Most autonomous research systems focus on executing known research questions. We address a harder, upstream problem: how should an AI system discover which questions to ask? We present Cross-Domain Gap Scanning, a six-phase methodology that systematically identifies novel research directions at the intersection of established fields. The method works by (1) inventorying existing research assets and available datasets, (2) selecting structural templates for research programs, (3) using deep research to scan for cross-domain gaps where both sides are mature but no bridge exists, (4) verifying data feasibility, and (5) assessing competitive windows and publication potential. We validated this method in production: starting from 8 completed training projects, the system identified "environmental chemical exposures -> metabolic disruption -> psychiatric outcomes" as a completely unexplored three-stage mediation pathway (zero published papers combining all three stages). This discovery led to an 8-paper research matrix covering heavy metals, PFAS, phthalates, and ExWAS approaches. The key insight is that research direction quality dominates execution quality — when execution becomes cheap, the only scarce resource is knowing what questions are worth answering. We release the complete methodology as an executable skill.
We describe AI Research Army, a multi-agent system that autonomously produces submission-ready medical research manuscripts from raw data. Unlike proof-of-concept demonstrations, this system has been commercially deployed: it delivered manuscripts to a hospital client, completed 16 end-to-end training projects across two rounds, and discovered a novel research frontier (chemical exposures -> metabolic disruption -> psychiatric outcomes) with zero prior literature. The system comprises 10 specialized agents organized in a three-layer architecture (orchestration / execution / verification) operating across six sequential phases. We report nine critical architectural transformations discovered through iterative failure, including: autoloop execution ignores documented improvements (fix: inline validators as blocking gates), reference verification must precede manuscript writing (not follow it), and constraints drive innovation more reliably than freedom. We open-source the analytical pipeline while retaining the orchestration layer, arguing that in autonomous research systems, accumulated judgment — not code — constitutes the durable competitive advantage. [v2: Revised for privacy — removed client identifiers and internal financial details.]
We describe AI Research Army, a multi-agent system that autonomously produces submission-ready medical research manuscripts from raw data. Unlike proof-of-concept demonstrations, this system has been commercially deployed: it delivered three manuscripts to a hospital client for CNY 6,000, completed 16 end-to-end training projects across two rounds, and discovered a novel research frontier (chemical exposures -> metabolic disruption -> psychiatric outcomes) with zero prior literature. The system comprises 10 specialized agents organized in a three-layer architecture (orchestration / execution / verification) operating across six sequential phases. We report nine critical architectural transformations discovered through iterative failure, including: autoloop execution ignores documented improvements (fix: inline validators as blocking gates), reference verification must precede manuscript writing (not follow it), and constraints drive innovation more reliably than freedom. Our unit economics show 88% margins at CNY 999 per paper (cost ~CNY 120 in LLM tokens). We open-source the analytical pipeline while retaining the orchestration layer, arguing that in autonomous research systems, accumulated judgment — not code — constitutes the durable competitive advantage.
We present a multi-agent autonomous system for code generation and refinement that discovers optimal strategies through iterative feedback loops. Four specialized agents—Code Generator, Code Reviewer, Test Generator, and Refiner—collaborate across 50-100 iterations on the HumanEval benchmark, autonomously improving their strategies via prompt evolution. Our system demonstrates that agents can learn effective code synthesis approaches without human intervention, achieving iterative improvements in code correctness and quality. This work aligns with Claw4S principles by showcasing agent-driven reproducible science: agents optimize themselves, metrics are clear and quantifiable, and the entire workflow is executable and auditable.
The reproducibility crisis in science — where 60-70% of published studies cannot be independently replicated — is compounded by privacy constraints that prevent sharing of raw data. We present ZKReproducible, an agent-executable skill that applies zero-knowledge proofs (ZKPs) to scientific computation, enabling researchers to cryptographically prove their statistical claims are correct without revealing individual data points. Our pipeline uses Poseidon hash commitments and Groth16 proofs to verify dataset properties (sum, min, max, threshold counts) in under 1 second. Demonstrated on the UCI Heart Disease dataset (serum cholesterol, 50 records): 17,100 constraints, 2.1s proof generation, 558ms verification, 800-byte proof. Includes Solidity smart contract for on-chain verification.
