도구

Finance plugin: ratio analysis, DCF valuation, budget variance, revenue and cash-flow forecasts, SaaS metrics like ARR, churn, LTV and CAC, and peer-comparison fundamentals for US and Indian listed companies. Includes Python scripts. Not investment advice; needs professional review.

Financial research terminal agent, like Claude Code for finance: breaks company research questions into steps, pulls financial statements and market data, and self-checks before answering. Needs Bun, a model API key and a Financial Datasets API key; for learning and research only.

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

Distills a colleague, friend or public figure's chats, documents and public material into a persona profile packaged as a callable skill, for handoffs and preserving know-how. Collects material from Lark, DingTalk, Slack and more. Mind privacy and consent when using others' data.

Google's official skill library and plugin marketplace: nearly 150 skills focused on Google Cloud (GKE, BigQuery, Cloud Run, IAM and more), plus 17 product plugins pairing skills with MCP for Cloud SQL, Spanner, AlloyDB, BigQuery, GCS and others.

Manages BigQuery datasets, tables and jobs with the bq and gcloud CLIs, runs SQL queries and loads data, with references for client libraries, MCP and Terraform. Google's official skill; requires a Google Cloud project.

Google's official skill library, focused on Google Cloud: 100+ skills for gcloud, Cloud Run, GKE, BigQuery, IAM, monitoring and logging, and the Well-Architected Framework, plus Ads and Analytics.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

AI2's tool for converting PDFs and scans to Markdown with a vision LLM, handling equations, tables, handwriting and multi-column layouts, suited to bulk digitizing papers and archives. Local runs need an NVIDIA GPU with 12GB+ VRAM; otherwise use a paid OpenAI-compatible remote endpoint.

Lets Claude Code push ML research forward unattended: literature review, topic selection, experiment deployment, cross-model review loops and paper writing through rebuttal, in 80+ skills. Codex acts as the independent reviewer by default; other model pairings work too.

Browser control from the browser-use team: an editable CDP connection lets agents drive the Chrome you are already using, writing missing helper functions as they go and keeping them for reuse. Also offers an MCP server. Allow remote debugging in Chrome on first use.

Context and harness engineering skills: context fundamentals, degradation diagnosis and compression, multi-agent architectures, memory systems, tool design, LLM-as-judge evaluation and self-improvement loops. Focused on principles and design patterns, not tied to any agent platform.

Context and harness engineering skills covering context compression and optimization, multi-agent architectures, memory systems, tool design and LLM-as-judge evaluation, activated automatically by task. Aimed at building production-grade agent systems.

Official Lark (Feishu) skill to create and edit Lark Sheets: formulas, charts and pivot tables, conditional formatting and filters, plus import and export of local Excel/CSV, for summaries, budgets and reports. Needs lark-cli on a machine with Node.js, plus app setup and authorization.

Official Lark (Feishu) CLI with 200+ commands for messages, docs, Base, Sheets, calendar, mail, approvals, OKRs, meetings and Minutes, plus 20+ bundled lark-* agent skills and structured output. Create a Lark app and sign in first.

Official Lark (Feishu) OKR skill: view OKR cycles, create and edit objectives and key results, update quantitative progress and notes, and adjust alignment, order and weights to drive team goals (no performance reviews). Needs lark-cli and authorization.

Official Lark (Feishu) skill for Lark Base: create tables, add fields, add and edit records, build views, forms and dashboards, or apply ready-made templates, good for sign-ups, asset registers and trackers. Needs lark-cli on a machine with Node.js, plus app setup and authorization.

Official Lark (Feishu) approval skill: list pending, handled and submitted approvals; approve, reject, transfer, return, remind or withdraw; and find and submit native approvals such as leave or expense requests. Needs lark-cli with app setup and sign-in authorization.

Official Lark (Feishu) skill: view and search events, create or edit meetings and invite attendees, check colleagues' availability and suggest free slots, and book meeting rooms. Needs lark-cli on a machine with Node.js, plus app setup and authorization.

The 20+ skills that ship with the official Lark (Feishu) lark-cli, covering messages, docs, Base, Sheets, calendar, mail, tasks, approvals and meeting notes. Install lark-cli and complete app setup and authorization first.

Alibaba's open-source offline data sync tool: JSON job configs batch-sync between heterogeneous sources like MySQL, Oracle, PostgreSQL, Hive, HDFS and MaxCompute, run with python datax.py. Needs JDK 1.8+ and Python; download and unpack the official toolkit.

Lets agents call thousands of ready-made scrapers and automation Actors from Apify Store to pull data from social media, search engines, maps, e-commerce sites and more. Maintained by Apify; needs an Apify account (OAuth) or API token.

ModelScope's official training framework for LLMs and multimodal models: the swift command covers pretraining, fine-tuning, RL, inference, evaluation, quantization and deployment for 600+ text and 400+ multimodal models, with Megatron parallelism and a web UI. Usually needs a GPU.

Version datasets and models the way Git versions code: data lives in remote storage like S3 or GCS while versions are tracked in your Git repo. Also offers reproducible pipelines and local experiment tracking, rerunning only the steps affected by a change.