Инструменты

Finance and accounting plugin: prepares journal entries, reconciles accounts, generates income statements, runs variance analysis, manages month-end close and supports SOX audit testing. Can pull data from ERPs and data warehouses. Official from Anthropic.

Account reconciliation following accounting methodology: GL to subledger, bank reconciliations and intercompany balances, with reconciling items categorized, aged and escalated. Part of Anthropic's official finance plugin; results need professional review.

Helps accountants prepare month-end journal entries: debit/credit treatment for accruals, prepaid amortization, depreciation, payroll and revenue recognition, plus required support and review checklists, following US GAAP. Not financial advice; review before posting. From Anthropic's finance plugin.

Month-end reconciliation for small businesses: matches QuickBooks or Xero line by line against PayPal, Stripe and Shopify payouts, flags likely duplicates and missing receipts, explains the P&L in plain terms and exports a close package (Excel and PDF). CSVs work too. Official from Anthropic.

Produces monthly, quarterly or annual income statements with prior-period, year-over-year and budget comparisons, flagging material variances. Includes balance sheet and cash flow formats plus GAAP presentation and period-end adjustment references. From Anthropic's finance plugin; get it reviewed.

Checks hours before payroll for US small businesses: totals regular time, overtime and PTO from Gusto, QuickBooks Payroll or timesheets, and flags missed punches, overtime anomalies, rate changes and mid-period hires or exits. Prepares only, never runs payroll. Official from Anthropic.

Helps finance teams run month-end close: a close checklist sequenced from T+1 to T+5, task dependencies and critical path, a progress tracker and tips to shorten the close, useful for close calendars and status tracking. Needs professional review. Part of Anthropic's official finance plugin.

Compensation analysis for HR and managers: market pay percentiles by role, level and location, offer competitiveness checks and equity modeling; upload a pay sheet to find employees outside their band and flight risks. Without a comp data source it uses public web data, so verify. By Anthropic.

Adds a workflow layer to OpenAI's Codex CLI: requirement clarification, plan review, persistent goals, parallel multi-agent teams and tmux session management, with project state in .omx/ and a bundled Codex plugin. Community project; needs a signed-in Codex CLI, macOS or Linux recommended.

Vercel's official deployment skill: checks the git remote, project link and CLI login, then deploys a preview (default) or production via git push or vercel deploy. When login isn't possible in a sandbox, it can create a claimable preview link.

React and Next.js performance rules from Vercel's engineering team: 70 rules ranked by impact covering request waterfalls, bundle size, server performance and re-renders, for writing, reviewing and refactoring. Maintained by Vercel.

Vercel's guide to React composition patterns: replaces boolean prop sprawl with compound components, lifted state and clean Context interfaces, including React 19 API changes. Useful for refactoring component libraries and reviewing component architecture.

Vercel's official skill that pulls the 80+ rules of Vercel's writing handbook online to review docs and copy for voice, structure, content types, code examples and formatting, listing issues as file:line.

Vercel's official cost and performance skill: gathers production metrics, usage and project config, investigates only the routes and files the metrics point to, and returns ranked, doc-backed recommendations. Supports Next.js, SvelteKit and Nuxt; needs Vercel CLI v53+ logged in and linked.

Daemonless, rootless container and pod manager with a Docker-compatible CLI for building, running and pushing OCI images. On macOS and Windows it runs inside a podman machine VM.

Installs ready-made subagents, slash commands, hooks, MCP configs and skills for Claude Code with one npx command, browsable online at aitmpl.com. Also includes session analytics, health checks and other helpers.

Runs the cognee memory engine as an MCP server whose remember, recall and forget tools write documents and conversations into a knowledge graph and vector store for cross-session retrieval. Start it with Docker or uv first; needs an LLM API key by default, or connect to Cognee Cloud.

Runs commands and scripts in a sandbox, indexes large tool outputs for full-text search and returns only results to the context window to save tokens; after compaction it can retrieve edits and task state. Supports Claude Code, Codex and more. Needs Node.js 22.5+.

Processes large tool outputs in a sandbox and returns only the results to context; logs session events in SQLite with FTS5 so work continues after context compaction. Supports Claude Code, Codex and a dozen other clients. ELv2 licensed.

Office command-line tool built for AI agents: a single binary that creates, reads and edits Word, Excel and PowerPoint files without Office installed, and renders them to HTML or PNG so agents can check the layout.

Fast vulnerability scanner driven by YAML templates: uses a community template library to detect known vulnerabilities over HTTP, DNS, TCP, SSL and more, supports custom templates and plugs into CI/CD. Use only on targets you're authorized to test.

Writes conversations and business data into Graphiti's temporal knowledge graph so agents can retrieve long-term memory by entity, fact and time. Open source from Zep; start FalkorDB or Neo4j and the server with Docker first, and configure an LLM API key.

Grafana's load and performance testing tool: write test scripts in JavaScript covering HTTP, WebSocket, gRPC and browsers, set threshold assertions and run them in CI.

Official web auditing tool from the Google Chrome team: score pages on performance, accessibility, best practices and SEO from the command line and get HTML, JSON or CSV reports, so agents can iterate on a page. Needs Node 22+ and Chrome.