presentation-content
Write bold, minimal slide content with punchy headlines, concise body text, and impactful bullet points. Use when writing slides, asking "write content for...", "draft slides about...", or "help me phrase this slide...". Transforms ideas into presentation-ready copy designed for speaking to, not reading from.
What this skill does
# Presentation Content Write slide content that is bold, minimal, and designed for speaking to — not reading from. ## Writing Principles - **Headlines that land** — statements, not descriptions. "AI has no memory" not "Discussion of AI context limitations" - **Minimal text** — if it takes more than 5 seconds to read, cut it - **Emphasis through scale** — big words at light weight, not small words in bold - **Conversation starters** — each slide prompts what you'll say, not what the audience reads ## Headline Patterns ### Statement headlines Bold declarations that take a position: - "Speed is a feature" - "AI has no memory" - "Context is everything" - "Passive beats active" ### Question headlines Create tension and invite reflection: - "What would we do differently if we started today?" - "What does this mean for you?" - "So does any of this actually work?" ### Action headlines Drive toward outcomes: - "Building blocks over modules" - "Always be gardening" - "Let agents write their own rules" ### Framing headlines Set context for what follows: - "How we got here" - "Where we're going" - "The real results" ## Body Text Patterns ### Bold lead-in + explanation ``` **Retention is the real metric** Acquisition gets attention, but retention builds the business. **Speed compounds** Ship fast, learn fast, win fast — momentum is the moat. ``` ### Key phrase emphasis Highlight critical words within sentences: - "Give the **right people**, the **right amount** of information, at the **right time**" - "We don't compete on **features** — we compete on **speed** and **focus**" ### Minimal bullets 3-4 points maximum, each earning its place: ``` - Focus over breadth — Do one thing better than anyone. - Platform, not tool — Customers run their whole operation here. - Speed is the moat — Ship weekly, learn daily, compound forever. ``` ### Inline code Use `backticks` for technical terms, file names, and commands within slides: - "Start with `AGENTS.md` in your project root" - "Run `npx skills add` to install" ## Slide Templates ### Statement slide ```markdown **Section label:** WHAT WORKS **Section color:** green **Headline:** Passive context beats active retrieval **Subtitle:** AGENTS.md is always loaded — skills only trigger when matched ``` ### Big statement slide ```markdown **Section label:** THE PROBLEM **Section color:** red **Headline:** AI has no memory ``` ### Quote slide ```markdown **Quote:** "What got you here, won't get you there" **Attribution:** Marshall Goldsmith ``` ### Data slide ```markdown **Section label:** THE DATA **Section color:** amber **Headline:** 10% MoM Growth, $10M ARR **Subtitle:** Scaling globally with strong traction **Metrics:** - ARR: $10M - MoM Growth: 10% - NPS: 90 ``` ### Code slide ```markdown **Section label:** IMPLEMENTATION **Section color:** blue **Headline:** Install the skills **Subtitle:** One command to add all recommended skills ` ` `bash npx skills add vercel-labs/agent-skills ` ` ` ``` ### Goals slide ```markdown **Section label:** WHY WE'RE HERE **Section color:** teal **Headline:** Goals for today **Points:** - **Get aligned** — One plan, one direction, no ambiguity. - **Make decisions** — Resolve the open questions today, not next week. - **Leave with actions** — Everyone knows what they're doing Monday. ``` ### Recap slide ```markdown **Headline:** Recap **Sections:** - **The problem** — AI has no memory, context rots, output is generic - **The fix** — Invest in AGENTS.md, use skills for domain knowledge - **The practice** — Always be gardening your project context ``` ## Transformation Examples **Before (verbose):** > "The fundamental issue with AI coding assistants is that they don't retain any context between sessions, leading to repetitive and generic outputs" **After (bold):** > **Headline:** AI has no memory > **Subtitle:** Every session starts from zero **Before (explanation):** > "Our product strategy going forward will be based on building reusable components" **After (statement):** > **Headline:** Building blocks over modules > **Supporting:** A platform built on configurable building blocks. Think "Notion for [your domain]." ## Workflow 1. **Identify the one thing** — what must the audience remember from this slide? 2. **Write the headline first** — bold statement or question 3. **Add only what earns its place** — cut anything the speaker will say anyway 4. **Read it at arm's length** — if you can't parse it in 3 seconds, simplify
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.