michael-lewis-style
Rewrite nonfiction prose in the style of Michael Lewis. Strips formula, scaffolding, and manufactured drama. Replaces them with earned narrative, invisible transitions, and evidence that draws its own conclusions.
What this skill does
# Michael Lewis Style Skill ## The Model Michael Lewis (*Moneyball*, *The Big Short*, *Liar's Poker*) is the gold standard for making technical, counterintuitive arguments readable without dumbing them down. His prose feels inevitable — like each sentence couldn't have been written any other way. That feeling comes from one thing: he builds to conclusions rather than announcing them. Everything else in this skill is a corollary of that. --- ## What He Does **He earns the drama.** Lewis never tells you to be impressed. He builds context until the implication becomes unavoidable, then moves on. Cut any sentence that announces how significant the next sentence is. **He trusts readers.** After a statistic or quote, he doesn't explain what it means. He presents evidence and lets the conclusion sit there, obvious. If your next sentence explains the previous one, cut it. **His transitions are invisible.** He ends sections at the moment a question naturally arises and opens the next section answering it. No "Now let's turn to..." — just the seam disappearing. **He integrates quotes.** Block quotes are reserved for moments where the exact wording is the point — a coinage, a paradox, a turn of phrase nobody else could have made. Everything else is paraphrase. Aim for no more than 2-3 block quotes per 1,000 words. **He uses specific people and moments.** Abstract ideas are anchored in specific humans making specific decisions. Not "investors noticed" but who noticed, when, and what they did about it. **His sentence length varies meaningfully.** Long sentences for complex connected ideas; short sentences for conclusions and reversals. The variation is driven by content, not a desire to sound dynamic. --- ## What to Cut **Scaffolding sentences** — sentences that announce what the next sentence will say: - "Before you can understand X, you need to know Y." - "This is where most people get it wrong." - "Here's the part that matters." - "X draws a distinction that changes everything." If removing a sentence loses no meaning, it's scaffolding. Cut it. **Post-quote explanation** — summarizing a quote you just quoted. If the quote needs that much unpacking, replace it with a paraphrase that carries the explanation inside it. **Manufactured urgency** — "And here's the part that should keep you up at night." Let the fact be alarming. Announcing that it's alarming kills the effect. **Fragment punches used as a rhetorical habit** — one or two per piece can work. When every paragraph has one, the prose goes staccato and readers stop feeling them. **Lists as a substitute for argument** — bullet points catalog; prose shows how things relate. If a list could be a paragraph that makes the reader feel something, make it a paragraph. --- ## The Rewrite Process 1. Read the whole section before touching a word. Find the one thing it's trying to establish. 2. Find where the argument actually begins — usually not the first sentence. 3. Cut every scaffolding sentence. 4. For each block quote: does the exact wording matter, or just the information? If just the information, paraphrase and cut the block. 5. After each remaining quote, cut any sentence that explains it. 6. Rewrite transitions: end sections at the moment of implication, open new sections already inside the next idea. 7. Read aloud. If it sounds like the same beat throughout, vary sentence structure. If it sounds choppy, connect ideas into longer sentences that show their relationships. --- ## The One Test After rewriting a passage, ask: does the reader arrive at the conclusion slightly ahead of where you lead them, feeling like they figured it out? That's the Lewis effect. If you're still announcing conclusions, keep cutting.
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.