Инструменты

Official Anthropic skill for cleaning messy Excel exports: trims spaces, standardizes case and dates, converts text numbers, dedupes, and flags mixed types, garbled text and errors. Keeps originals via helper-column formulas and confirms each step. Works in Claude for Excel; local files need Python.

Cross-platform shell built around structured data: pipelines pass tables instead of plain text, and you can open and query JSON, CSV, TOML and more directly. Default builds include nu --mcp, which serves it to agents as an MCP server.

Converts PDFs, images, PPTX, DOCX, XLSX, EPUB and more into Markdown, JSON or HTML, preserving tables, formulas and layout, with optional LLM help for higher accuracy. Needs Python 3.10+ and PyTorch; large-scale commercial use of the model weights needs a paid license.

Drafts self-reviews, peer reviews, 360 and upward feedback in STAR structure with concrete examples instead of filler, as Markdown drafts it never submits. With Microsoft WorkIQ it gathers your contributions from Microsoft 365 mail and meetings; otherwise it works from your notes.

PostHog's official hosted MCP: lets agents query product analytics with HogQL, manage feature flags and A/B experiments, and investigate errors and session replays. Sign in to PostHog to authorize; tool calls are free, though a few LLM-powered tools count toward AI usage.

Browser automation MCP server open-sourced by ByteDance in the UI-TARS-desktop repo: drives pages through Puppeteer accessibility data with an optional vision mode, running locally over stdio or remotely over SSE or Streamable HTTP.

ByteDance's open-source multimodal agent CLI: operates browsers via vision or the DOM and calls terminal, file and MCP tools to complete tasks, with a Web UI and headless server mode. Needs Node.js 22+ and a model API key.

Headless browser written from scratch in Zig for AI agents and automation, using less memory and running faster than headless Chrome in official benchmarks. fetch turns pages into Markdown, and it can serve CDP or MCP. Telemetry is on by default (an env var disables it); Windows needs WSL.

Detects your CPU, memory and GPU and scores open models on whether they run, speed, quality and context, then works with local runtimes like Ollama, llama.cpp and MLX to download and benchmark them. recommend --json gives agent-friendly output.

Local model gateway that routes requests from Claude Code, Codex and other coding agents to providers like DeepSeek, Kimi, Gemini and OpenRouter, with failover, rule-based routing and request logs. Bring your own API keys.

When a user asks whether a skill exists for some task, searches the skills.sh ecosystem with the skills CLI, then recommends and installs a fit. Maintained by Vercel Labs and shipped in the skills CLI repo.

Package manager for the open Agent Skills ecosystem: one command installs skills from GitHub and other sources into Claude Code, Codex, Cursor and dozens more agents, with search, update and removal. From Vercel Labs.

Trading research agent from HKU's HKUDS whose MCP server offers 70+ tools for quotes, financials, backtesting and research across A-shares, Hong Kong and US stocks and crypto. Needs local Python; HK, US and crypto research need no API key. For research only; not investment advice.

Official CLI for Tencent's open-source knowledge base platform WeKnora: upload documents, manage knowledge bases, run hybrid search and answer questions from them, or serve as a read-only MCP. Needs your own WeKnora deployment and a source build with Go 1.26+.

Generates people analytics reports from employee data: headcount snapshots, voluntary and involuntary attrition, diversity metrics, spans of control and flight risk, with findings and recommendations for leadership. Needs an uploaded employee CSV or a connected HRIS. Official from Anthropic.

Data analysis plugin: writes queries in each SQL dialect, explores datasets, runs statistical tests, charts with Python and builds interactive HTML dashboards, then reviews methods and conclusions before sharing. Connects to Snowflake, BigQuery and other warehouses. Official from Anthropic.

Drafts customer-facing replies tuned to the situation and relationship: product questions, outage notices, bad news like delays or won't-fix, declined feature requests and billing disputes, with adjustable tone. From Anthropic's official customer-support plugin; review before sending.

For preclinical life sciences research: bundles MCP connectors for PubMed, bioRxiv, ChEMBL, Open Targets, ClinicalTrials and more, plus analysis skills for single-cell RNA QC, scvi-tools and nf-core pipelines. Official from Anthropic; some data sources need accounts.

HR plugin: drafts offer letters, generates onboarding checklists, runs performance reviews, answers policy questions, and produces compensation benchmarks and people analytics reports. Can connect to HRIS and ATS systems. Official from Anthropic.

Performance review season helper: generates self-review and manager review templates and calibration materials, summarizes rating distributions and promotion cases, and rewrites vague feedback into specific behavioral examples. Works in plain chat. Official from Anthropic.

Screens resumes against a role rubric into a cited shortlist, ignoring irrelevant details like name and age; drafts invite, hold or decline replies, schedules interviews and builds onboarding checklists. Gmail and Calendar are optional, sending only after you confirm. Official from Anthropic.

Collects reviews and complaints from Google, Yelp, Facebook and more, groups them by theme with quotes, and drafts replies in the owner's voice that post only after approval; also finds lapsed customers and drafts win-back messages. Official Anthropic small-business plugin.

Builds onboarding plans for new hires: a pre-start checklist (accounts, equipment, buddy), day-one and first-week schedules, and 30/60/90-day goals. Works in plain chat; with an HRIS, knowledge base or calendar connected it pulls in team info and books day-one events. Official from Anthropic.

Builds structured interview kits for a role: behavioral and situational questions by competency, follow-up probes, a 1 to 4 scoring rubric and a debrief template, so interviewers assess candidates against the same bar. Part of Anthropic's official human-resources plugin.