Research & Data

Daily AI model radar: track, compare, and visualize model quality across domains. / AI模型雷达：每日追踪对比各领域模型质量与价格

A reusable AI-agent skill for Gulf and Middle East risk analysis across Iran sanctions, GCC banking, energy, and maritime chokepoints.

Multi-repo workflow isolation skill for DeepSeek Harness - one isolated entry agent per repo, one controller for cross-project dispatch, model routing & hash-chained ledger

基金副驾：AI agent skill that screens Chinese mutual funds from public data for manual purchase through Alipay. Copilot, not autopilot — 它筛选，你决定。不登录、不下单、不预测。

开源 skill：把「首席科学家 + flash 研究员」团队协作模式固化为可复用规则手册——主模型只做规划/审查/汇报，便宜的小模型并行执行，省 pro 开销、省时间。

Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

Codex skill that locally scans files and text for C2PA, AI metadata and Unicode provenance signals

Agent skill for codebase analysis, requirement alignment, explicit approval, and style-consistent development

Binary-only static reverse-engineering CLI and agent Skill for bounded, evidence-backed analysis

Grade Agent Skills against a production-grade quality rubric (3 hard gates + six-dimension weighted scoring). Evidence-based LLM-as-judge reports.

Codex skill for converting FileOrganization tasks into independently judgeable metadata.json files

Intelligent, catalog-driven Codex Skill for PPTX, HTML slides, PDF, covers, infographics, diagrams, exact-data binding, routing, and QA.

AI-agent skill for migrating Matillion ETL pipelines to Databricks

35 production Claude Code skills for GTM engineering: campaign ops, deliverability, lead gen, enrichment, reporting

Privacy-focused Codex skill for diagnosing Lithe Audio speaker dropouts, delays and network issues. Checks a local IP, Wi-Fi, DHCP, latency, packet loss and roaming; provides guided fixes, permission-based router support and redacted reports without exposing credentials or internal APIs.

Codex skill for natural-language analysis of LAS, DLIS, and WITSML well logs

SAP Commerce agent skills for analysis and upgrade workflows.

Orbit Skills: API-grounded agent skills for ORBIT organoid research workflows

Codex skill for summarizing PyTorch commit ranges into Chinese Markdown reports.

Evidence-based Codex skill for technical, product, research and commercial auditing of software projects with an immersive intelligence dashboard.

Agent skills for data development: routing + financial DB quality checks

Amazon review analysis Agent Skill: dynamic taxonomy, original excerpts, HTML board.

A Claude Code / Codex skill that generates concise, research-oriented Chinese group-meeting presentation scripts from papers, slides, notes, figures, and code.

Claude Code skill: unified search across GitHub and OpenAlex