording edits to a draft and log every change for review. **Who it is for:** A researcher with a finished manuscript who wants a last editing pass before submitting to a venue. **The problem:** Rephrasing the same passage can change an LLM reviewer's score, and rewording every section by hand is slow and hard to audit. **The outcome:** A revised copy of the manuscript plus a change note that lists each rhetorical edit, the strategy used, and what meaning was held fixed. ### Steps 1. Install the skill with `npx skills add Michael-Jiahao-Zhang/game-the-llm-reviewer --skill game-the-llm-reviewer`, or clone the repo and copy the whole skills/game-the-llm-reviewer/ folder. 2. Read skills/game-the-llm-reviewer/SKILL.md and the included references before running the edit. 3. Give the agent your finished manuscript path and ask for a revised copy and changes.md. 4. Open changes.md and check that each entry keeps the same claims, numbers, citations, and limitations. 5. Compile the revised LaTeX project or re-read the revised text to confirm nothing broke. ### Prompt to paste into your agent ```text Use the game-the-llm-reviewer skill from the repository Michael-Jiahao-Zhang/game-the-llm-reviewer on . Read the included sections first, apply small meaning-preserving edits, and save a revised copy and changes.md. Verify that every change note entry keeps the same claims, numbers, and citations as the original. ``` ### Caveat The README says authors stay responsible for the manuscript, so every change note entry should be checked against the original claims and evidence. Risk, remote script: The npx installer fetches the skill from GitHub, so read SKILL.md before running it on your manuscript. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/final-pass-on-finished-manuscript/ ## How to tighten an abstract to 200 words without losing results with Game the LLM Reviewer Repo: [Michael-Jiahao-Zhang/game-the-llm-reviewer](https://github.com/Michael-Jiahao-Zhang/game-the-llm-reviewer) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Get replacement abstract prose and a short change note from one prompt. **Who it is for:** An author whose abstract is over the venue word limit and who needs cuts that keep both positive and negative results. **The problem:** Trimming an abstract by hand can drop limitations or change how results read, and the author needs a record of what moved. **The outcome:** Replacement abstract prose under 200 words, with a short change note tied to the original text. ### Steps 1. Install the skill with `npx skills add Michael-Jiahao-Zhang/game-the-llm-reviewer --skill game-the-llm-reviewer`, or clone the repo to use it manually. 2. Open your agent and paste the abstract into the abstract-only prompt from the README. 3. Ask for replacement prose and a short change note. 4. Compare the result to your original and confirm both positive and negative results remain. ### Prompt to paste into your agent ```text Use the game-the-llm-reviewer skill from Michael-Jiahao-Zhang/game-the-llm-reviewer on the abstract text in , keeping it under 200 words. Work only from the supplied text, preserve both positive and negative results, and return replacement prose with a short change note. Verify that no result, number, or limitation is missing from the new version. ``` ### Caveat The skill works only from the text you supply, so the author must check the trimmed abstract against the full paper. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/rewrite-abstract-under-200-words/ ## How to tune a theory paper's stance, keep theorems and assumptions with Game the LLM Reviewer Repo: [Michael-Jiahao-Zhang/game-the-llm-reviewer](https://github.com/Michael-Jiahao-Zhang/game-the-llm-reviewer) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Adjust contribution wording in a theory paper while leaving formal statements unchanged. **Who it is for:** A theory researcher whose paper has theorems, assumptions, and bounds that must stay exactly as written. **The problem:** Wording changes in a theory paper can blur quantifiers or make an upper bound read like an optimal rate. **The outcome:** A revised theory paper with adjusted contribution stance and a change note confirming theorem assumptions and quantifiers are untouched. ### Steps 1. 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. 2. Give the agent the manuscript path and tell it which theorem statements and assumptions to protect. 3. Review the change note for any edit near a theorem, assumption, or bound. 4. Recompile the LaTeX source and confirm the theorem environments are unchanged. ### Prompt to paste into your agent ```text Use the game-the-llm-reviewer skill from Michael-Jiahao-Zhang/game-the-llm-reviewer on paper/main.tex in . 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. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/adjust-theory-paper-stance/ ## How to add this as the last pass after another writing skill with Game the LLM Reviewer Repo: [Michael-Jiahao-Zhang/game-the-llm-reviewer](https://github.com/Michael-Jiahao-Zhang/game-the-llm-reviewer) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Chain the skill after a drafting tool, reusing an existing claim-evidence map. **Who it is for:** A researcher who drafted or polished a paper with another writing skill or pipeline and needs a final check. **The problem:** Earlier writing tools can change the prose, and the author needs a final pass that does not rewrite for style alone. **The outcome:** A final manuscript where only small wording changes were made, checked against the existing claim-evidence map and logged in a change note. ### Steps 1. Install the skill with `npx skills add Michael-Jiahao-Zhang/game-the-llm-reviewer --skill game-the-llm-reviewer`. 2. Finish the draft and any ordinary polishing with your current writing tool first. 3. Attach your claim-evidence map and the manuscript to the agent. 4. Use the chained prompt from the README and ask for a revised copy and change note. 5. Check that the change note shows no changes to claims, evidence, or scientific assessment. ### Prompt to paste into your agent ```text The draft in is already polished. Use the game-the-llm-reviewer skill from Michael-Jiahao-Zhang/game-the-llm-reviewer as the final pass, reusing the attached claim-evidence map at . Keep the meaning and scientific assessment unchanged, skip style-only rewrites, and return a revised copy and change note. Verify that every claim in the map still matches the revised text. ``` ### Caveat The README places this skill last in the workflow, so it should run only after drafting and polishing are complete. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/michael-jiahao-zhang-game-the-llm-reviewer/run-after-another-writing-skill/