unslop
Skill1 starsChanged 3 days agoMITView on GitHub
Rewrite prose people will read (PR bodies, READMEs, docs, issue text) to remove AI tells. Use also for "explain simply" or "plain English".
197 other projects use a version of this, 134 of them edited.
Adopted by
Most recently taken up by
- gfunc/skillsedited, first seen Nov 16, 2026
- shiwenbin1617/pstackedited, first seen Nov 16, 2026
- MetrolistGroup/Metrolistedited, first seen Nov 15, 2026
- mostafaalagamy/Metrolistedited, first seen Nov 15, 2026
- backnotprop/pstackedited, first seen Nov 15, 2026
- titouannwtt/claude-toolstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use principle-never-block-on-the-human, greploop-apps and 10 more.
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.
jaydubya818Skillprinciple-never-block-on-the-human
Apply when safe reversible implementation details can proceed inside scope.
Also in 45 projects that use this
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
ianclearySkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 30 projects that use this
bnemaSkillsetup-pstack
Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.
Also in 26 projects that use this
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 15 projects that use this
- +7 more from jaydubya818
Other versions197 projects use a version of this.
Word for word · 0
None found.
Edited · 134
- MetrolistGroup/Metrolist★ 14k21% same
- mostafaalagamy/Metrolist★ 14k21% same
- tester-army/e2e★ 14k19% same
- jaredpalmer/kev★ 9.8k21% same
- backnotprop/pstack★ 4.2k21% same
- michaelshimeles/rstack★ 1.4k19% same
- michaelshimeles/skills★ 1.4k19% same
- VladSez/easy-invoice-pdf★ 1.1k21% same
- moeru-ai/xsai★ 66721% same
- chinmay-sawant/gopdfsuit★ 60718% same
124 more not listed
Wrote their own version · 63
- 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
53 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 repository22 other files it gives its agents.
- analyze-logsSkill
- architectSkill
- build-audit-logsSkill
- cloudflareSkill
- code-reviewSkill
- design-engineeringSkill
- diagnosing-bugsSkill
- full-sendSkill
- full-stopSkill
- ghSkill
- grillingSkill
- impeccableSkill
- improve-animationsSkill
- interrogateSkill
- no-use-effectSkill
- prSkill
- retroSkill
- t3-toolsSkill
- triageSkill
- vitestSkill
- wait-whatSkill
- writing-for-agentsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 3 are common, 10 are distinctive, and 0 are very specific to this project.
3
Common
Most of the 192 edited versions we read keep these.
10
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 8
Remove the patterns that make text read as machine written.
- Distinctive: line 12
Read the text and find the patterns in the list below.
- Distinctive: line 14
Read your version once more and ask what makes it obviously AI written.
- Distinctive: line 18
When asked to explain simply, or in plain English, write for a reader who has to take in each sentence at once:
- Distinctive: line 22
No jargon unless you define it first.
- Distinctive: line 30
Every rule below is one line.
- Distinctive: line 48
13. Em dashes: Do not use them. Split the sentence or use a comma.
- Distinctive: line 50
15. Boldface overuse: Do not bold every name or acronym.
- Common: line 52
17. Title case headings: Use sentence case.
- Common: line 53
18. Decorative emojis: Remove them from headings and bullets.
- Distinctive: line 54
19. Curly quotes: Use straight quotes.
- Common: line 74
28. Dense sentences: If the reader has to reread a sentence, split it or drop a clause.
- Distinctive: line 83
Read these when you need the full list instead of the one line summary.
“Common” is measured: kept by at least 6 in 10 of the 192 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
Unslop
Remove the patterns that make text read as machine written. Keep the meaning and the tone the author wanted.
How to use this skill
- Read the text and find the patterns in the list below.
- Rewrite each one you find. Keep the meaning.
- Read your version once more and ask what makes it obviously AI written. Fix whatever you find.
Explain simply
When asked to explain simply, or in plain English, write for a reader who has to take in each sentence at once:
- Short sentences, one idea each.
- Everyday words.
- No jargon unless you define it first.
Rule 28 covers dense sentences in all writing. This section sets the bar when the user asks for simple.
Pattern list
Rule numbers are stable ids that other skills cite by number. Keep the numbers where they are. If you delete a rule, leave its number as a gap instead of renumbering the rest.