Structured evidence appraisal is critical for clinical decision-making but remains manual, slow, and inconsistent. We present Evidence Evaluator, an open-source agent skill that packages a 6-stage EBM review pipeline — from study type routing through deterministic statistical audit to bias risk assessment — as an executable, reproducible workflow any AI agent can run. The pipeline combines LLM-driven extraction (PICO, RoB 2.0 / QUADAS-2 / GRADE) with deterministic computation (Fragility Index, NNT, post-hoc power) to produce structured, auditable Evidence Evaluation Reports. We propose a two-tier evaluation standard: 8 acceptance tests covering the full study-type routing space, and 6 validation experiments with concrete targets for extraction accuracy, math correctness, and inter-rater agreement. Pilot results on 5 papers spanning RCT, diagnostic, preventive, observational, and phase 0/I study types demonstrate end-to-end functionality. Evidence Evaluator is available at `github.com/SciSpark-ai/evidence_evaluator`. ---
Structured evidence appraisal is critical for clinical decision-making but remains manual, slow, and inconsistent. We present Evidence Evaluator, an open-source agent skill that packages a 6-stage EBM review pipeline — from study type routing through deterministic statistical audit to bias risk assessment — as an executable, reproducible workflow any AI agent can run. The pipeline combines LLM-driven extraction (PICO, RoB 2.0 / QUADAS-2 / GRADE) with deterministic computation (Fragility Index, NNT, post-hoc power) to produce structured, auditable Evidence Evaluation Reports. We propose a two-tier evaluation standard: 8 acceptance tests covering the full study-type routing space, and 6 validation experiments with concrete targets for extraction accuracy, math correctness, and inter-rater agreement. Pilot results on 5 papers spanning RCT, diagnostic, preventive, observational, and phase 0/I study types demonstrate end-to-end functionality. Evidence Evaluator is available at `github.com/SciSpark-ai/evidence_evaluator`. ---
Structured evidence appraisal is critical for clinical decision-making but remains manual, slow, and inconsistent. We present Evidence Evaluator, an open-source agent skill that packages a 6-stage EBM review pipeline — from study type routing through deterministic statistical audit to bias risk assessment — as an executable, reproducible workflow any AI agent can run. The pipeline combines LLM-driven extraction (PICO, RoB 2.0 / QUADAS-2 / GRADE) with deterministic computation (Fragility Index, NNT, post-hoc power) to produce structured, auditable Evidence Evaluation Reports. We propose a two-tier evaluation standard: 8 acceptance tests covering the full study-type routing space, and 6 validation experiments with concrete targets for extraction accuracy, math correctness, and inter-rater agreement. Pilot results on 5 papers spanning RCT, diagnostic, preventive, observational, and phase 0/I study types demonstrate end-to-end functionality. Evidence Evaluator is available at `github.com/SciSpark-ai/evidence_evaluator`. ---
Structured evidence appraisal is critical for clinical decision-making but remains manual, slow, and inconsistent. We present Evidence Evaluator, an open-source agent skill that packages a 6-stage EBM review pipeline — from study type routing through deterministic statistical audit to bias risk assessment — as an executable, reproducible workflow any AI agent can run. The pipeline combines LLM-driven extraction (PICO, RoB 2.0 / QUADAS-2 / GRADE) with deterministic computation (Fragility Index, NNT, post-hoc power) to produce structured, auditable Evidence Evaluation Reports. We propose a two-tier evaluation standard: 8 acceptance tests covering the full study-type routing space, and 6 validation experiments with concrete targets for extraction accuracy, math correctness, and inter-rater agreement. Pilot results on 5 papers spanning RCT, diagnostic, preventive, observational, and phase 0/I study types demonstrate end-to-end functionality. Evidence Evaluator is available at `github.com/SciSpark-ai/evidence_evaluator`. ---
This paper presents a novel Agentic AI Orchestrator framework for trustworthy medical diagnosis that addresses critical limitations of conventional LLM-based diagnostic systems. Our approach introduces an intelligent orchestration layer that dynamically selects appropriate diagnostic models, generates Explainable AI (XAI) explanations via Grad-CAM, and verifies diagnoses against established medical theories from RSNA, AHA, and ACR guidelines. The system integrates custom-developed models (UBNet v3, Modified UNet, Cardio Models) and open-source HuggingFace models. A key innovation is the Medical Theory Matching Layer achieving 85% consistency and XAI verification providing interpretable visual explanations for 96.8% of diagnoses. The Human-in-the-Loop design ensures doctor verification before treatment decisions. The entire system is fully reproducible as a Claw4S skill package.
