Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hhellbusch-unslop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/unslop
Tools it pre-approves 3
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
ReadGrepGlob
What's inside
- Skill name
unslop- Description
- Cut AI tells from writing. Use when the user says /unslop, "unslop this", or asks to strip AI patterns from a draft, doc, or essay.
- License
- MIT
- Allowed tools
- Read, Grep, Glob
- Instructions
- 110 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Unslop — Cut AI Tells (Invoked) <objective> Edit text to remove AI patterns. Preserve meaning. Match the intended tone (this kit: practitioner, shorter over longer). Derived from [cursor/plugins pstack unslop](https://github.com/cursor/plugins/blob/main/pstack/skills/unslop/SKILL.md). Rule numbers stay stable so other skills can cite them. A removed rule leaves a gap. **Not always-on.** Ambient brevity already lives in working style. This skill is a deliberate pass on a named draft. </objective> <process> ### Step 1: Identify the target Parse `$ARGUMENTS`: - **File path** → read the file - **Inline / no path** → the most recent draft in conversation If ambiguous, ask: "Which file or draft should I unslop?" Do not rewrite YAML frontmatter `review:` blocks except to keep them valid. ### Step 2: Scan, rewrite, self-audit 1. Scan for the patterns below. 2. Rewrite. Preserve meaning. Match intended tone. 3. Self-audit: "What still makes this obviously AI generated?" Fix remaining tells. 4. If the consumer has a style guide (em dashes in titles, project jargon), keep those. Do not "unslop" a required convention. ### Step 3: Report then apply If the user asked for a review only, list hits by rule id and stop. If they asked to unslop the file, apply the rewrite. </process> <patterns> Rule numbers are stable ids. ### Content 3. **Superficial -ing phrases.** "highlighting...", "ensuring...", "reflecting...", "showcasing...", "fostering...". Delete or expand with real sources. 5. **Vague attributions.** "Experts believe", "Industry reports suggest", "Some critics argue". Name the source or delete. ### Language 7. **AI vocabulary.** Additionally, crucial, delve, enduring, enhance, fostering, garner, interplay, intricate, landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore, vibrant. Replace with plain words. 8. **Fancy ways to say "is".** "serves as", "stands as", "boasts", "features". Just say "is" or "has". 9. **"Not just X, but Y."** State the point directly instead. 10. **Rule of three.** Forcing ideas into groups of three. Use the natural number. 11. **Synonym cycling.** Protagonist, main character, central figure, hero all in one paragraph. Pick one, repeat it. 12. **False ranges.** "from X to Y" where X and Y are not on a meaningful scale. List topics directly. ### Style 13. **Em dash overuse.** Do not use em dashes as clause glue in body prose. Period or comma. Consumer style guides may still use an em dash in a title (`# Topic — subtitle`); keep that. 14. **Colon overuse.** Colons are fine before a list or example. Not as mid-sentence connectors. 15. **Boldface overuse.** Do not bold every proper noun or acronym. 16. **Inline-header lists.** The tell is a bold label and colon that restates the line. Convert those to prose. A bold lead-in that ends in a period and is followed by new detail is fine. 17. **Title case headings.** Sentence case unless the consumer style guide requires title case for `#` headings. 18. **Decorative emojis.** Remove from headings and bullets. 19. **Curly quotes.** Replace with straight quotes. ### Communication artifacts 20. **Chatbot phrases.** "I hope this helps!", "Let me know if...", "Of course!", "Certainly!", "Found the smoking gun!" Remove. 22. **Sycophantic tone.** "Great question! You're absolutely right!" Respond directly. ### 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. **Excessive hedging.** "could potentially possibly be argued that it might" becomes "may". 25. **Generic conclusions.** "The future looks bright." State specific plans or facts. ### Jargon 26. **Abstract metaphor nouns.** Substrate, wedge, vector, locus, vantage, nexus, primitive (as noun), harness (as metaphor), surface (as in "API surface"), bedrock, scaffolding (as metaphor), modality, paradigm, gold-plating, ratchet (as metaphor), evacuate (for moving code), endgame, north star, flywheel. Pick the concrete word. **Do not replace** when the word is the actual name of a thing in the project (this kit's "harness", Ambler's "sandbox", a product called Scaffold). ### Plain speech 27. **Say what it does, not how it feels.** If you cannot restate a sentence as a concrete instruction, fact, or number, cut it. If the sentence could appear unchanged in another project's docs, it says nothing about this one. Cut it. 28. **Shorten or split dense sentences.** One idea per sentence. 29. **Active voice.** Prefer it. Passive is fine when the actor is unknown or does not matter. 30. **Cut adverbs, or use a stronger verb.** "significantly improves" becomes the measured delta. 31. **Prefer the plain word.** "utilize" / "leverage" become "use". "facilitate" becomes "help". 32. **Mannered prose.** Aphorisms, rhetorical fragments, personified code, figurative verbs, stock framing. Say what you mean. 33. **Over-compression.** Dropped articles, verbless fragments, symbol-speak. Write whole sentences. </patterns> <failure_modes> - **Fighting the style guide.** Stripping required title em dashes or project terms. - **Always-on.** Running this on every reply. It is a pass on a draft. - **Meaning change.** Cutting a hedge that was an honest limit. </failure_modes> <success_criteria> - Hits cited by rule id when reporting - Meaning preserved - Self-audit named at least one remaining tell, or stated none remain - Style-guide exceptions honored </success_criteria>
From hhellbusch/zanshin-pi-extension, MIT.
