프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. Google로 로그인하면 리뷰를 쓸 수 있어요.프로토타입 · 30분마다 업데이트
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

paperthin Skill

저장소 ↗

제작자: LilMGenius★ 1,451 (whole repo)skill 28개

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 28 skills

  • Connects Instruction files the AI reads
  • Account or key Not confirmed yet (README not read yet)
  • Category 디자인과 웹
Maker’s original description
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.
제작자용: README에 배지 달기

제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/lilmgenius-paperthin.svg)](https://mcp.popnx.com/en/skills/lilmgenius-paperthin)

함께 쓰기

같은 작업에서 AI를 서비스에 연결하는 MCP

Next AI Draw.io

draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand

제작자: DayuanJiang널리 사용됨↓ 2.2만/주★ 3.7만 저장소 전체의 별3일 전 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

제작자: pascalorg널리 사용됨↓ 1천/주★ 2.6만 저장소 전체의 별4일 전 업데이트

MCP · 서비스 연결컴퓨터 또는 클라우드✓ 서비스 회사 · pascal.app

비슷한 Skill

같은 종류의 작업, Skill 목록과 같은 순서

비슷한 항목과 비교
이 항목
paperthin
impeccablediagram-designfrontend-slidesguizang-ppt-skill
제작자LilMGeniuspbakauscathrynlaveryzarazhangruiop7418
Skill 수281111
GitHub 별1,451111,26567,61332,40729,891
마지막 코드 변경2026년 11월 15일2026년 11월 17일2026년 11월 13일2026년 6월 24일2026년 10월 30일
라이선스MITApache-2.0MITMITAGPL-3.0

LilMGenius의 Skill(지시 묶음) 28개, AI가 읽고 그대로 일해요 · MCP server가 아니에요

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

Install the whole set (28)

If you want every one, let the AI install them in one go. Know 2 things first

  • Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
  • Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Where to install
Please install all 28 skills from https://github.com/lilmgenius/paperthin: aim, autobahn, catchup, debloat, dedash, detool, factchk, feynman, hate, macrothink, mandela, modelchk, nba, prism, re0, re0-git, re0-loop, re0-memo, re0-merge, re0-plan, re0-release, re0-upgrade, re0-work, readchk, reorder, shower, sip, ssotize, for all my projects, putting each at ~/.claude/skills/<skill name> (in Codex use ~/.agents/skills/<skill name>, in Cursor ~/.cursor/skills/<skill name>). Folders in the repo: aim = skills/depth/aim · autobahn = skills/depth/autobahn · catchup = skills/coil/catchup · debloat = skills/depth/debloat · dedash = skills/depth/dedash · detool = skills/depth/detool · factchk = skills/depth/factchk · feynman = skills/depth/feynman · hate = skills/depth/hate · macrothink = skills/depth/macrothink · mandela = skills/depth/mandela · modelchk = skills/depth/modelchk · nba = skills/coil/nba · prism = skills/mesh/prism · re0 = skills/depth/re0 · re0-git = skills/depth/re0-git · re0-loop = skills/coil/re0-loop · re0-memo = skills/coil/re0-memo · re0-merge = skills/depth/re0-merge · re0-plan = skills/coil/re0-plan · re0-release = skills/depth/re0-release · re0-upgrade = skills/breadth/re0-upgrade · re0-work = skills/coil/re0-work · readchk = skills/depth/readchk · reorder = skills/depth/reorder · shower = skills/depth/shower · sip = skills/depth/sip · ssotize = skills/breadth/ssotize. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the full path you will install each one to and wait for me to agree.
Please install all 28 skills from https://github.com/lilmgenius/paperthin: aim, autobahn, catchup, debloat, dedash, detool, factchk, feynman, hate, macrothink, mandela, modelchk, nba, prism, re0, re0-git, re0-loop, re0-memo, re0-merge, re0-plan, re0-release, re0-upgrade, re0-work, readchk, reorder, shower, sip, ssotize, into the project this chat is open in (at .claude/skills/<skill name>; in Codex use .agents/skills/<skill name>, in Cursor .cursor/skills/<skill name>). Folders in the repo: aim = skills/depth/aim · autobahn = skills/depth/autobahn · catchup = skills/coil/catchup · debloat = skills/depth/debloat · dedash = skills/depth/dedash · detool = skills/depth/detool · factchk = skills/depth/factchk · feynman = skills/depth/feynman · hate = skills/depth/hate · macrothink = skills/depth/macrothink · mandela = skills/depth/mandela · modelchk = skills/depth/modelchk · nba = skills/coil/nba · prism = skills/mesh/prism · re0 = skills/depth/re0 · re0-git = skills/depth/re0-git · re0-loop = skills/coil/re0-loop · re0-memo = skills/coil/re0-memo · re0-merge = skills/depth/re0-merge · re0-plan = skills/coil/re0-plan · re0-release = skills/depth/re0-release · re0-upgrade = skills/breadth/re0-upgrade · re0-work = skills/coil/re0-work · readchk = skills/depth/readchk · reorder = skills/depth/reorder · shower = skills/depth/shower · sip = skills/depth/sip · ssotize = skills/breadth/ssotize. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the project name and the full path you will install each one to and wait for me to agree.

Uploading to Claude on the web and apps: you need 28 uploads, one ZIP per skill. Open each skill in the list below to download it

Checked against official docs 2026년 11월 12일 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • aim

    When data lands with a thin ask (files, a repo, a paste, a chat scrollback), read it and propose what the user is trying to do with it for them to confirm. Use the moment material arrives without a fully-formed ask, or when the ask reads thinner than the data suggests.

