Stats
Actions
Tags
From superpowers-plus
Rewrites human-readable prose (messages, email, social posts, docs, commits) to remove generic AI patterns. Supports interactive review or automatic GVR loop with validation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers-plus:eliminating-ai-slopThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Guidelines:** See [CLAUDE.md](../../CLAUDE.md) for writing standards.
Guidelines: See CLAUDE.md for writing standards. Last Updated: 2026-06-16 See also: reference.md (patterns), examples.md (usage)
Wrong skill? Analyzing/scoring text (read-only) →
detecting-ai-slop. Profanity/inappropriate language →professional-language-audit.
Fires for: All human-readable prose — messaging, email, social/professional, documentation, business writing. Does NOT fire for: AI-to-AI content (prompts, system instructions, agent config, tool parameters, few-shot examples).
[GVR: 2 iterations | removed 8 patterns | σ: 7.2→16.4]| Metric | Pass | Action if Failed |
|---|---|---|
| Lexical patterns | 0 | Rewrite flagged phrases |
| Sentence length σ | ≥15.0 | Vary sentence lengths |
| TTR | 0.50-0.70 | Diversify vocabulary |
Location: {workspace_root}/.slop-dictionary.json — this skill writes, detecting-ai-slop reads.
Commands: "Add [phrase] to slop dictionary" | "Never flag [phrase]" | "Show my top slop patterns"
| Slop Pattern | Better Alternative |
|---|---|
| "It's worth noting that..." | (delete — just state it) |
| "In order to..." | "To..." |
| "Leveraging/utilizing" | "Using" |
| "A comprehensive solution" | (describe what it actually does) |
| "Incredibly powerful" | (specific metric or capability) |
| "Seamless integration" | "Connects to X via Y" |
| "It's important to understand" | (delete — just explain) |
| "The frame" / "the lens" / "the narrative" | Name the specific concept |
| "Pivotal" / "crucial" / "essential" | State why, or delete |
| "Impactful" / "meaningful" / "compelling" | Quantify or drop |
| "Harness" / "elevate" / "enhance" | Use the plain verb ("use", "improve") |
| "It's not about X. It's about Y." | Make the direct claim instead |
| "In today's ever-evolving world" | (delete — ground in the specific situation) |
| "In conclusion" / "In summary" | (delete — if it's not adding, cut the whole paragraph) |
| "Game-changer" / "revolutionary" / "unprecedented" | Describe the specific difference |
| "Data-driven" / "customer-centric" | Show the data or customer evidence |
| "End-to-end" / "holistic" / "seamless experience" | Name the actual scope or flow |
See reference.md for the full pattern catalog.
These slogan-like forms signal AI generation even with clean vocabulary.
| Slop Form | Rewrite Approach |
|---|---|
| "It's not about X. It's about Y." | Drop the contrast — state Y directly |
| "No X. No Y. Just Z." | State Z with evidence |
| "X is not just A; it's B." | Lead with B and prove it |
| "The more you X, the more you Y." | Replace with a specific example |
| One-sentence paragraphs for emphasis | Fold into adjacent prose or support with evidence |
| Random bolded mid-sentence phrases | Bold only genuine call-outs; remove decorative bolding |
Before publishing: meaning preserved? specificity added? voice consistent? no new slop introduced? GVR thresholds met?
detecting-ai-slop (analysis, read-only) | professional-language-audit (profanity detection)
| Failure | Fix |
|---|---|
| Over-correction strips personality from writing | Preserve author voice — only target known slop patterns |
| False positive on legitimate hedging language | Context matters — "it's worth noting" in a risk section is fine |
| Slop patterns evolve faster than the deny list | Update pattern list quarterly from real examples |
# Example: invoke slop detection
node ~/.codex/superpowers-augment/superpowers-augment.js use-skill eliminating-ai-slop
npx claudepluginhub bordenet/superpowers-plus --plugin superpowers-plusGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.