scientific-method

A portable agent skill for sharpening research questions.

Turn vague research directions into falsifiable, evidence-grounded Research Idea Briefs with a six-stage Codex workflow.

Pressure-test research claims with falsifiable evidence plans, adversarial checks, frozen verifiers, and proof ledgers.

A personal learning environment that helps you find your unknown unknowns by grilling you against the consensus research on a particular topic or question.

Improve scientific collaboration in AI-assisted research. Citation validation, claim verification, cross-file consistency.

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.

Big Research：独立第三方 AI 辅助科研插件。研究者主导问题、方法与判断，支持 Codex 和 Claude Code，提供证据追踪、本地 MCP 和交互视图。

This repository contains a solutions for the exercises in the "Math Concepts For Developers" course at SoftUni .

One epistemic standard on three hosts. Claude Code: 15 problem-shaped skills, 97 sourced reasoning patterns, 120 agents, commit-time gates. Codex and Gemini CLI: portable evidence-synthesis, design and goal-loop skills. Shared gates block unsourced constants, vacuous tests and AI-writing patterns. I do not know is a supported outcome.

Structured observation management for research agents

Your agents change the code, then explain why. This skill makes them bet on the result first.

A research graph that remembers what didn't work. Markdown in git. Run it before the experiment, not after: it says what to work on, what has already died, and what the result must survive.

Scientific TDD for AI coding agents: pre-registration before data, claims audit before submission, external novelty gate, reproducibility. Claude Code + 4 platforms.

MCP server for Claude Desktop that applies Popperian falsifiability to verify claims from social media, news and blogs — with real academic sources, not opinions.

FlatEarthers unite, organise and produce. Document your proofs and help make an archive that anyone can reference at any time. We want FEU in every country, thus all languages. Lets bridge the gap between those that know Earth's measured flat & those that simply believe what they've been taught.

A method for keeping AI-assisted research honest: pre-registration + an independent agent that recomputes every claim from raw data. Forged on markets — 16 certified dead hypotheses. Runnable demo included.

DISCOvery engine: the agent invents its own questions, predicts before it runs, keeps only machine-verified, reality-culled claims — self-evolving methodology, multi-agent science. Procedurally-generated contamination-free worlds make discovery an RL environment: execution-anchored rewards, SFT/GRPO-ready trajectories.

Virtualized GnosisLab research environment with KVM isolation, protected scientific services, and sandboxed experiment execution.

Scientist agent mode for AI coding agents — hypothesis-driven, evidence-based, uncertainty-aware.