  • autobahn

    Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licens…

  • catchup

    Rebuild the human's lost context on a project from live state, in plain language: what needs them, what changed, what new words mean. Use when the human returns after a gap, says they can't follow the project anymore, asks what happened or what a term means, or before deciding what to do next when…

  • debloat

    Cut an artifact that has accreted into bloat, prose or code, to its load-bearing density, meaning and behavior preserved. In prose: padding, over-qualification, fused sentences, walls of enumeration, adjacent restatement. In code, behind green tests: comments that restate the code, commented-out co…

  • dedash

    Remove the em and en dashes an agent drops into running prose where a comma, colon, parentheses or a sentence break belongs, from a user-owned scope, keeping hyphens, ranges and dashes that separate a label from its text.

  • detool

    Make durable artifacts portable by replacing incidental stack, vendor, model, CLI, path, quota, or harness nouns with the mechanism they mean, while keeping provenance, runbooks, and tool-subject claims concrete.

  • factchk

    Verify reality-grounded claims against external sources in both directions before they ship: could the 'absurd' be real, could the 'obvious' be false or long-established? Use whenever an artifact, or the sentence you are about to write, asserts something as plausible, realistic, absurd, novel, or i…

  • feynman

    No description from the maker

  • hate

    Attack a plan, design, or argument like you want it to fail before you commit real effort; return the single load-bearing objection and the cheapest experiment that would prove it matters, not a checklist. User-invoked on purpose: a hate-it reflex always in the agent's reach would bias it toward de…

  • macrothink

    User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without treating convergence as proof; or, when asked, re-read one decision at a larger scale and return linked exp…

  • mandela

    Audit any eval, metric, experiment, or benchmark for leakage: does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked', including an A/B, a holdout, a score, a v…

  • modelchk

    Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which…

  • nba

    Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a project is between phases, the author asks what to do next, too many valid threads are open, or the work needs re-entry into frame, build, drive, re0-memo, hate, re0-work, or ship.

  • prism

    No description from the maker

  • re0

    Refresh an existing artifact into the current best v0. Use when the user asks to clean up, sync up, dedupe, de-noise, smooth, rewrite, or update an artifact after iteration; when nearby artifacts may have drifted; or when changes in one place should be reflected across related artifacts while keepi…

  • re0-git

    Rewrite a finished commit's message into a clean, handoff-ready form in your own log style, place a late commit in time order on a linear history, and take a rejected or duplicate commit out of a range, so `git log` alone tells the story. User-invoked: run it once you've decided to commit.

  • re0-loop

    Run repeated cycles of build, QA, re0-memo and re0-work while preserving learning and letting code die. Use for long agentic projects where progress must be measured by quality-cleared templates, reusable modules, and eliminated anti-patterns rather than hours spent or features accumulated.

  • re0-memo

    Turn a finished, failed, or disappointing work cycle into portable lessons, anti-patterns, quality gates, and next-cycle vocabulary, and measure how far the work stands from its objective. Use after a build, QA pass, demo, user complaint or correction, a request the user had to repeat, a user askin…

  • re0-merge

    Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing.

  • re0-plan

    Open a paperthin iteration's casebook before re0-loop's first turn, seeded with real content the moment the folder exists, never an empty directory. User-invoked, paperthin-only: assumes the full skill package installed. Run when opening a new build cycle in this repo.

  • re0-release

    Walk a pending change in the repository it runs in through that repository's release procedure end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.

  • re0-upgrade

    Keep one paperthin install current and loaded once: move an old skills.sh install onto the Claude Code or Codex plugin, clear the session-start notice older releases wired, set up the daily update job where skills.sh stays, and bring that install to the full current catalog, all shown and confirmed…

  • re0-work

    Restart a project or artifact from v0 while preserving only proven lessons, contracts, gates, vocabulary, real-surface tests, and negative corpus. Use when the foundation is wrong, accumulated code is misleading progress, or a new pass should learn from the old one without inheriting its accidental…

  • readchk

    No description from the maker

  • reorder

    No description from the maker

  • shower

    Cold-read the artifact you're focused on from a fresh, zero-context sub-session to confirm it stands on its own: a shower-thought reset for accumulated session bias. Use when a long session has worn away your fresh eyes and you can no longer tell whether the artifact in focus is clear to someone wi…

  • sip

    After you create or change an artifact or skill, taste-test it with our own skills instead of trusting your in-session judgment. Use right after writing or editing anything, before calling it done, committing, or handing it off.

  • ssotize

    Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or plat…

Skill과 MCP의 차이

MCP = 손

AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.

Skill = 안내서

작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.

겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.

쓸 수 있는 앱

Claude CodeCodexCursorOpenCode

제작자 README와 repo 폴더 기준

설치

Pick a skill first

This repo has 28 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

토론

질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.

아직 글이 없어요. 처음으로 질문하거나 공유해 보세요.

이곳의 글은 사용자가 쓴 것으로, PopNx 팀의 글이 아니에요.

로그인하고 글쓰기

GitHub 정보

GitHub 스타
1,451
Stars are for the whole repo, not each skill
제작자
LilMGenius
라이선스
MIT
최근 코드 수정
2026년 11월 15일
repo 안 SKILL.md(번역본과 템플릿 포함)
28
토픽
agent-skills, ai-agents, anti-slop, claude-code, codex, coding-agents, context-engineering, cursor, design-patterns, evals, fact-check, grok