Research & Data

Практический гид по AI для 1С: MCP, Agent Skills, OData, безопасность и проверенные сценарии

A standalone AI agent runtime for Windows, Linux, and macOS. Execute declarative YAML agents with built-in access to 2,600+ connectors—including databases, APIs, files, SSH, cloud services, messaging platforms, and more. No coding. No installation.

Save any webpage as one high-resolution PDF — also on Firefox for Android. Runs entirely on your device: no upload, no account, no data collection. Webseite als PDF speichern, komplett lokal. MIT licensed.

Ozmed AI is a chat assistant that lives in your terminal and can actually do things on your computer, not just talk. You type what you want in plain words, and it can run Python code, run PowerShell commands, and search the internet, all on its own, to get the job done.

用中文进行Blender建模的技能

拆抖音对标 · 输入一个抖音账号，全量采集公开作品数据并产出对标调研报告（原始数据 + Markdown + 浅色杂志风 HTML）。Agent-friendly skill.

Give your AI agent a phone number: order a private number in any country over the API, read the SMS verification code, hand the number back.

Create, review, explain, export, verify, or check the freshness of evidence-backed engineering decisions with Proofline. Use for ADRs, architecture decisions, exact source citations, provenance review, stale-decision checks, portable Decision Evidence Packages, and requests to explain which immutable evidence justified a decision.

Audit a local repository for governance gaps, GitHub Actions trust-boundary risks, and unsafe moderation automation. Use for repository security reviews, pull-request workflow audits, pull_request_target or workflow_run analysis, token-permission checks, policy coverage, and requests for a reviewable remediation patch.

DataCube data access agent skill

发现、核验、评分并移交主流 AI 工具新闻、视频案例与实战技巧的 Codex Skill

A claude skill that pulls data from App Store Analytics

Official Mentionlytics skills for Claude — query the Mentionlytics API for mentions, sentiment & brand monitoring data.

Claude Code skills for dev automation (auto-dev pipeline, JHipster test support, data-driven planning)

A Claude Code / Codex skill to export and decrypt WeChat (macOS) chat history into plaintext SQLite databases

A Codex skill for project operations research, competitor discovery, SEO analysis, paid ads analysis, and go-to-market strategy.

362 Claude Code skills, agents, and plugins (30+ agents, 70+ commands) for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and daily productivity skills. MIT licensed.

A single skill file that turns Claude into a full project manager. One command decomposes a plan, spins up parallel sub-agents in isolated git worktrees, runs QA, tracks costs, and delivers a tabbed HTML report.

Recently updated agent-skill-related GitHub repository: cs-xdu-dev-001/-analyze-paper-deeply-C-Users-z2986.codex-skills-analyze-paper-deeply-.

Recently updated agent-skill-related GitHub repository: cas-bigdatalab/piflow.

Portable Codex and Claude skills for researched, minimal, end-to-end verified development workflows.

Claude Skills for financial data analysis using slacking.biz — SEC, FRED, Census, World Bank. 28 MCP tools.

A privacy-safe Codex Skill for Feishu work logging, weekly and monthly reports, and Hermes delivery.

A Claude Skill for auditing the business logic of data analytics deliverables (notebooks, SQL/BigQuery views, dashboards) — verifies claims against raw data, catches redundant computations, unsupported narrative claims, and common aggregation bugs.