backprop
Skill1.4k starsChanged todayMITView on GitHub
Feed what a finished cycle taught back through the sources that produced it: measure the lesson, question the requirements it touches, land it in one owner, refresh that owner to a clean v0, cut its padding and realign its listings, each pass only when it applies. Use after a correction, a request the user had to repeat, a failed or disappointing cycle, or a cleanup pass over a repository's docs, rules or skills, when the lesson has to change the sources rather than sit in a memo.
4 other projects use a version of this.
Trending
Less talk lately.thin dataabout the whole repository
Most recently taken up by
- kborovik/spec-driven-devtheir own version, first seen Aug 4, 2026
- kborovik/grok-skillstheir own version, first seen Jul 19, 2026
- bdunn313/repolabtheir own version, first seen Jul 9, 2026
- JuliusBrussee/cavekittheir own version, first seen Apr 20, 2026
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
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- JuliusBrussee/cavekit★ 1.1ksame name
- kborovik/grok-skills★ 2same name
- kborovik/spec-driven-dev★ 2same name
- bdunn313/repolab★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- re0-importSkill
- re0-readmeSkill
- re0-upgradeSkill
- ssotize-localSkill
- ssotizeSkill
- 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-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
12 rules. 0 are common, 9 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Measure: Call the Skill tool with "re0-memo" on the output.
- Distinctive: line 18
Refresh: Call the Skill tool with "re0" on each owner the steps above changed, so it reads as though the lesson had always been there.
- Distinctive: line 19
Tighten: Call the Skill tool with "debloat" on prose or code in scope that is correct and current but padded, AI slop included.
- Distinctive: line 20
Realign: Call the Skill tool with "re0-order" on each listing in scope whose order no longer follows one principle.
- Very specific: line 21
Hand off punctuation: If the changed text has em-dashes or look-alikes, ask the user to run dedash on it.
- Distinctive: line 27
Run a pass only when its condition holds and state every skip.
- Distinctive: line 28
Run each pass once. When a later pass finds duplication or drift it does not handle, report it with its location instead of looping back.
- Very specific: line 29
Use the members; never reimplement their procedures.
- Distinctive: line 31
Stop at the artifact. Never stage, commit or push.
- Distinctive: line 35
Every step reports ran, skipped with a reason, or handed off.
- Very specific: line 36
Every lesson re0-memo produced either landed in its owner or is reported with why it did not.
- Distinctive: line 37
Every edit lies inside the pinned scope, and the passes ran in the stated order.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Carry a lesson from the output back into the sources that produced it, then leave those sources clean.
Goal
A correction says the output was wrong; the fix belongs in what produced it. Backpropagation in a network measures the error at the output and sends it back through every layer that contributed, each adjusting by its share. backprop does the same for a body of work: re0-memo measures the error and names its class, elon questions the requirements that let it through, ssotize puts the lesson in the one source that owns it, and re0, debloat and re0-order leave that source reading as its clean current version. The scope you name bounds every pass, each pass runs only when its condition holds, and the order stays fixed.
Workflow
- Pin the scope. Name the output the lesson came from (the correction, the failed cycle, the review finding) and the sources it implicates: the docs, rules, skills or code that produced it. If neither is named, propose the user's last correction and the files it concerns, and wait for a yes before editing; with no correction to propose, ask for the output and stop. Every later step stays inside this scope.
- Measure. Call the Skill tool with "re0-memo" on the output. Its lessons, each a class with its evidence and the owner it names, are what the remaining steps carry back. When it finds no lesson, report that and stop.
- Question. Call the Skill tool with "elon" on the requirements and rules in scope that the lessons touch. Skip it when the scope holds no requirement or rule. Stop at its approval gate; what the user approves is carried out, and what is declined stays as it was.
- Consolidate. Call the Skill tool with "ssotize" so each lesson lives in the owner
re0-memonamed and every other copy in scope becomes a reference. Skip it when nothing in scope duplicates or contradicts a lesson. Stop at its approval gate; what the user approves is carried out, and what is declined stays as it was. - Refresh. Call the Skill tool with "re0" on each owner the steps above changed, so it reads as though the lesson had always been there. Skip it when no owner changed.
- Tighten. Call the Skill tool with "debloat" on prose or code in scope that is correct and current but padded, AI slop included. Skip it when nothing is bloated.
- Realign. Call the Skill tool with "re0-order" on each listing in scope whose order no longer follows one principle. Skip it when no listing drifted.
- Hand off punctuation. If the changed text has em-dashes or look-alikes, ask the user to run
dedashon it; if it has Korean prose or label rows joined by middle dots,dedot. Name the files to pass. - Report each step as ran, skipped with its reason, or handed off, and name each lesson with the owner it landed in.
Rules
- Keep the order. The lesson comes first because every later pass carries it; requirements are questioned before anything is consolidated, so nothing is moved that should have been deleted;
ssotizeprecedesre0becausere0repairs from the canonical source;re0precedesdebloatbecausedebloattightens prose that is already current;re0-orderfollows both because they may cut or merge the items it moves; punctuation comes last because every rewrite regenerates dashes. - Run a pass only when its condition holds and state every skip. Running every member by default is a misuse.
- Run each pass once. When a later pass finds duplication or drift it does not handle, report it with its location instead of looping back.
- Use the members; never reimplement their procedures. Skip a member that is not installed and say so; without
re0-memothere is no lesson to carry, so stop and say so. dedashanddedotare user-invoked, so this skill names them as handoffs and never runs them.- Stop at the artifact. Never stage, commit or push.
Verification
- Every step reports ran, skipped with a reason, or handed off; none is silent.
- Every lesson
re0-memoproduced either landed in its owner or is reported with why it did not. - Every edit lies inside the pinned scope, and the passes ran in the stated order.
- Each changed owner reads as its clean current version, with no lesson appended to a neighboring sentence.
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.

