outline
Design paper structure: generate a section-by-section outline with purpose, key content, estimated length, and narrative arc. Adapts to paper type and venue conventions. Updates .papermill/state.md.
What this skill does
# Paper Outline Help the researcher design the structure of their paper. A good outline is the skeleton that determines whether the paper's argument flows logically. Produce a section-by-section plan that is specific to this paper, not a generic template. ## Step 1: Read Context Read `.papermill/state.md` (Read tool) for: - **Thesis**: The central claim and novelty (critical -- the outline serves the thesis). - **Prior art**: Key references and gaps (these shape the related work section). - **Format**: `latex`, `markdown`, or `rmarkdown` (affects section conventions). - **Stage**: Current progress. - **Venue**: Target venue (affects length, section naming, and emphasis). If `.papermill/state.md` does not exist, outlining can still proceed — ask the user to describe the thesis and intended contribution type directly. Suggest running `/papermill:init` afterward to persist the outline. Also scan existing paper files (Glob/Read tools). If there is already a partial draft, read it to understand what exists. ## Step 2: Determine the Paper Type Different paper types have different conventional structures. Identify which applies: - **Theoretical/mathematical**: Introduction, Preliminaries, Main Results, Proofs, Discussion, Conclusion - **Empirical/experimental**: Introduction, Related Work, Method, Experiments, Results, Discussion, Conclusion - **Systems/engineering**: Introduction, Background, Design, Implementation, Evaluation, Related Work, Conclusion - **Survey/tutorial**: Introduction, Taxonomy/Framework, Section per topic, Discussion, Open Problems - **Short paper/workshop**: Compressed -- Introduction, Approach, Results, Conclusion Ask the user if you are unsure. The structure should match the contribution type. ## Step 3: Draft the Outline For each section, specify: | Field | Description | |-------|-------------| | **Section title** | The heading as it will appear in the paper | | **Purpose** | What this section accomplishes for the reader (1 sentence) | | **Key content** | Bullet points of what goes here (3-5 items) | | **Estimated length** | Approximate page/paragraph count | | **Dependencies** | What must be established before this section | Example: > ### 3. Preliminaries > **Purpose**: Establish notation and recall the key definitions the reader needs. > **Key content**: > - Series system model (Definition 2.1) > - Masked failure time observation model > - Exponential lifetime assumption and its implications > - Notation table for symbols used throughout > > **Estimated length**: 1.5 pages > **Dependencies**: None (self-contained background) ## Step 4: Check the Narrative Arc After drafting the outline, verify the story: 1. **Does the introduction motivate the problem clearly?** The reader should understand why this matters by the end of the first page. 2. **Does related work position the contribution?** It should make clear what gap this paper fills. 3. **Does the technical content flow logically?** Each section should build on the previous one. 4. **Does the paper deliver on the thesis?** The main results section should directly address the claim. 5. **Does the conclusion do more than summarize?** It should state implications and future work. Raise any structural issues with the user. Common problems: - Related work that reads like a list rather than a narrative - Main results section that is too dense with no intuition - Missing "so what?" in the conclusion - Sections that could be merged or reordered for better flow ## Step 5: Present and Iterate Present the complete outline to the user. Ask: > Does this structure capture the argument you want to make? Would you reorder, merge, or split any sections? Iterate until the user approves. ## Step 6: Update State File Once approved, update `.papermill/state.md` (Edit tool): - Set `stage` to `outlining` (or `drafting` if progressing). - Append the outline to the markdown body under a `## Outline` heading. Append a timestamped note documenting the outline creation. ## Step 7: Suggest Next Steps Based on what the outline reveals, suggest the most relevant next step: - If the outline exposed that the thesis is unclear or too broad → "The outlining process suggests the thesis may need sharpening. Consider running `/papermill:thesis` to refine the claim before drafting." - If the outline includes a related work section with few references → `/papermill:prior-art` - If the outline includes experiment/simulation sections → `/papermill:experiment` or `/papermill:simulation` - If the outline includes proof sections → `/papermill:proof` - Otherwise → "Begin writing with the section you feel most confident about. Many authors start with the method/results, not the introduction."
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.