medradar
An evidence-first research platform for observing and studying early signals in medical technology development.
- 321
- Python
- 13 h ago
An evidence-first research platform for observing and studying early signals in medical technology development.
Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.
Private, local-first health intelligence for labs, 51 curated SNPs, wearables, light exposure, Biology Scores, optional AI, encrypted sync, sharing, and Agent Access.
The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel, darwin, and redblue behind a promotion gate that never merges.
Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit human approval gates.
Evidence-graded strength-training course curated from 316 public YouTube demos — 11 chapters, 44 units, 31 hours. Every link verified, every movement category checked against PubMed: only 2 of 65 evidence claims reach "strong". Course content in Traditional Chinese.
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.
Proof-carrying completion for AI coding agents. Block 'I'm done' until every critical obligation has evidence.
把 sat.cool《工作流改造術》擴寫成 mega pack:11 章 40 個工作卡點、250+ 支經驗證的 YouTube 影片,每個方法附研究文獻查核。
Anti-marketing product research skill for Claude. Forces category landscape mapping, owner-only sources, counterfactual bias check, scoped verdicts.
把養生建議換算成同一個單位——全因死亡率。15 章 54 單元、348 支經驗證的 YouTube 影片、54 則對回 PubMed 的證據查核,其中 96 支是反方影片。改編自 geekan/HowToLiveLonger。
Agent Skill: turn 'what is the best practice for X?' into a cited literature review — source ladder, claim cards, folklore label, derived confidence. Claude Code / Codex / Cursor / Gemini CLI.
An evidence-graded personality assessment: 65 questions across nine dimensions, every biological claim labelled by how good the research actually is. Static pages generated at build time, one Solid 2 island, scored on your device. Nothing sent anywhere. Not a diagnosis.