unslop
Skill1 starsChanged 21 days agoLicence not identifiedView on GitHub
Cut AI tells from any writing.
199 other projects use a version of this, 123 of them edited; 67 of 123 edited versions we compared changed its rules; 17 new projects in the last 4 weeks, against 28 the 4 before.
How people change it
67 of 123 edited versions changed its rules, and some changes recur.
Of the 123 edited versions we compared: 25 keep every rule, 31 are an older text, 67 made changes of their own.
Not in older versions
- A rule we can't quote: its licence doesn't allow itmissing from 31 of 31
- A rule we can't quote: its licence doesn't allow itmissing from 31 of 31
- A rule we can't quote: its licence doesn't allow itmissing from 2 of 31
- A rule we can't quote: its licence doesn't allow itmissing from 1 of 31
- A rule we can't quote: its licence doesn't allow itmissing from 1 of 31
Rules people drop
- A rule we can't quote: its licence doesn't allow itdropped by 62 of 67
- A rule we can't quote: its licence doesn't allow itdropped by 62 of 67
- A rule we can't quote: its licence doesn't allow itdropped by 62 of 67
- A rule we can't quote: its licence doesn't allow itdropped by 8 of 67
- A rule we can't quote: its licence doesn't allow itdropped by 8 of 67
- A rule we can't quote: its licence doesn't allow itdropped by 8 of 67
- A rule we can't quote: its licence doesn't allow itdropped by 7 of 67
Rules people add
- Add soul (see next section).added by 52 of 67
- Shorten or split dense sentences. If the reader has to backtrack, split or drop clauses. One idea per sentence.added by 3 of 67
- When a contract fixes the output format (headings, table columns, JSON keys, verdict tokens, commit prefixes, required language), keep that format exactly and apply these rules to the sentences.added by 2 of 67
- H1. No em-dash (
—) or en-dash (–). Use a full stop, a comma, parentheses, or a colon before a list. A Markdown bullet-is fine.added by 2 of 67 - H2. No counterbalancing. Never « ce n'est pas X, c'est Y », « il ne s'agit pas de X mais de Y », « moins X que Y », « non pas X, plutôt Y », "not just X, but Y". State Y directly.added by 2 of 67
- H3. No inclusive writing in French. No middle dot, no « celles et ceux », no doublets. Generic masculine or a neutral wording.added by 2 of 67
- Boldface overuse. Don't bold every term. Bold at most what the reader must not miss.added by 2 of 67
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Cooling: 17 new projects took it in the last 4 weeks, 0.6× the 4 weeks before.
Most recently taken up by
- RIJUDEVx/agent-skillsedited, first seen Nov 16, 2026
- shiwenbin1617/pstackword for word, first seen Nov 16, 2026
- MetrolistGroup/Metrolistword for word, first seen Nov 15, 2026
- mostafaalagamy/Metrolistword for word, first seen Nov 15, 2026
- backnotprop/pstackword for word, first seen Nov 15, 2026
- titouannwtt/claude-toolstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use greploop-apps.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
jaydubya818Skillgreploop-apps
Run greploop through @greptile-apps when the normal trigger rejects a large PR. Use only with the companion greploop skill.
Also in 5 projects that use this
Other versions199 projects use a version of this.
Word for word · 20
- MetrolistGroup/Metrolist★ 14k100% same
- mostafaalagamy/Metrolist★ 14k100% same
- backnotprop/pstack★ 4.2k100% same
- moeru-ai/xsai★ 667100% same
- dsebban/skills★ 71100% same
- vtno/skills★ 35100% same
- overextended/skills★ 22100% same
- mariusflorescu/pstack-t3★ 13100% same
- adjohn/pstack★ 9100% same
- shiwenbin1617/pstack★ 4100% same
10 more not listed
Edited · 123
- tester-army/e2e★ 14k65% same
- jaredpalmer/kev★ 9.8k85% same
- michaelshimeles/rstack★ 1.4k63% same
- michaelshimeles/skills★ 1.4k63% same
- VladSez/easy-invoice-pdf★ 1.1k84% same
- chinmay-sawant/gopdfsuit★ 60759% same
- open-telemetry/semantic-conventions-genai★ 52865% same
- pnpm/pnpm.io★ 31465% same
- arleypadua/PKHeX.Everywhere★ 30486% same
- jtaroreh/agystack★ 12862% same
113 more not listed
Wrote their own version · 56
- heydamir/unslop★ 17ksame name
- theclaymethod/unslop★ 1.1ksame name
- Silo-Server/silo-server★ 899same name
- nodetool-ai/nodetool★ 637same name
- mshumer/unslop★ 551same name
- mxyhi/ok-skills★ 511same name
- savannahfeder/agentbox★ 419same name
- MohamedAbdallah-14/unslop★ 192same name
- alexj11324/Mikka★ 87same name
- asavvin-pixel/unslop★ 61same name
46 more not listed
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 repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- architectSkill
- arenaSkill
- automate-meSkill
- benchmark-checklistSkill
- blast-radiusSkill
- broSkill
- correctSkill
- create-formal-verification-skillSkill
- create-verification-skillSkill
- domain-modelingSkill
- figure-it-outSkill
- grillingSkill
- grill-with-docsSkill
- handoffSkill
- howSkill
- improve-codebase-architectureSkill
- interrogateSkill
- in-your-own-wordsSkill
- ketchupSkill
- ketchup-videoSkill
- learnSkill
- maintain-formal-verification-skillSkill
- maintain-verification-skillSkill
- make-bot-uiSkill
- no-commentsSkill
- playwright-cliSkill
- playwright-expertSkill
- poteto-helpSkill
- poteto-modeSkill
- principle-attack-the-premiseSkill
- principle-boundary-disciplineSkill
- principle-build-the-leverSkill
- principle-encode-lessons-in-structureSkill
- principle-exhaust-the-design-spaceSkill
- principle-experience-firstSkill
- principle-explain-the-numberSkill
- principle-fix-root-causesSkill
- principle-foundational-thinkingSkill
- principle-guard-the-context-windowSkill
- principle-laziness-protocolSkill
- principle-make-operations-idempotentSkill
- principle-migrate-callers-then-delete-legacy-apisSkill
- principle-minimize-reader-loadSkill
- principle-model-the-domainSkill
- principle-never-block-on-the-humanSkill
- principle-outcome-oriented-executionSkill
- principle-prove-it-worksSkill
- principle-redesign-from-first-principlesSkill
- principle-separate-before-serializing-shared-stateSkill
- principle-sequence-verifiable-unitsSkill
- principle-subtract-before-you-addSkill
- principle-test-behavior-not-implementationSkill
- principle-type-system-disciplineSkill
- prototypeSkill
- recallSkill
- reflectSkill
- researchSkill
- setup-pstackSkill
- setup-workspaceSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 4 are common, 3 are distinctive, and 0 are very specific to this project.
4
Common
Most of the 174 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 174 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.
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.

