opener-critique

$npx mdskill add lyndonkl/claude/opener-critique

Diagnoses draft openers to enforce authorial voice contracts.

  • Identifies weak openings that undermine essay impact.
  • Depends on trigger keywords like hook or confession opener.
  • Classifies text into confession, reframe, or generic-opener categories.
  • Flags tier-1 failures to guide structural revisions.

SKILL.md

.github/skills/opener-critiqueView on GitHub ↗
---
name: opener-critique
description: Evaluates the first 1-3 sentences of a substacker draft against the writer's signature opener patterns — confession / "I hadn't done X" / reframe / small concrete admission. Classifies opener as confession | reframe | admission | news-hook | generic-opener and flags news-hook/generic as tier-1. The opener sets the voice contract for the essay. Use on every draft. Trigger keywords: opener, hook, first sentence, opening, confession opener, news hook, generic opener.
---

# Opener Critique

## Table of Contents

- [Classifier](#classifier)
- [Workflow](#workflow)
- [Worked example](#worked-example)
- [Guardrails](#guardrails)

**Related skills:** Called by Editor in structural pass. Sets tone contract; downstream skills (`voice-check`, `slop-detector` S1) can reference its classification.

## Classifier

| Class | Markers | Voice verdict |
|---|---|---|
| **confession** | `I hadn't`, `I used to think`, `I did not know`, `Until last week`, `I spent three hours`, `I was wrong about` | PASS |
| **reframe** | `X is commonly called Y — actually Z`, `Most people think X; actually Y` | PASS |
| **admission** | `I substitute learning for doing`, `I have been meaning to`, `I have opinions about X — the kind that feel like knowledge` | PASS |
| **puzzle** (biology cold open) | Biological/systems question opened with a specific number or contradiction | PASS |
| **epistolary** | `Dear friend`, `Dear reader`, second-person address to a specific imagined reader | PASS (rare but valid) |
| **news-hook** | `GPT-5 launched`, `Last week OpenAI`, `With the release of X`, reacting to an external event | **FLAG tier-1** |
| **generic-opener** | `AI is transforming`, `In a world where`, `In today's fast-paced`, `As we enter a new era` | **FLAG tier-1** |

## Workflow

```
Evaluate opener:
- [ ] Step 1: Extract first 1-3 sentences
- [ ] Step 2: Match against classifier marker lists
- [ ] Step 3: Assign class
- [ ] Step 4: Write one-line justification
- [ ] Step 5: If news-hook or generic-opener, produce 2 rewrite options in the confession/admission register
```

## Worked example

**Draft opener** (bad): "In today's rapidly evolving AI landscape, teams face a critical choice between RAG and fine-tuning for domain knowledge."

**Classification**: generic-opener. Tier-1.

**Rewrites**:
- (a) "I spent four months trying to make a RAG demo not lie. The model was never the problem."
- (b) "I had not shipped a fine-tune until last quarter. I assumed the model was the hard part. It wasn't."

**Draft opener** (good): "I spent a week re-prompting a customer-service agent before I realised the agent was the wrong unit of analysis."

**Classification**: confession (`I spent`, `I realised`). PASS.

**Draft opener** (puzzle — valid): "Your immune system can recognize roughly ten trillion distinct molecular threats. It does this with a genome that contains fewer than twenty thousand protein-coding genes. The math should not work."

**Classification**: puzzle. PASS.

## Guardrails

1. First 3 sentences only. If the writer's opener is 1 sentence, use that alone.
2. Never rewrite the opener beyond 2 suggested options, each ≤2 sentences.
3. News-hook and generic-opener are automatic tier-1. Never soften.
4. If the opener is borderline (e.g., an admission that's ALMOST generic), default to PASS and note as candidate for Editor's drift review.
5. Series-log posts often open with the scoreboard or a direct match reference — that's admission-adjacent, accept.
6. Epistolary register is valid but RARE. Flag if the writer uses it more than 1 in 10 posts.

## Quick reference

- Input: first 3 sentences of draft.
- Output: classification + verdict (PASS / FLAG tier-1) + rewrites if flagged.
- Seven classes: confession, reframe, admission, puzzle, epistolary (all pass); news-hook, generic-opener (flag).

More from lyndonkl/claude

SkillDescription
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".