Every rule below is one line. The full word lists and the before and after rewrites live in the reference files.
Content
- 3. Superficial -ing phrases. "highlighting", "ensuring", "reflecting", "showcasing", "fostering". Delete the phrase, or finish the sentence with a fact or a source.
- 5. Vague attributions. "Experts believe", "reports suggest", "some argue". Name the source, or cut the claim.
Language
- 7. AI vocabulary. additionally, crucial, delve, enduring, enhance, foster, garner, interplay, intricate, landscape (when abstract), pivotal, showcase, tapestry (when abstract), testament, underscore, vibrant. Swap table in
references/word-swaps.md. - 8. Fancy ways to say "is". "serves as", "stands as", "boasts", "features". Say "is" or "has".
- 9. "Not just X, but Y." State the point directly in one sentence. Examples in
references/examples.md. - 10. Rule of three. Ideas forced into groups of three. Use the number the author actually had.
- 11. Synonym cycling. protagonist, main character, central figure, hero in one paragraph. Pick one word and repeat it.
- 12. False ranges. "from X to Y" where X and Y are not two points on the same scale. List the topics instead.
Style
- 13. Em dashes. Do not use them. Split the sentence or use a comma. This covers en dashes, hyphens used as dashes, and parentheses used as dashes too.
- 14. Colons as connectors. A colon is fine before a list or a quoted example. A colon that sets up a contrast mid sentence carries nothing, so cut it and let the point stand. Examples in
references/examples.md. - 15. Boldface overuse. Do not bold every name or acronym.
- 16. Inline header lists. A bold label and colon that restates the line, such as "Performance: Performance improved". Turn it into prose. A bold lead-in that ends in a period and adds new detail, such as "Schema in TypeScript. Tables live in one file.", is fine.
- 17. Title case headings. Use sentence case.
- 18. Decorative emojis. Remove them from headings and bullets.
- 19. Curly quotes. Use straight quotes.
Communication artifacts
- 20. Chatbot phrases. "I hope this helps!", "Let me know if...", "Of course!", "Certainly!", "Found the smoking gun!". Delete them.
- 22. Sycophancy. "Great question! You're absolutely right!" Answer the question.
Filler
- 23. Filler phrases. "in order to" becomes "to". "due to the fact that" becomes "because". "it is important to note that" gets deleted.
- 24. Hedging stacks. "could potentially possibly be argued that it might" becomes "may".
- 25. Generic conclusions. "The future looks bright." Name the next step, or give the number.
Jargon
- 26. Abstract metaphor nouns. substrate, wedge, vector, locus, vantage, nexus, primitive, harness, surface, bedrock, scaffolding, modality, paradigm, gold-plating, ratchet, evacuate, endgame, north star, flywheel. Each one hides a plain word. Swap table in
references/word-swaps.md.
Plain speech
- 27. Say what it does, not how it feels. "the database stays close at hand" and "SQL you can read" describe a mood. Write the mechanism or the number instead, such as "
.toSQL()returns the exact string sent to the database", or "renaming a column fails the build". If you cannot restate the line as an instruction, a fact, or a number, cut it. Examples inreferences/examples.md. - 28. Dense sentences. If the reader has to reread a sentence, split it or drop a clause. One idea per sentence.
- 29. Passive voice. Name the actor. "queries are validated" becomes "the compiler validates queries". Keep the passive only when the actor is unknown or does not matter.
- 30. Adverbs. Cut the adverb, or pick a stronger verb. "runs quickly" becomes "is fast", or the number. An adverb holding up a weak verb means the verb is wrong.
- 31. Fancy plain words. utilize, leverage, facilitate, numerous, in the event that. Swap table in
references/word-swaps.md. - 32. Mannered prose. Aphorisms, fragments used for effect, personified code, figurative verbs, stock framing phrases. Say the literal thing. Rule 26 covers the metaphor nouns. Examples in
references/examples.md. - 33. Over-compression. Missing articles, verbless fragments, arrows, abbreviations. Write the whole sentence. Examples in
references/examples.md.
Reference files
Read these when you need the full list instead of the one line summary.
references/word-swaps.mdholds the word lists for rules 7, 26, and 31, with the plain word to use instead.references/examples.mdholds before and after rewrites for the rules that are hard to spot on their own, mostly 9, 13, 14, 16, 27, 29, 32, and 33.
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.

