LilMGeniusLilMGenius/paperthin/skills/coil/paperthin/SKILL.md

paperthin

Skill1.4k starsChanged todayMITView on GitHub

The one command to remember: type /paperthin, then your dream. It hands the request to re0-workflow, which runs the rest.

Jul 26, 2026Paperthin 핵심 기능 도입 작업 지시서 — LowyShin/giip-fde-agent1 reaction
Nov 6, 2026Refactor and Debloat skill — dragoscirjan/ai0 reactions
Oct 20, 2026Pilot four Paperthin-inspired skills in Pi Consultants — tranhoangnguyen03/pi-consultants0 reactions · 1 comment
Oct 3, 2026agent-skills.github.lilmgenius.paperthin: init at 0.17.7 — sudosubin/agents.nix0 reactions
Aug 29, 2026research(ultragoal): explore Paperthin principles for bounded, evidence-driven execution — Yeachan-Heo/gajae-code0 reactions · 1 comment

5 more on GitHub

Aug 26, 2026📝 https://github.com/LilMGenius/paperthin tool-study — adszzz11/study0 reactions
Aug 26, 2026Track Codexy 1.6.0 lightweight skills and mechanical enforcement reduction — eunsoogi/codexy0 reactions · 10 comments
Aug 26, 2026Record clean-room observations from the pinned research source — eunsoogi/codexy0 reactions · 3 comments
Aug 26, 2026feat: add Paperthin-inspired artifact reflexes — BokEumEom/infrastructure-engineering-harness0 reactions · 1 comment
Jun 21, 2026[skills.sh] Redirect LilMGenius/skills listings to LilMGenius/paperthin — vercel-labs/skills0 reactions · 1 comment

In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- re0-importSkill
- re0-readmeSkill
- re0-upgradeSkill
- ssotize-localSkill
- ssotizeSkill
- backpropSkill
- catchupSkill
- nbaSkill
- re0-loopSkill
- re0-memoSkill
- re0-planSkill
- re0-tutorialSkill
- re0-watchSkill
- re0-workflowSkill
- re0-workSkill
- aimSkill
- autobahnSkill
- crossthinkSkill
- debloatSkill
- dedashSkill
- dedotSkill
- deidSkill
- demockSkill
- detoolSkill
- elonSkill
- factchkSkill
- hateSkill
- macrothinkSkill
- mandelaSkill
- modelchkSkill
- re0-decideSkill
- re0-gitSkill
- re0-mergeSkill
- re0-orderSkill
- re0-releaseSkill
- re0Skill
- re0-squashSkill
- re0-styleSkill
- readbackSkill
- scopechkSkill
- showerSkill
- sipSkill
- whychkSkill
- multithinkSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Never shorten, rephrase, translate or complete the request.
line 20
Distinctive:
When the forward call fails, report that failure as it came back and run nothing else.
line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Hand the person's request to re0-workflow, unchanged, and add nothing of its own.

Goal

Someone who has never read this suite's catalog types /paperthin with what they want, and that is enough. This skill is only a name for that door: every behavior (reading the intent, choosing and ordering the skills, showing the order, running it and stopping where a person must act) belongs to re0-workflow. It is user-invoked because it exists for a person to type; the model reaches re0-workflow directly, so a second model-facing entry with the same triggers would only split them.

Workflow

Call the Skill tool with "re0-workflow", passing the person's request word for word as the stated intent, and pass along whatever they attached (files, pasted text) the way the host passes attachments to a skill. If they typed /paperthin with nothing after it, say so in the call ("no request given"); asking for the intent is the router's job.

Rules

Forward only: plan, select, order or run nothing here, and call no other skill. Everything after the hand-off is re0-workflow's.
Never shorten, rephrase, translate or complete the request; the router reads the person's own words.
Whether re0-workflow is installed is read from the installed roster before the call, never tried as a second call; when it is missing, stop and say so, naming it as the skill to install. Never stand in for it with a plan of your own.
When the forward call fails, report that failure as it came back and run nothing else.
re0-workflow never routes back here, so the hand-off cannot loop.

Verification

Before finishing:

Exactly one Skill tool call ran, to re0-workflow, carrying the request as typed; or, when re0-workflow was not installed, none ran and the person was told to install it.
Nothing else ran from this skill; the report the person sees is the router's.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free