Research & Data

Obsidian Vault Assistant is a local-first Codex skill and MCP server for people who want a searchable, maintainable Markdown knowledge base. It discovers configured Obsidian vaults, searches a three-layer model (Raw, evidence/middle, and Wiki), reads only the relevant chapter, and stages every change for explicit review.

本地 Agent Skill 管家:盘点全部本地 skill 的功能/来源/配套客户端,体检重复加载与链接漂移,生成 Markdown+HTML 报告,支持 --json 自动巡检 | Local agent-skills auditor with interactive HTML reports

Agent Skills for Neon Severless Postgres

A consent-first Codex skill for daily work reports and Feishu calendar planning

DVERA agent skills for CT C/C++ verification workflows: project setup, analysis, test generation, coverage, reporting, and regression.

Claude Skill for reviewing requirements/user stories against 7 quality criteria before test analysis — quote-based findings, severity levels, and open questions to the BA

Claude Code skills for running models cost-effectively: security gates (secret scanner, commit-gate), model-quality tooling (eval harness, token-squeeze, compact-io, opus-workers), review/advisory (trusted-advisor, audit, skill-vet, research-brief), and a read-only reorg-proposal advisor.

Evidence-grounded Codex Skill for protected data, controlled deformations, and reverse consistency.

Vet MCP and AI-agent tools before attachment. Local, deterministic static scanning with no tool execution, plus CI and redacted public records.

Generate private, reproducible Local Services Ads responsiveness reports from any raw-GAQL-capable Google Ads connector.

Brand Soul — an open-source framework created by Cacao Web Studio for persistent, evidence-aware AI brand identity.

Homelab automation packaged as Agent Skills for skills.sh, plus the MCP servers built on top of them

An automated auditor skill for Claude Code that performs comprehensive Technical SEO, Accessibility, Structured Data, and Generative Engine Optimization (GEO) audits on any website, page, or codebase.

ROSTR Agent — Self-improving multi-agent framework with built-in PAL, NPAO, RAG DAL, and Rostr Hub. Built on Hermes Agent by Nous Research.

把散乱资料，沉淀成自己的知识资产。将真实材料整理成可复用的文稿、摘要和来源索引。

MCP server for Scholar Sidekick — resolve any scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into 10,000+ CSL styles or nine export formats, single or batch.

Skills Constitution — meta-rule governing all skill invocations across agent platforms

Codex skills for game research, market analysis, opportunity discovery and project greenlight decisions.

Agent skill: your AI coding logs as a gamified character sheet — Claude Code, Codex, OpenCode, Gemini, Copilot. 74 achievements, fixed-scale metrics, LLM-written chronicle, research-backed advice. 100% local, RU/EN.

Reusable Codex Skill for verified public-X research, Japanese beauty discovery, and linked Excel dashboards.

结构化奇门遁甲实战分析 Codex Skill：取用、分层读局、专题模块、风险边界与案例回归。

Evidence-driven Agent Skills for project recovery, persistent-state safety, product data auditing, and release qualification.

Cost-aware Claude skill (playbook) for the DataForSEO API — companion to the official DataForSEO MCP server. Picks the right endpoint & mode (Live/Standard/Labs) and enforces budget guardrails.

An evidence-driven Codex skill for analyzing public companies and industries with Porter Five Forces, industry-chain mapping, ecosystem-control assessment, and public filings.