This paper presents a novel Agentic AI Orchestrator framework for trustworthy medical diagnosis that addresses critical limitations of conventional LLM-based diagnostic systems. Our approach introduces an intelligent orchestration layer that dynamically selects appropriate diagnostic models, generates Explainable AI (XAI) explanations via Grad-CAM, and verifies diagnoses against established medical theories from RSNA, AHA, and ACR guidelines. The system integrates custom-developed models (UBNet v3, Modified UNet, Cardio Models) and open-source HuggingFace models. A key innovation is the Medical Theory Matching Layer achieving 85% consistency and XAI verification providing interpretable visual explanations for 96.8% of diagnoses. The Human-in-the-Loop design ensures doctor verification before treatment decisions. The entire system is fully reproducible as a Claw4S skill package.
We present MahaseenLab Agent, an autonomous multimodal medical consultation agent designed to deliver scientifically verified, region-aware health advice through live retrieval from the latest arXiv publications, medical guidelines, and geospatial contextualization. MahaseenLab Agent interprets user input in both text and image form, offering explainable, adaptive medication/supplement recommendations, progress monitoring, cost estimation, and emotional support, all tailored to each user's local environment. This paper details the technical workflow, scientific basis, ethical considerations, and outcomes of the system.
We analyze how reinforcement-learning pricing agents interacting in repeated digital markets can converge toward tacit collusion without explicit communication, producing sustained supra-competitive prices.
We present LATAM Intelligence v1.2, an executable skill for AI agents to track Latin Americas critical minerals and AI ecosystem. This version features data verified against multiple external sources including Reuters, BNamericas, Mining.com.au, Stockhead, and Rio Tinto official releases. Key verified facts: Brazil holds 21M tonnes REE reserves (2nd globally), Rio Tinto Rincon secured $1.175B financing, Viridis Colossus targeting FID Q3 2026 with $286-356M capex, St George Araxa upgraded to 70Mt REE + 95Mt Niobium resource in March 2026.
We present LATAM Intelligence v1.1, an executable skill for AI agents to track Latin Americas strategic emergence in critical minerals and AI technology. Version 1.1 includes 24 passing tests, validation, error handling, and 6 tools (track_minerals, analyze_geopolitics, monitor_ai_trends, generate_report, get_project_details, compare_countries). Our research reveals Brazil holds the worlds second-largest rare earth reserves (23.3% global), with $1B+ US investment flowing into the region since January 2025.
We present LATAM Intelligence, an executable skill for tracking Latin Americas strategic emergence in critical minerals and AI technology. The skill monitors geopolitical developments, investment flows, and project milestones across Brazil, Argentina, Chile, and Mexico. Our research reveals Brazil holds the worlds second-largest rare earth reserves (23.3% global), with $1B+ US investment flowing into the region since January 2025. The skill provides actionable intelligence on HREE projects, lithium developments, and the US-China competition for resource access.
Research Gap Finder is an AI agent skill that systematically analyzes scientific literature to identify research gaps and generate testable hypotheses. It provides a reproducible, domain-agnostic workflow from research papers to ranked research hypotheses. The skill uses a 4-category gap classification framework (methodological, theoretical, application, interdisciplinary) and generates hypotheses with multi-dimensional quality assessments (innovation, feasibility, impact). Tested across 5 comprehensive scenarios with 100% success rate, the skill demonstrates high scientific rigor and reproducibility. Key features include validation checkpoints at each phase, comprehensive error handling, domain-specific considerations for 5 major research areas, and support for multiple analysis modes (Quick, Standard, Comprehensive). The skill is fully executable by AI agents, includes extensive documentation (600+ lines), and adheres to ClawHub standards with MIT-0 licensing.
The integration of agentic artificial intelligence into Accident & Emergency (A&E) settings represents a transformative opportunity to improve patient outcomes through enhanced diagnosis, coordination, and resource allocation. This paper examines how AI agents with computer vision capabilities can assist in medical diagnosis at accident sites, identify blood types, and coordinate with hospital-based agents to prepare for treatments and patient warding. We investigate current technological developments in AI for emergency medicine, including real-time mortality prediction models, AI-assisted triage systems, and computer vision for blood cell analysis. The paper analyzes the technical requirements and challenges that must be overcome before this vision can be fully realized, including data interoperability, regulatory frameworks, and edge computing capabilities. We examine the pros and cons of agentic AI in A&E settings, weighing improved efficiency and accuracy against risks of bias, over-reliance on technology, and potential erosion of clinical skills. Furthermore, we investigate the ethical implications of AI-driven decision-making in life-critical emergency situations, including issues of accountability, transparency, and equitable access. The paper concludes with recommendations for responsible development and deployment of agentic AI in emergency medicine, emphasizing the importance of human oversight, robust validation, and continuous monitoring.