- Trading skills (OKX, dividend, lottery, quantitative) - Creative skills (ASCII art, diagrams, video) - Development skills (GitHub, debugging, TDD) - Research skills (arXiv, blog monitoring) - Productivity skills (email, documents, notes) - MCP integration skills - Custom user skills
3.8 KiB
name, description, version, author, license, platforms, metadata
| name | description | version | author | license | platforms | metadata | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| stop-slop | Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells. | 1.0.0 | Hardik Pandya (https://hvpandya.com) | MIT |
|
|
Stop Slop
Eliminate predictable AI writing patterns from prose.
Core Rules
-
Cut filler phrases. Remove throat-clearing openers, emphasis crutches, and all adverbs. See references/phrases.md.
-
Break formulaic structures. Avoid binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency. See references/structures.md.
-
Use active voice. Every sentence needs a human subject doing something. No passive constructions. No inanimate objects performing human actions ("the complaint becomes a fix").
-
Be specific. No vague declaratives ("The reasons are structural"). Name the specific thing. No lazy extremes ("every," "always," "never") doing vague work.
-
Put the reader in the room. No narrator-from-a-distance voice. "You" beats "People." Specifics beat abstractions.
-
Vary rhythm. Mix sentence lengths. Two items beat three. End paragraphs differently. No em dashes.
-
Trust readers. State facts directly. Skip softening, justification, hand-holding.
-
Cut quotables. If it sounds like a pull-quote, rewrite it.
Quick Checks
Before delivering prose:
- Any adverbs? Kill them.
- Any passive voice? Find the actor, make them the subject.
- Inanimate thing doing a human verb ("the decision emerges")? Name the person.
- Sentence starts with a Wh- word? Restructure it.
- Any "here's what/this/that" throat-clearing? Cut to the point.
- Any "not X, it's Y" contrasts? State Y directly.
- Three consecutive sentences match length? Break one.
- Paragraph ends with punchy one-liner? Vary it.
- Em-dash anywhere? Remove it.
- Vague declarative ("The implications are significant")? Name the specific implication.
- Narrator-from-a-distance ("Nobody designed this")? Put the reader in the scene.
- Meta-joiners ("The rest of this essay...")? Delete. Let the essay move.
Scoring
Rate 1-10 on each dimension:
| Dimension | Question |
|---|---|
| Directness | Statements or announcements? |
| Rhythm | Varied or metronomic? |
| Trust | Respects reader intelligence? |
| Authenticity | Sounds human? |
| Density | Anything cuttable? |
Below 35/50: revise.
Examples
See references/examples.md for before/after transformations.
Companion skill: humanizer
For a gentler approach, pair with humanizer (skill_view(name='humanizer')):
- stop-slop: aggressive — kills all adverbs, bans em-dashes, 5-dimension scoring
- humanizer: 29 patterns with worked examples, preserves more voice — good when rewrite needs to stay close to original
When user says "去AI味" or asks to humanize text, check both skills. For aggressive cleanup use stop-slop; for nuanced editing use humanizer.
CJK/中文小说 gap: Neither skill covers Chinese-specific AI patterns. Known patterns to watch for in Chinese AI text:
- 四字成语堆砌 (excessive 成语 stacking)
- "然而/不禁/竟然/居然" overuse as plot transitions
- 排比三连 (triple parallelism, same as English rule-of-three)
- "宛如/仿佛/恍若" as default simile connectors
- "目光/眼神" overuse for character reactions
- "心中暗道" as internal monologue crutch
- 过度心理描写 (excessive internal monologue padding)
License
MIT