readback
Skill1.4k starsChanged todayMITView on GitHub
Verify the model's understanding of a user's instruction before spending non-trivial work. Use when a request is long, bundled, high-stakes, hard to undo, or has ambiguous scope or referents such as this, that, it, the other one, whatever is cleaner, or whichever order makes sense. Restate internally, cross-check against available context, proceed silently when resolved, and surface only a genuine surviving fork.
7 other projects use a version of this.
Trending
Less talk lately.thin dataabout the whole repository
Most recently taken up by
- persiyanov/skillstheir own version, first seen Nov 15, 2026
- iurysza/agent-skillstheir own version, first seen Nov 1, 2026
- menot-you/n-soultheir own version, first seen Nov 1, 2026
- agentydragon/ducktapetheir own version, first seen Oct 9, 2026
- olcayseygan/crumoratheir own version, first seen Oct 2, 2026
- wilbeibi/wilbeibi-skillstheir own version, first seen Sep 7, 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 versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- backnotprop/bro★ 176same name
- agentydragon/ducktape★ 11same name
- iurysza/agent-skills★ 5same name
- wilbeibi/wilbeibi-skills★ 2same name
- persiyanov/skills★ 1same name
- menot-you/n-soul★ 0same name
- olcayseygan/crumora★ 0same 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
- 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-orderSkill
- re0-releaseSkill
- re0Skill
- re0-squashSkill
- re0-styleSkill
- scopechkSkill
- showerSkill
- sipSkill
- whychkSkill
- multithinkSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
7
Distinctive
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: line 16
Check that restatement against the available context (the message, session history, project memory, files on disk, and conventions the Goal …
- Distinctive: line 17
If the context settles it, proceed without saying anything.
- Distinctive: line 18
If a fork survives, ask one specific clarifying question that is tied to your restated understanding and names the choice, never a vague …
- Distinctive: line 26
Never silently resolve a fork that changes the shape of the work.
- Distinctive: line 27
Keep the durable read log for plans, multi-file changes, irreversible actions, or work a fresh reviewer may need to audit, not for every …
- Distinctive: line 35
Every surfaced fork is truly unresolved by the available context.
- Distinctive: line 36
No substantial work starts without either a silent pass or a resolved fork.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Restate an instruction in your own words and check it against context before work starts on it.
Goal
Catch a misread instruction before work starts on the wrong target. The requester's intended meaning is checked against the current message, the session history, project memory, files on disk, and established conventions. When that context settles the read, the work proceeds with no question; when two readings survive, the requester gets one specific question about the choice.
Workflow
- Recognize the signal: a long or multi-part instruction, ambiguous scope or referents, deliberately flexible wording, or stakes high enough that a wrong guess costs real work, including work that is hard to undo.
- Restate the instruction to yourself in your own words. Copying the user's words does not count as understanding.
- Check that restatement against the available context (the message, session history, project memory, files on disk, and conventions the Goal names) for contradictions, missing antecedents, or two plausible readings the context cannot settle.
- If the context settles it, proceed without saying anything. Do not ask the requester to confirm what the context already answered.
- If a fork survives, ask one specific clarifying question that is tied to your restated understanding and names the choice, never a vague "does this look right?". The requester decides: wait for the answer before the shape-changing work proceeds.
- Before substantial work, record one durable line beginning
understood as:with the confirmed read, so a later reader can check the work against it. Keep it in the plan or task file the work already has; with none, put it in the commit message or pull request body that delivers the work.
Rules
- A paraphrase shows a model of the request was built; a verbatim repeat shows little.
- Asking about a request that context resolves, or that is unambiguous, is a defect; proceed silently.
- Surface one fork at a time, highest stakes first, never a checklist of ambiguities.
- Never silently resolve a fork that changes the shape of the work.
- Keep the durable read log for plans, multi-file changes, irreversible actions, or work a fresh reviewer may need to audit, not for every turn. A silent pass still writes the line when one of these cases holds.
- Boundary with a sibling: readback verifies intent;
factchkverifies whether a claim about the world is true. That sibling is named as a boundary, not called. This skill calls no skill.
Verification
Before proceeding, confirm:
- The restatement is a paraphrase.
- Every surfaced fork is truly unresolved by the available context.
- No substantial work starts without either a silent pass or a resolved fork.
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.

