PiPilot

Create or revise high-quality academic and research presentation slides in Markdown using Marp, following a story-first multi-phase workflow. Use when the user needs conference talk slides, lab or group meeting decks, thesis defense presentations, research seminars, invited talks, mixed-audience or industry research talks, OR wants to create, revise, or edit a talk deck or a specific slide of it (e.g. 'revise slide 7 of my conference talk'). Starts from an audience-facing story spine before slide titles, frameworks, screenshots, or feature lists; then applies Assertion-Evidence and Mayer multimedia principles. For teaching/lecture slides use `teaching-marp-slides`; for written documents use `paper-writing` or `scientific-writing`; for individual figures use `scientific-visualization`.

Create or revise lecture/teaching slides in Markdown using Marp for upper-undergraduate and graduate courses across any academic discipline. Use when the user needs classroom lecture slides, course materials, tutorial slides, or workshop sessions — including a request framed as creating or editing a slides Markdown file (e.g. a '*_slides.md' in a course or week folder) for teaching a class — or wants to revise existing teaching slides. Enforces Cognitive Load Theory, worked-example effect, scaffolding, and retrieval practice principles. Produces both a lecture version and a handout version. For research/conference talks use `academic-marp-slides`; for written documents use `paper-writing` or `scientific-writing`.

Strategically revise an existing CS/AI/Systems conference paper draft for resubmission or submission readiness. Focuses on framing diagnosis, claim crystallization, narrative unification, evidence strengthening, reviewer defense, and venue-aware polish.

Write publication-ready ML/AI/Systems conference papers (NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP). Use when the user requests a conference manuscript, needs conference-specific templates/checklists, or format conversion between venues. For journal articles or technical reports, use scientific-writing instead.

Core skill for high-quality research strategy, topic exploration, idea generation, scope/framing critique, contribution assessment, and mentor-style research direction refinement. Use when the user asks whether an idea is worth pursuing, wants brainstormed research directions, needs to pivot, sharpen a paper/proposal scope, evaluate novelty, identify the strongest objection, or turn a vague area into a concrete, testable research plan. Produces a small number of high-bar candidates with premise audits, nearest alternatives, decisive experiments, and kill criteria.

Prompt guidance for the generate_diagram tool — how to describe different scientific diagram types (flowcharts, pathways, architecture, circuits, networks, conceptual) so the tool produces publication-grade output on the first iteration.

Route long-running research compute across available backends — currently local sandbox and Modal remote, generic enough that AWS/GCP/CloudLab can be added without changing this skill. Use for training, fine-tuning, GPU jobs, large data processing, or scripts that may run for many minutes.

Local sandboxed compute — Docker or host process. Use for quick / iterative work, MLX/Metal on Apple Silicon, anything that fits within local memory + disk. Free, no approval gate, supports stop.

Modal remote GPU compute. Use for CUDA workloads, fine-tuning, large training, or anything the local machine can't fit. Requires explicit user approval per plan (cost > 0).

Diagnostic in-memory compute backend. Use ONLY when the user explicitly asks to verify that the compute pipeline (Registry → IPC → renderer) is wired correctly without invoking real shells or remote services. Off by default — register via ENABLE_COMPUTE_STUB=1.

Rewrite existing draft to sound more natural and less AI-templated while preserving scientific meaning, facts, numbers, citations, and claims. Use when user asks to reduce AI tone, improve flow, or humanize wording without changing conclusions.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use a two-stage process with (1) section outlines supported by literature-search tools and (2) conversion to flowing prose. Covers IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), and journal-ready manuscript drafting.

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.

Systematic coding workflow for implementing, debugging, and refactoring code. Covers test-first development, 300-line generation limits, edit-over-rewrite, error-feedback loops, and incremental verification patterns.

Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.