A structured epistemological framework for high-stakes discovery and investigation. Generate wide. Filter hard. Verify everything. Report what survives.
-
Updated
Aug 28, 2026
A structured epistemological framework for high-stakes discovery and investigation. Generate wide. Filter hard. Verify everything. Report what survives.
KANIT: an evidence-graded knowledge base of antimicrobial resistance biomarkers in the ESKAPEE pathogens
Process card, kill gates and zero-dependency checkers for tools that make decisions.
Medical student AI methodology prompts — capture, knead, decide. Study aid only. Not medical advice.
Medical-Research-MCP: Evidence-graded scientific literature search for AI agents - an MCP server for PubMed, Europe PMC, ChinaXiv and RussiaRxiv.
Open-API-first literature search for rapidly finding high-quality references, resolving open access, grading evidence, and exporting citations.
KANIT: an evidence-graded knowledge base of antimicrobial resistance biomarkers in the ESKAPEE pathogens
Execution protocol for AI coding agents. Complexity routing, phase gates, TDD, evidence grading, verification gates, multi-persona review.
An open-source tree of knowledge filled by autonomous AI research workers — grading scientific claims (T1–T6) from primary literature, clinical trials, and the web.
The sleep cycle for AI memory: SHA-256 evidence receipts, drift detection, and a 5-stage consolidation pass. Facts that stop being true stop being served.
Auditable comparative-genomics workflow for evaluating longevity-related signals in the Greenland shark.
Claude Code skill: tiers every factual claim in a manuscript STRONG, MODERATE or SPECULATIVE before print; debunked claims count as findings.
DeepSeek Harness plugin: registers the research-charts-mode (调研与图表模式) agent preset - evidence-graded clinical and pipeline research that ends in auditable figures. Bundles three self-contained skills (high-confidence research, target/indication diligence, clinical landscape charts) and is installable as a .dshpreset.
Stress-test a claim before it becomes a decision. Decision-readiness grading for humans and agents.
Turn research corpora into auditable, evidence-graded claim inventories. A Claude skill with archaeology and medical-scientific grading presets.
《粗码》:越省力为什么分得越粗,核实为什么总是追不上 —— 28 章、491 页,一条驻点式推到个人/群体/社会/文明;A/B/C 证据分级、21 条预言台账、9 处空白。 / Coarse Codes: why saving effort makes us coarser, and why verification trails behind. 28 chapters, 491 pp; one first-order condition carried through four layers; graded evidence, 21 predictions, 9 declared gaps. CC BY 4.0.
DeepEpisteme — reusable epistemic infrastructure for evidence-graded corpora. Tunisia is the first deployment.
诠释的权衡|历史研究中的置信度、权衡与理论流变——从人物还原到范式转移的五个应用。7 部分 25 章 / 216 页。独立研究系列「有限系统的取舍」之ㄧ:结论标 A/B/C,登记簿 append-only,结构校阅 lint 0 error。 · The Interpretation Tradeoff: Confidence, Tradeoffs and Theory Change in History
To associate your repository with the evidence-grading topic, visit your repo's landing page and select "manage topics."