slop-detector
$
npx mdskill add lyndonkl/claude/slop-detectorDetects ten AI slop signatures in draft text.
- Identifies generic content patterns in Substacker drafts.
- Depends on hedge-detector for context and voice checks.
- Flags specific phrases and structural weaknesses automatically.
- Returns flagged spans with clean or flagged status.
SKILL.md
.github/skills/slop-detectorView on GitHub ↗
---
name: slop-detector
description: Scans a substacker draft for 10 signatures of AI-generated explainer slop — meta-framing openers ("In this post"), list-heavy argument, nominalization clusters, generic examples lacking first-person texture, prompt-residue phrases ("Let's break this down"), buzzword stuffing, outline-shaped paragraphs, hedge clusters, flattened uncertainty. Use when a draft "feels generic" even after voice-check passes. Trigger keywords: slop, AI-written, generic, template, meta-framing, zombie nouns, prompt residue, outline-shaped.
---
# Slop Detector
## Table of Contents
- [The 10 signatures](#the-10-signatures)
- [Workflow](#workflow)
- [Worked example](#worked-example)
- [Guardrails](#guardrails)
**Related skills:** Called by the Editor voice pass. Consumes hedge-cluster count from `hedge-detector` (S8). Emits the "Slop signatures" subsection.
## The 10 signatures
Fixed list. Each either `clean` or `flagged` with the offending span.
| # | Signature | Detection |
|---|---|---|
| S1 | Meta-framing opener | First paragraph contains `In this post`, `This article`, `We will explore`, `Let's dive into`, `Today we'll look at` |
| S2 | List-carrying-argument | Any bulleted list where the argument collapses if bullets are removed. Test: does the prose still stand without the list? |
| S3 | Zombie nouns (Sword) | >3 nominalizations per 100 words (suffixes: -ation, -ity, -ment, -ence on abstract nouns) |
| S4 | Generic examples | "a company" / "a model" / "a user" with no specific name, scale, dataset |
| S5 | No first-person | Zero `I`, `my`, `we-as-me` in a >800-word reflective essay |
| S6 | Prompt residue | `Let's break this down`, `To summarize`, `In conclusion`, `Key takeaways`, `Let me explain` |
| S7 | Outline-shaped paragraphs | >60% of paragraphs follow same syntactic shape: topic → 3 supporting sentences → transition |
| S8 | Hedge cluster | ≥2 epistemic-weakness hedges within 50 words (from `hedge-detector`) |
| S9 | Buzzword stuffing | ≥3 terms from {game-changer, paradigm shift, under the hood, delve, unpack, dive into} in a single draft |
| S10 | Flattened uncertainty | Any small-N caveat that appears in `corpus/drafts/notes/` but was removed in the submitted draft (requires notes; else skip this signature) |
## Workflow
```
Slop scan draft D:
- [ ] Step 1: For each signature, run detection rule
- [ ] Step 2: Mark each signature as clean | flagged (with quote)
- [ ] Step 3: Tier-1 signatures: S1, S2, S6 (generic framing + prompt residue)
- [ ] Step 4: Tier-2 signatures: S3, S4, S5, S7, S9
- [ ] Step 5: Emit the slop signatures subsection with each labeled clean/flagged
```
### S3 nominalization scoring
Count suffix hits (`-ation`, `-ity`, `-ment`, `-ence`, `-ness`, `-ance`) on abstract nouns per 100 words. >3 = flag. Example: "provides analysis of" → nominalized; "analyzes" → active.
### S4 generic-example rule
Flag an example if it uses only generic pronouns / nouns without a specific anchor:
- "A company might use this" → flag.
- "At Google in 2024, Chen et al. used this" → clean.
### S7 outline-shape rule
Parse paragraphs; count those with the shape:
- Sentence 1: topic statement
- Sentences 2–4: three supporting sentences
- Last sentence: transition
>60% of paragraphs following this shape → the draft reads like an AI-generated outline expanded.
## Worked example
**Draft fragment**:
> In this post, we'll explore why RAG beats fine-tuning.
>
> First, let's define RAG. It's a technique where models retrieve documents before generating. A company might use RAG for their customer service chatbot.
>
> Second, fine-tuning involves training. A team might fine-tune to adapt style.
>
> Third, RAG has benefits. Fine-tuning has drawbacks. It could be argued that hybrid works.
>
> To summarize, both approaches have merit.
**Detections**:
- S1: flagged ("In this post, we'll explore").
- S2: flagged (argument carried by "First / Second / Third" list-in-prose).
- S3: zombie-noun check — "technique", "documents", "benefits", "drawbacks" — borderline. Not flagged yet.
- S4: flagged ("A company might use RAG", "a team might fine-tune") — no specifics.
- S5: clean (has "we").
- S6: flagged ("To summarize").
- S7: flagged (each paragraph: topic + supporting + transition).
- S8: weakness hedges — "It could be argued" — cluster check: just 1, not a cluster (yet).
- S9: buzzword — "explore" is close. Not flagged yet (1 term).
- S10: skipped (no notes dir).
**Output**: 5 signatures flagged (S1, S2, S4, S6, S7). Tier-1: S1, S2, S6 = 3 tier-1 slop violations.
## Guardrails
1. Each signature has a concrete detection rule. No "feels slop."
2. Quote the offending span. Don't just say "S1 triggered" — quote the opener.
3. Signatures are additive, not exclusive. A draft can trip 8 signatures and still be revise-able; Editor's must-not #13 sets the no-go threshold.
4. S10 requires a notes dir; skip quietly if absent.
5. Don't double-count with `hedge-detector`. Hedge clusters flow from hedge-detector into S8 as an input, not a separate scan here.
6. S5 (no first-person) — reflective essays only. How-to / methodology posts may legitimately lack "I."
## Quick reference
- 10 fixed signatures, deterministic detection.
- Tier-1: S1, S2, S6. Tier-2: the rest.
- Consumes `hedge-detector` cluster count as S8 input.
More from lyndonkl/claude
- abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
- academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
- adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
- adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
- alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
- analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
- answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
- attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
- auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
- auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".