Research

Compiles research and analysis results into a structured report. Use when asked to "summarize," "create a report," or "document findings" after investigation.

Validate a plan or pipeline with evidence-based checks, dry runs, and research. Use when the user asks to validate, verify, or QA a plan or process or asks for confidence.

Professional CV and resume builder transforming career narratives into ATS-optimized, multi-format resumes. Integrates with career-biographer for data and competitive-cartographer for positioning. Generates PDF, DOCX, LaTeX, JSON Resume, HTML, and Markdown. Activate on 'resume', 'CV', 'ATS optimization', 'job application'. NOT for cover letters, portfolio websites (use web-design-expert), LinkedIn optimization, or interview preparation.

Write and format Rust documentation correctly. Apply proactively when writing code with rustdoc comments (//! or ///). Covers structure (inverted pyramid), intra-doc links (crate:: paths, reference-style), constant conventions (binary/byte literal/decimal), and formatting (cargo rustdoc-fmt). Also use retroactively via /fix-intradoc-links, /fix-comments, or /fix-md-tables commands.

Develops intuition for what makes research "good" versus "incremental." Use when asked about research taste, how to identify good research, what makes a paper impactful, how to develop research intuition, or how to pick important problems. Analyzes patterns in highly-cited work and what top researchers do differently.

Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis

Automatically score growth experiments using the ICE framework (Impact × Confidence × Ease). Use when the user creates a new experiment, mentions scoring or prioritization, or when analyzing experiment backlogs. Helps prioritize experiments by evaluating Impact (1-10), Confidence (1-10), and Ease (1-10).

Log problems, bugs, and debugging processes with solutions. Use when encountering issues during development, debugging problems, or documenting solutions for future reference. Maintains DEBUG_LOG.md with structured problem-solution entries.

Read, write, and manage Google Docs. Load when user mentions 'google docs', 'google document', 'create doc', 'read doc', 'write doc', 'edit document', or references creating/editing text documents in Google Drive.

Ask the user to pick a response style and persist the preference.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

Reference for Azure DevOps work item fields, link types, and states. Use when the user needs to know field names, field paths, reference names, link types, or work item type configurations. Use when user mentions "field name", "field path", "what field", "link type", "relation type", "parent child", "work item type", or needs to set/update specific work item properties.

Automated alert system for key events in drug discovery. Use for trackingcompetitor milestones, clinical trial updates, regulatory decisions, andpublications of interest.Keywords: alerts, monitoring, tracking, notifications, competitive intelligence

Machine learning integration patterns for rRNA-Phylo covering three use cases - rRNA sequence classification (supervised learning with sklearn/PyTorch), multi-tree consensus (ensemble methods), and generative tree synthesis (GNNs/transformers). Includes feature engineering, model training, hyperparameter tuning, model serving, versioning, and evaluation metrics for bioinformatics ML workflows.

Expert guidance for researching, documenting, and integrating Model Context Protocol (MCP) servers and tools. Covers MCP architecture, server/client implementation patterns, tool discovery, integration workflows, security best practices, and multi-language SDK usage (Python, TypeScript, C#, Java, Rust). Enables seamless integration of MCP tools into Claude Code and AI applications.

UI/UX design guidelines focusing on what AI commonly overlooks or fails to verify. **CRITICAL**: Emphasizes concrete checklists, measurement criteria, and verification steps that AI tends to skip during design reviews. Reference during Phase 1 (UI/UX Design Review).

Takes the dual of a linear program (LP). Use when the user provides an LP in LaTeX or markdown and wants its dual, or asks about LP duality transformations.

Growth engine for ID8Labs. Systematic experimentation and optimization to scale products through data-driven decisions, retention focus, and sustainable acquisition channels.

Find qualified leads with decision makers and outreach strategies

Oxford Nanopore basecalling with Dorado on University of Michigan HPC clusters (ARMIS2 and Great Lakes). Use when running dorado basecalling, generating SLURM jobs for basecalling, benchmarking models, optimizing GPU resources, or processing POD5 data. Captures model paths, GPU allocations, and job metadata. Integrates with ont-experiments for provenance tracking. Supports fast/hac/sup models, methylation calling, and automatic resource calculation.