Research

Conduct a quarterly review of your overall research mission and direction. This is a user-level review stored in ~/.researchAssistant/. Use when the user types /quarterly_review, every 3 months, after major project milestones, or when questioning research direction.

Shared resource library for Beam AI integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by beam-connect and individual Beam skills.

Project type definitions with type-specific questions, patterns, and stacks.Use when: determining project architecture, asking type-specific questions.Referenced by: idea-validation, brainstorming, /ship command.

This skill should be used when users need to translate technical documents, API documentation, academic papers, or any technical content while preserving technical accuracy and terminology. It specializes in maintaining technical rigor while ensuring readability in the target language.

Systematic fact-checking, source verification, and quality assurance for competitive research deliverables. This skill ONLY activates when explicitly requested - it does not auto-trigger. Use this skill when you explicitly ask to review competitive research, fact-check claims, verify sources, validate consistency, or assess quality of completed analysis documents. Example requests that activate this skill "review this competitive analysis", "fact-check these findings", "verify the sources", "quality check this report", "are these claims accurate", or "validate this analysis".

Storybook CSF3 story authoring methodology for UI component catalogs.Prioritizes visual showcase patterns over exhaustive argTypes enumeration.Reference for creating scannable, maintainable component documentation.

Add Better Auth signup/signin, personalize chapter content, and persist user preferences. Use when implementing authentication, user sessions, or personalized content delivery.

Generate comprehensive Commercial & Industrial (C&I) loan credit memos for banking demos. Interviews bankers, gathers data from Morningstar/S&P/Aiera/LSEG, handles file uploads, tracks citations, and produces standardized credit approval documents. Use when a banker needs to create a credit memo for a C&I loan application.

Assists authors in researching topics, verifying facts, and ensuring accuracy in their writing. Particularly useful for historical fiction, non-fiction, science fiction, and any genre requiring real-world accuracy. Use when the user needs help with research or fact-checking.

Orchestrate the complete LA-Bench experimental procedure generation workflow from JSONL input to validated output. This skill should be used when processing LA-Bench format experimental data to generate and validate detailed experimental procedures. It coordinates parsing, reference fetching, procedure generation, and quality validation with 10-point scoring.

Self-reference guide for Claude Code's own architecture, configuration, and extension points. Use when needing to know where Claude Code stores its configuration files, skills, plugins, hooks, MCP servers, settings, or any other internal structure. Triggers on questions like "where do skills go?", "how do I configure hooks?", "where is the settings file?", or when creating/modifying Claude Code extensions.

Execute project release workflows by locating and following project-specific RELEASE_GUIDE.md in the repository root or docs/. Use when asked to perform a release, publish a release, cut a tag, run release steps, or when a user references RELEASE_GUIDE.md.

Apply a Research → Plan → Implement → Validate workflow with Copilot CLI, including context budgeting and persistent artifacts via /share.

Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.

Curated project templates that guide feature-dev Phase 3 questions with research-backed technology choices. Provides standardized options for common project types (SaaS API, ML Service, CLI Tool, Full-Stack). Use when starting new projects or when feature-dev needs structured decision guidance. Do NOT use for existing projects with established stacks - analyze existing code instead.

Advanced code search tool that finds definitions, usages, tests, and references across the entire codebase. Use when you need to understand how a symbol is used throughout the project.

Research-driven investigation skill for validating solutions and exploring documentation. Never ask questions you can answer yourself through research. Use WebFetch, WebSearch, and testing to validate ideas before presenting them. Deliver concrete, tested recommendations with evidence.

Orchestrate comprehensive TODAS research for novel/emerging domains (1-7 subagents adaptive). Specializes in unprecedented topics, post-training data, and emerging technologies. Uses adaptive depth-based methodology: straightforward queries (1 agent), standard queries (2-3 agents), complex queries (5-7 agents). Handles depth-first (multiple perspectives), breadth-first (distinct sub-topics), and straightforward investigations. Triggers include "novel", "emerging", "2025", "2026", "unprecedented", "new technology", research on topics that didn't exist during training cutoff.

Orchestrate workflows across multiple AI models (Perplexity, GPT, Grok, Claude, Gemini) for comprehensive security research, competition execution, and strategic analysis using GUI interfaces or API automation

Identifies dependencies between GitHub issues and creates appropriate cross-references. Use when you need to map issue relationships, find blockers, or organize work order based on dependencies.