도구

Google's official skills for building ADK agents: dev workflow, scaffolding, the ADK Python API, evaluation with LLM judges and adaptive rubrics, deployment to Agent Runtime, Cloud Run or GKE, publishing and observability. Works with agents-cli; local dev needs only an AI Studio key.

Posit's open-source scientific and technical publishing system built on Pandoc: embed Python, R or Julia code in Markdown or Jupyter notebooks, then quarto render produces HTML, PDF, Word, slides, websites and books.

Semi-automated research workflow for computer science and AI researchers: ideation, Zotero literature management, experiment analysis and reports, paper writing and polishing, and rebuttals, with optional Obsidian knowledge base. 40+ skills; also installable as a Claude Code plugin.

Semi-automated research assistant for CS and AI researchers that links ideation, Zotero literature management, experiment analysis and reporting, paper writing and reviewer responses, and keeps project knowledge in Obsidian. Branches for Codex and other agents exist.

From the FinanceToolkit author: computes ratios, valuation, risk and macro indicators with 500+ transparent formulas, for company comparisons and first-pass due diligence. Hosted, no install; enter a Financial Modeling Prep key on first connect (free tier: US stocks, 5 years). Verify results.

Detects shot changes in video and splits long footage into scenes, exporting cut lists and per-scene thumbnails, useful for shot analysis, organizing footage and finding edit points. Runs locally; needs Python 3.10+, plus FFmpeg or mkvmerge for splitting.

LM Studio's official CLI: list, load and unload local models, start and stop the local API server, and check status and logs; ls, ps and other commands support --json output for scripts and agents. Requires the LM Studio desktop app.

CLI and TypeScript runtime for discovering and calling MCP servers from the terminal and scripts: list tool signatures and call tools directly, or generate a standalone CLI or typed client from a server. Auto-imports existing MCP configs from Claude Code, Codex and others.

Empirical social science skills from Stanford REAP and CoPaper.AI, bundling 77 in-house and third-party collections: topic selection, literature reviews, DID/RD/IV identification, regression tables in Python, Stata or R, robustness audits and paper writing. Stata flows need Stata installed.

Draws bar charts, histograms, line charts, scatter plots and box plots in the terminal from CSV/TSV on stdin, so you can glance at data distributions at the end of a shell pipeline. The command is uplot.

Teaches agents to code against the latest Gemini API and Python/TypeScript SDKs: multi-turn chat, function calling, structured output, and image and speech generation, while avoiding deprecated older models. Maintained by Google's Gemini team.

Gemini API development skills: gemini-api-dev (core API and SDKs), gemini-live-api-dev (real-time bidirectional audio/video streaming) and gemini-omni-flash-api (Omni video generation and editing), filling in APIs released after model training cutoffs. Maintained by Google's Gemini team.

Generates 26+ chart types with AntV, including line, bar, Sankey, word cloud, mind map and pivot table, returning image links. Officially maintained by Ant Group's AntV team; uses a public rendering service by default and can be self-hosted.

Create, read and modify xlsx workbooks without Microsoft Excel installed: formulas, formatting and conditional formatting, charts, pivot tables and tables. Runs locally over stdio or as a remote HTTP service.

Three.js lighting reference with code: ambient, hemisphere, directional, point, spot and area lights with their cost and shadow support, shadow setup, image-based environment lighting and lighting performance tips.

Three.js materials reference with code: when to use Basic, Lambert, Phong, Standard, Physical, Toon and other materials, PBR properties such as roughness and metalness, custom ShaderMaterial and material performance.

Three.js fundamentals with code: setting up the scene, cameras and WebGLRenderer, Object3D hierarchy, coordinate systems and transforms, the render loop and resize handling. A starting point for building a 3D scene on the web.

Three.js geometry reference with code: parameters for built-in shapes like boxes, spheres, cylinders and tori, building custom meshes from vertices with BufferGeometry, and instanced rendering for large numbers of objects.

Three.js interaction reference with code: raycasting for click detection and object selection, camera controls such as OrbitControls, and mouse and touch input handling for interactive 3D experiences.

Three.js asset loading reference with code: loading GLTF models, textures, images and HDR environments, coordinating loaders and progress with LoadingManager, and async loading patterns.

Three.js post-processing reference with code: chaining passes with EffectComposer, adding bloom, depth of field, color grading, blur and glow, and writing custom screen-space shader passes.

Three.js shader reference with code: writing GLSL vertex and fragment shaders, ShaderMaterial versus RawShaderMaterial, uniforms and animating them, and extending built-in materials for custom visual effects.

Three.js texture reference with code: loading and configuring texture maps, UV mapping, cubemaps and HDR environment maps, texture settings and optimization.

Three.js animation reference with code: procedural motion with Clock, the AnimationClip, AnimationMixer and AnimationAction keyframe system, playing GLTF animations, skeletal animation, morph targets and blending multiple animations.