Research

Gather comprehensive biological target intelligence from 9 parallel research paths covering protein info, structure, interactions, pathways, expression, variants, drug interactions, and literature. Features collision-aware searches, evidence grading (T1-T4), explicit Open Targets coverage, and mandatory completeness auditing. Use when users ask about drug targets, proteins, genes, or need target validation, druggability assessment, or comprehensive target profiling.

Build AI agents that automate scientific research — hypothesis generation, experiment design, data analysis, and paper writing using agentic tree search. Use when: automating research workflows, generating and testing hypotheses, building AI-powered research assistants.

Coordinate multiple AI agents working together on complex tasks — routing, handoffs, consensus, memory sharing, and quality gates. Use when tasks involve building multi-agent systems, coordinating specialist agents in a pipeline, implementing agent-to-agent communication, designing swarm architectures, setting up agent orchestration frameworks, or building autonomous agent teams with supervision and quality control. Covers hierarchical, mesh, and pipeline topologies.

Extract insights from data with SQL, visualization, and clear communication of findings.

Classic Zwicky box: parameter identification → value enumeration → matrix construction

Generate a complete, executable Research Spec from North Star + user input. Strategy-level skill that orchestrates questioning, outline, and spec writing.

Design worst possible solution → extract insights → invert. Deliberate failure design as creative catalyst.

Design the worst possible solution. Deliberate failure engineering to reveal hidden constraints and inversion opportunities.

Construct extreme but plausible worst-case scenarios for stress testing

Stress-test the winning candidate using Pre-mortem, Red Teaming, and Failure Mode Analysis to expose hidden weaknesses before commitment.

Score a problem against Rittel's 10 criteria to determine if it is tame, complex, or wicked.

Apply Rittel's 10 criteria to determine if the problem is tame, complex, or wicked, and adjust research strategy accordingly.

Feature cross-matrix construction and blank area identification for patent opportunity mapping

Identify unexplored viable regions in the morphological matrix where no existing methods operate.

Identify matrix regions not covered by existing methods

Identify patent coverage gaps — feature cross-matrix blank areas revealing unprotected technology combinations. Budget: 150 patent families, 10 claim parses, 60 web searches.

SOP: 扰动权重检验 gap 排序稳定性，输出稳定性判定

Determine criteria weights using AHP, Swing, BWM, MACBETH, or Simos methods.

Compute criteria weights using a specified elicitation method (AHP, Swing, BWM, MACBETH, or Simos).

Quick web scanning for landscape understanding. Import of web-browsing/web-search skill. Snippets only — no conclusions from snippets alone.

Full-page web reading for non-academic perspectives — blogs, tech reports, product pages, industry analysis. Import of web-browsing/web-research skill. Must fetch full page via apify for every analyzed page.

Classifies discovered weaknesses into severity tiers (fatal/major/minor/cosmetic) with structured justification and exploitability assessment.

Simplified crystallization strategy for users who have a general research direction (e.g., "I'm interested in LLM reasoning") but lack specificity. Simplifies actor profiling and landscape reconnaissance, then proceeds through direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use when the user's first message reveals a general area but not a specific problem.

Map 15 vital relations between concepts