도구

Connects to the Arize Phoenix observability platform so agents can query LLM traces and sessions, manage prompts, browse datasets and read experiment evaluation results. Maintained by Arize; needs a self-hosted or cloud Phoenix instance.

ByteDance's open-source, general software engineering agent: trae-cli edits files and runs commands from natural language, supports multiple model providers and MCP, and records full execution trajectories. Transparent design suits agent research and customization. Needs your own model API key.

Scans files and directories for personal data such as names, emails and credit card numbers using Presidio Analyzer, with configurable entity types, confidence thresholds and ignore rules. Needs Python 3.10+ and a spaCy language model.

Lets agents operate the Windows desktop directly: launch apps, switch windows, simulate keyboard and mouse, read UI elements and run PowerShell, without needing a vision model. Windows only.

Google's official dependency vulnerability scanner: parses project lockfiles and container images, checks them against the OSV.dev database to find affected dependencies, and can suggest upgrade fixes (experimental).

Hugging Face's official skills: manage Hub models and datasets with the hf CLI, fine-tune language and vision models, run model evaluations, and build Gradio apps deployed to Spaces. Needs an HF account; cloud training on HF Jobs requires a paid plan.

Teaches agents the Hugging Face Hub CLI hf: search and download models, manage datasets, Spaces, Buckets and repos, and run Jobs and inference endpoints. The skill content is generated from your local CLI, so install hf first. Maintained by Hugging Face.

Lets agents fine-tune language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, supporting SFT, DPO, GRPO and reward models, and convert results to GGUF for local use. Requires an HF Pro or higher paid plan. Maintained by Hugging Face.

Lets agents work with the Hugging Face Hub through the hf CLI: search and download models and datasets, manage repos and Spaces, and run training and evaluation jobs on cloud GPUs, with more workflow skills installable as needed. Maintained by Hugging Face.

The official MCP debugging tool: connect to any MCP server through a web UI, CLI or terminal UI to list and call its tools, resources and prompts. CLI mode outputs JSON, suited to scripts and CI smoke tests.

Lets agents control iOS and Android simulators and real devices: reads the accessibility tree first and falls back to screenshot coordinates, and can swipe, install and uninstall apps, record the screen and read device logs. Requires Xcode or Android platform tools.

Tencent's open-source browser bridge: through the bsk CLI and a Chrome/Edge extension, agents use your logged-in accounts in a separate visible window to browse, fill forms and take full-page screenshots, and correlate network requests with console output to debug sites.

Open-source research agent: one command runs literature reviews, deep research, paper reviews, paper-code consistency checks and replication plans, searching arXiv, PubMed and more with sources recorded. Good for grad students writing reviews. Run feynman setup to sign in to a model provider.

NVIDIA's open-source LLM vulnerability scanner that probes for prompt injection, jailbreaks, data leakage, hallucination and harmful content, supporting OpenAI, Hugging Face, Bedrock and most REST-accessible models. Scanning cloud models needs their API keys.

Privacy compliance plugin: decides whether processing activities need a PIA or DPIA, generates privacy impact assessments, reviews DPAs from the controller or processor side, and drafts DSAR responses within statutory deadlines. Official from Anthropic.

Anthropic's official AI governance plugin: tiers AI use cases against your internal register, runs impact assessments across applicable laws such as the EU AI Act, reviews vendor AI terms for training-data and liability risk, and periodically checks for drift between AI policy and practice.

NetEase's open-source cross-platform UI automation framework: locates elements by image recognition to automate games and apps on Android, iOS and Windows without touching their code. airtest run executes cases and airtest report builds HTML reports.

High-accuracy retrieval-augmented Q&A over paper PDFs, text and Office documents, filling in citation metadata, checking retractions and attaching traceable sources to answers. Provides the pqa CLI and a Python library. Needs an LLM API key by default; local models can be configured.

Say build a harness for this project and it designs a domain-specific agent team, generating subagent definitions, companion skills and orchestration, validates them and keeps evolving them from feedback. Supports workflow orchestration, persistent agent teams and subagent delegation.

Static scanner for security and compliance issues in Terraform, CloudFormation, Kubernetes, Helm, Dockerfiles and CI pipeline configs, with over a thousand built-in policies and hard-coded secret detection. Outputs SARIF, JSON and more. Maintained by Prisma Cloud.

Turns Peng Sida's public research-writing notes into a skill: revises abstracts, introductions, methods and experiments of ML/CV/NLP papers from a reviewer's view, checks that each claim has experimental evidence, and runs a pre-submission self-check. Pure methodology, no API key.

asc CLI for scripting the App Store Connect API: manage builds, TestFlight, metadata, signing and review submissions to automate iOS and macOS releases from the terminal or CI. Ships with a companion agent skill pack. Needs an App Store Connect API key.

Offline speech toolkit for Apple Silicon Macs: CLI text-to-speech (including Chinese and voice cloning) and speech-to-text, for voicing lessons and explainer videos or transcribing lectures and interviews, with data staying local. Needs an M-series Mac and Python 3.10+; MP3 export needs ffmpeg.

Trail of Bits static analysis skills: CodeQL for interprocedural taint tracking and data-flow analysis, Semgrep for rule-based scanning, plus parsing and deduplicating SARIF results. Requires CodeQL or Semgrep installed locally.