More from hhellbusch/zanshin-pi-extension
- 0.565score
kihon
hhellbusch
Basics / fixed forms (基本): shell, secrets, vault, sql, git, k8s, testing, lint, ansible, helm, kustomize, python, typescript, structured edit.
SkillAFreshness: AClaude Code +9 - 0.565score
yomi
hhellbusch
Second-order lens (読み — reading ahead): and then what?
SkillAFreshness: AClaude Code +9 - 0.565score
craft
hhellbusch
Apply engineering principles to code or design — DRY, KISS, SRP, YAGNI, convention over configuration, orchestration vs program, shared change scope, phased…
SkillAFreshness: AClaude Code +9 - 0.565score
kaeshi
hhellbusch
Inversion lens (返し — reversal): what would guarantee failure?
SkillAFreshness: AClaude Code +9 - 0.565score
shoshin
hhellbusch
Surfaces load-bearing assumptions against source artifacts before building.
SkillAFreshness: AClaude Code +9 - 0.565score
domain-language
hhellbusch
Audit established domain terms across glossaries, ADRs, code, schemas, APIs, tests, UI, and external contracts.
SkillAFreshness: AClaude Code +9 - 0.559score
lab-journal
hhellbusch
Append one lab-journal entry after a meaningful surprise, or skip.
SkillAFreshness: AClaude Code +9 - 0.558score
spar
hhellbusch
Adversarial review of any content — essays, designs, plans, or ideas
SkillAFreshness: AClaude Code - 0.558score
whats-next
hhellbusch
Analyze the current conversation and create a handoff document for continuing this work in a fresh context
SkillAFreshness: AClaude Code - 0.558score
checkpoint
hhellbusch
Save current session state mid-session — faster than /whats-next, designed for crash recovery
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 9, 2026 (1 month ago)
- Last release
- Oct 5, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hhellbusch
- 0.565score
kihon
hhellbusch
Basics / fixed forms (基本): shell, secrets, vault, sql, git, k8s, testing, lint, ansible, helm, kustomize, python, typescript, structured edit.
SkillAFreshness: AClaude Code +9 - 0.565score
yomi
hhellbusch
Second-order lens (読み — reading ahead): and then what?
SkillAFreshness: AClaude Code +9 - 0.565score
craft
hhellbusch
Apply engineering principles to code or design — DRY, KISS, SRP, YAGNI, convention over configuration, orchestration vs program, shared change scope, phased…
SkillAFreshness: AClaude Code +9 - 0.565score
kaeshi
hhellbusch
Inversion lens (返し — reversal): what would guarantee failure?
SkillAFreshness: AClaude Code +9 - 0.565score
shoshin
hhellbusch
Surfaces load-bearing assumptions against source artifacts before building.
SkillAFreshness: AClaude Code +9 - 0.565score
domain-language
hhellbusch
Audit established domain terms across glossaries, ADRs, code, schemas, APIs, tests, UI, and external contracts.
SkillAFreshness: AClaude Code +9
Cite this page
unslop skill. Agent Mart. https://agentmart.dev/skills/hhellbusch-unslop (last updated 2026-10-24)