Maintainer of this skill?
by LilMGenius
The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.
# Add to your Claude Code skills
git clone https://github.com/LilMGenius/paperthinGuides for using ai agents skills like paperthin.
See how paperthin compares with popular alternatives.
paperthin is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by LilMGenius. The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method. It has 1,384 GitHub stars.
paperthin's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/LilMGenius/paperthin" and add it to your Claude Code skills directory (see the Installation section above).
paperthin is primarily written in JavaScript. It is open-source under LilMGenius on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh paperthin against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
The skillbook for recursive self-improvement (RSI).NVIDIA's latest proof, unpacked with timeless engineering.Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.
On any agent | Codex, Claude Code, OpenCode, Cursor, Grok Build, Grok Bot, Muse, Pi, etc.
"Best part is no part." Elon Musk[^musk]
Built by Bran Lee2026: OpenAI harness engineering hackathon (Ralphthon Seoul #2, held simultaneously in Seoul and SF), 1st place, the only solo team against big-tech and top-university PhD teams2026: Claude Code official meetup invited speaker, twice2026: Google DeepMind AI hackathon invited judge2014: Korea Olympiad in Informatics (KOI) national contest, silver award2009~: coding since age 9
Quickstart · The Map · The Index · The Problem · The Proof · Credits
Read in: English · 中文 · हिन्दी · Español · العربية · Português · Русский · 日本語 · Français · Deutsch · 한국어
Pick one route per agent; installing two loads every skill twice.
codex plugin marketplace add LilMGenius/paperthin && codex plugin add paperthin@paperthin
claude plugin marketplace add LilMGenius/paperthin && claude plugin install paperthin@paperthin
/plugin, open Marketplaces, select paperthin and choose Enable auto-update, once.npx skills@latest add LilMGenius/paperthin --global --agent '*' && node "$HOME/.agents/skills/re0-upgrade/scripts/schedule/schedule.mjs" install
/paperthin, then your dream. That's it. Want the mechanism? Relax, there's /re0-tutorial.Installed it before? Run /re0-upgrade once in a fresh session.
Not sure? Tell your agent install https://github.com/LilMGenius/paperthin. A web chat takes llms-full.txt.
How many artifacts, and across how much time?
depth/| Skill | What it does | Invoker | Read-only |
|---|---|---|---|
| ♻️ re0 | Rewrites a messy, much-patched document or file as a clean first version instead of patching it again | model | |
| 🗜️ debloat | Trims bloated writing or code down to what carries weight, without losing a rule or a behavior | model | |
| 🔃 re0-order | Puts a jumbled list back in a sensible order under one stated rule; it moves items and rewords nothing | model | |
| 🧰 detool | Replaces brand and tool names in lasting docs with what they actually do, so the docs outlive the tools | model | |
| 🎨 re0-style | Fixes code to match the project's own style, and asks where the project itself does it two ways | model | |
| ✂️ dedash | Removes the long dashes an agent sprinkles into sentences, and keeps hyphens, ranges and label dashes | user | |
| ⸱ dedot | In Korean text, suggests a comma or a linking word, with a reason, for each middle dot that joins a list | user | ✔ |
| 🧭 readback | Checks it understood your request before working, and asks only when two readings really differ | model | ✔ |
| 🏹 aim | Reads the files or text you hand over and suggests what you likely want, so you only confirm | model | ✔ |
| 📏 modelchk | Picks the cheapest model tier and thinking effort that still do the job well | model | ✔ |
| 🧹 elon | Suggests dropping or deferring requirements and commitments kept only out of habit, with where each came from; never touches rules set from outside | model | ✔ |
| 🧩 scopechk | Checks, by the target's own written scope, whether a new piece belongs where you want to put it, and names a better home if not | model | ✔ |
| 😈 hate | Plays the hostile critic: the one objection that could sink your plan, and the cheapest test to settle it | user | |
| 🧠 macrothink | Asks several fresh minds the question without your framing and shows first where they disagree | user | ✔ |
| 🔀 crossthink | When every option looks alike, borrows working ideas from five or more unrelated fields and keeps only the new ones | model | ✔ |
| ⚖️ re0-decide | Turns the material behind a decision into a checklist whose verdict comes from your own answers; it never picks for you | user | ✔ |
| 🧐 whychk | Questions a decision you just made until you can explain it, or shows where the reasoning has a hole | user | ✔ |
| 🛣️ autobahn | Sets the risky parts of a task aside first with safer alternatives, runs the rest at full speed, and logs what was left out | model | |
| 🥄 sip | Right after any change, before you call it done, runs paperthin's own checks on your output | model | |
| 🚿 shower | Hands your work to a fresh reader with no background and asks whether it makes sense on its own | model | ✔ |
| 🔬 factchk | Checks claims against real sources both ways: the absurd may be true, and the obvious may be false | model | |
| 🧪 mandela | Checks whether a test or metric is grading itself, or whether real outside truth decides the result | model | ✔ |
| 🎭 demock | Finds fakes and silent fallbacks in live code that make a success report false, and suggests the real fix | model | |
| 🥸 deid | Finds one person's or company's data in shared files, replaces it with the role it plays, and lists the old commits that still hold it | model | |
| 🧾 re0-git | Rewrites a finished commit's message with its dates and place kept, so the git history alone lets anyone take over | user | |
| 🚀 re0-release | Runs the release checklist, then tags and publishes once you confirm | user | |
| 🤝 re0-merge | Reviews and lands someone else's contribution, keeps their credit, and explains any change made to it | user | |
| 🧨 re0-squash | Republishes a GitHub repository as one signed commit with the same files, leaving no old commit reachable | user |
breadth/| Skill | What it does | Invoker | Read-only |
|---|---|---|---|
| 🧲 ssotize | Finds a fact copied in many places, gives it one home once you approve, and points the rest there | model | |
| 🔗 ssotize-local | Merges duplicate files or folders into one real copy the others link to, with a tested way back | model | |
| 📖 re0-readme | Sorts a README and its AGENTS.md so each line sits in the file whose reader needs it | model | |
| 📥 re0-import | Files handed-over material into the right page of an existing knowledge base, by that base's own rules, and reports what has no home | user | |
| 🆙 re0-upgrade | Brings your install up to the full current catalog in one confirmed step: retires renamed skills and adds new ones | user |
coil/| Skill | What it does | Invoker | Read-only |
|---|---|---|---|
| 🚪 paperthin | The one command to remember: type your dream after it | user | |
| 🪜 re0-workflow | For one goal, picks which skills to run in which order, shows you, then runs them and stops where you must act | model | |
| 📝 re0-memo | Pulls the lessons, and the mistakes to avo |