re0-order
Skill1.4k starsChanged todayMITView on GitHub
Move items only, reword nothing; realign a listing whose order has gone arbitrary (a list, table, catalog, sections, an enum) into a logical sequence under one stated principle. Nothing is added or removed. Use when the user names a listing, or a scope holding one, whose order no longer helps a reader follow the set, or when a pipeline the user invoked passes that scope on. Acts only inside that scope.
Trending
Less talk lately.thin dataabout the whole repository
Who's talking about LilMGenius/paperthin
- LowyShin/giip-fde-agent“Paperthin 핵심 기능 도입 작업 지시서”GitHub · Jul 26, 2026 · 1 reactions
- dragoscirjan/ai“Refactor and Debloat skill”GitHub · Nov 6, 2026
- tranhoangnguyen03/pi-consultants“Pilot four Paperthin-inspired skills in Pi Consultants”GitHub · Oct 20, 2026
- sudosubin/agents.nix“agent-skills.github.lilmgenius.paperthin: init at 0.17.7”GitHub · Oct 3, 2026
- Yeachan-Heo/gajae-code“research(ultragoal): explore Paperthin principles for bounded, evidence-driven execution”GitHub · Aug 29, 2026
The biggest 5 of 10 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 10
Talked about on GitHub (10 times).
On GitHub · 10
- 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
- paperthinSkill
- 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-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
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Put kin next to each other, then sequence those clusters by that one principle.
- Distinctive: line 24
Use one principle a reader can name.
- Very specific: line 38
Every mirrored copy carries the identical order.
≈ “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.
Files
Move the items of a named listing into one order a reader can name, changing nothing but their positions.
Goal
A listing carries meaning when related items sit together along one clear axis; items appended where they happened to be written blur that. re0-order realigns the set under one principle a reader can name, moving items and changing nothing else. It acts on a list, table, catalog, set of sections, or enum the human named, or one inside a scope they named or a pipeline they invoked passes on. The result lands in place: in the listing itself and in every copy that mirrors it.
Workflow
- Pin the listing and its items: the ordered set in focus, inside the scope the human gave.
- Name the one principle that makes the order most meaningful, from workflow or lifecycle sequence, dependency, grouping by kind, severity, frequency, alphabetical. If a latent order already exists, surface it and complete it instead of imposing a new one. When it is unclear whether the current order is deliberate, surface that call to the human and let them decide; move nothing until they do.
- Put kin next to each other, then sequence those clusters by that one principle.
- When the principle is a measured count (how often each item is used, how often it is searched), read each count from the record the listing serves and use it as a starting order, never as the sort key itself. Lead with the item the others are reached through, keep kin together even when their counts differ, let the reading or working order a newcomer follows decide the rest, and let the count settle only what that order leaves open. Name each place the result departs from the count and why.
- Move items into the new order in place. Reword nothing; add nothing; remove nothing.
- Apply the identical order everywhere the set is mirrored, translated copies and second surfaces included. To find the mirrors, search the repository for two or three of the set's items, by identifier where items have one and otherwise by a distinctive phrase, and for files that call themselves copies of this one, such as translations. Every hit holding the same set is a mirror and part of the listing the human named.
Rules
- Reorder only: never reword, add, remove, split, or merge an item. Those are other reflexes.
- Use one principle a reader can name; never blend incompatible sorts in one listing.
- Before sorting by that principle, place every item that another item depends on before it, and keep every precedence the human stated; a dependency constrains the sort and is never a second principle. An item that produces knowledge (research, a survey, a measurement) is depended on by every plan or build it would inform even when none of them names it, so it goes before them; its breadth or open end never sends it to the back, since what it finds late is work redone.
- Respect a deliberate order: when the current sequence already encodes a real principle, complete and tidy it rather than replacing it, and surface the call when unclear.
- Act only inside the scope a human named or that a pipeline they invoked passes on. Never choose a listing yourself; its order is the human's call, and a reorder reflex choosing its own target churns what nobody asked to move.
- Mirrored copies of one set get the same order.
- Edit safely: assert each item exists before moving it and report a MISS rather than dropping it silently; edit unicode-safe; script a large structural move instead of sweeping by hand.
Verification
Before finishing, confirm:
- A reader can name the ordering principle from the result alone.
- Every original item remains; only positions changed; nothing was reworded, added, or removed. Save the listing before the move and run
node scripts/same-set.mjs <before-file> <after-file> [--json]: each non-blank line is an item, exit 0 means the same multiset, exit 1 names the added, removed or changed items, exit 2 is a usage error. - Kin are adjacent and the sequence follows the one principle end to end.
- Every mirrored copy carries the identical order. Run the same script with
--mirror <file>once per copy: it compares the items the copy shares with the after file and, on exit 1, names the first divergence.
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
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.

