Research & Data

Four Claude skills built to remove recurring manual work from actual, repeated tasks in my coursework, FYP search, job applications, and project presentations at FAST-NUCES Lahore.

Codex skill: authorized web security assessment and evidence-based reporting

Claude and Codex skill to analyze and evaluate VMware RVTools XLSX exports.

waterline - offline, LLM-free, dependency-free differential reachability analyzer for Agent Skill bundles: computes the reachable closure under four resolver models and reports where a scanner's view diverges from an agent's (the audit-runtime gap + reference laundering)

A Claude skill that turns rough topics into evidence-backed, research-ready project ideas. Use it when you need a thesis/capstone/final-year topic, want to find research gaps, check whether an idea is already explored or patented, or turn a vague idea into a well-scoped research proposal.

Codex skill for researching, drafting, previewing, and safely publishing Cantonese market commentary on TTM

亚马逊选品 之 Listing全维度穿透分析报告 加上 全品类分析 ，关键词分析，差评分析 ，市场调研 等等。OpenClaw /claude code agent skill, amazon sellersprite research MCP 智能体skill.基于 卖家精灵 MCP 服务和 Claude Skills 的亚马逊竞品分析工具集

Reusable agent skills for Mercury/pi assistants - schema-driven registries (what exists) and trackers (work that moves), zero-dependency Python engines

An Overview for Agency Agent to view all the Agents and Search for them

TOA询问法：人指导AI的逐题征询协议 / A question-by-question elicitation protocol for human-guided AI

Ten Claude Code skills that audit and clean data quality in any SQL database: profiling, quality metrics, audit report, standardization, imputation, deduplication, and defect prevention.

Evidence-first fact-checking Agent Skills suite for reproducible source verification and answer comparison.

name: mind-skill

牛得林奇每周课程直播总结 Agent Skill：转写优先、观点归属、公司全量台账与跨期记忆

𝑺𝒌𝒊𝒍𝒍𝒔 𝒂𝒏𝒅 𝒑𝒍𝒖𝒈𝒊𝒏 𝒕𝒐𝒐𝒍𝒌𝒊𝒕 𝒇𝒐𝒓 𝑯𝒂𝒓𝒏𝒆𝒔𝒔 𝑨𝒈𝒆𝒏𝒕.

AI Skill for Xuntou QMT Knowledge Docs

Public skill project for OpenAI- and Groq-aware LLM rate limiting, retries, quota handling, and provider-specific pacing.

Agent skill and TypeScript client for non-custodial Hoodieswap trades and launches on Robinhood Chain

Agent skills for the BigValue data marketplace workspace.

从项目结果中学习，在改动前预防返工，并沿根因完成治理的 Agent Skill。

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

Codex skills and validation tools for agentic Power BI report development

Read-only MCP server and Codex skill for local LLM-powered repository analysis

Personal Claude Code skills for deployment, debugging, testing, research, and project scaffolding