Research & Data

Analyze LinkedIn performance and manage engagement through Publora. Use when the user asks how a LinkedIn post or account performed (impressions, reach, reactions, comments, reshares, follower growth) or wants to react, comment, reshare or resolve an @mention. Statistics run over the REST API, engagement over MCP tools. Not for creating posts (use linkedin-post).

Scrape AI papers published by 28 big tech companies and AI labs in a given date window, with institutional attribution (lead vs. participating vs. intern). Use when the user asks "what did big tech publish recently", "what AI research has <company> put out", "run the paper radar", or wants to inventory recent arXiv output by company or topic. Also for fact-checking questions like "has <company> published anything on <topic>".

Find, verify and rank potential customers, first customers, early adopters, design partners, beta users or sales leads for a product using public pain, demand and timing signals. Use when the user supplies a product URL, repository, pitch or description and wants an ideal customer profile, a researched prospect shortlist, evidence-backed lead qualification, fit and timing scores, source-verified buying signals, repeated pain patterns, a CRM-ready lead export, source-based outreach drafts, or a shareable prospecting report. Every prospect must be traceable to a fetched, dated public source. Never sends outreach.

Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, or Hermes Agent, apply an author's frameworks while working, or build a reusable knowledge base from a file.

Modular, production-ready skills for Claude Code, Claude Desktop, and Cowork (Google Search, Antigravity Pool, etc.)

Battle-tested Claude Code skills extracted from real production work — Meta ads tracking, multi-tenant Next.js, Shopee data import, and FB domain verification

量化分析方法论 - 5阶段自下而上框架,适用任何数据集。Claude skill + 独立脚本,沉淀机制让方法论自我进化。

A CLI way to interact with autodoc.ru & armtek.ru to search & order spare parts for your car. Includes agent skill for tool usage

Claude Skills toolkit for diagnosing audience-development opportunities: research, awareness, engagement, and integration mechanics.

A Hermes agent wired for DeFi: native onboarding, four modular Galleon skill packs, and official data, infrastructure and wallet connections.

Multi-year health checkup reports to normalized time series: trend analysis, offline dashboard. Runs fully local · 体检趋势分析

PII & PIPL/GDPR audit for Agent Skills: 17 sensitive fields + 5 credential formats, anti-false-positive, CI exit codes · 个人信息脱敏审查

Zero-harm Windows cleanup skill: thorough Edge/Chrome startup disable, official-first drive migration, cache cleanup.

KLineAPI - A股实时行情 API Skill：56+ 数据接口（实时行情/涨停池/龙虎榜/资金流向/财务数据），注册即送全部接口体验额度。

An evidence-first workflow for consequential repository changes and completion claims.

多元星途 · PathwayAtlas：点亮多种升学路径，走出个性升学星途。基于可验证公开证据的 AI 升学规划 Skill。

12 agent skills for finance and accounting: FP&A, cap tables, tax, treasury, and investment research.

Decision-research skill for Claude Code and Codex - every claim states how well it is supported, and says when the evidence cannot settle it. A free tool by DBHQ.

Copilot CLI-first workflows for AI agents: shared instructions, reusable skills, multi-model delegation, human approvals, and local-first task tracking. Fork your own.

山西证券Tushare Skill

Build production-ready Codex skills from workflow descriptions. Complete reusable skill package with metadata, references, and behavioral evals.

A Codex skill and project-local toolkit for installing AUTO-07p, running bifurcation analysis, and visualizing continuation results.

An evidence-driven Codex skill for reviewing code, diffs, repositories, tests, dependencies, CI/CD, infrastructure configuration, and machine-generated analysis reports.

Claude skill for OneLogin SSO/SCIM setup, benchmarked: 100% with-skill vs 50% without on the same rubric. Full eval harness and transcripts included.