“openai api”的搜索结果

OpenAI API (developers.openai.com) の画像生成・画像入力リファレンス。 GPT Image 2.5 (`gpt-image-2.5-sunburst` / `flare`), Images API `images.generate` / `images.edit`, mask, reference images, quality xhigh / max, image prompting, image_generation tool (Responses API), vision (画像入力, detail, image tokens, cost calculator, vision fine-tuning)。 Sora 2 / Videos API は 2026-09-24 終了 (履歴のみ)。

中文简介正在准备中。当前显示原文说明。

OpenAI API (developers.openai.com) の Responses API リファレンス。 text generation, embeddings, gpt-6-astra / gpt-6.1-sol / gpt-6-luna, structured outputs, streaming, function calling, programmatic / async tool calling, conversation state, prompt caching, prompt cache diagnostics, reasoning (configuration_update), background mode, compaction, multi-agent, WebSocket mode (mid-turn steering, stream_id), webhooks, error codes, rate limits, Realtime server controls, 公式 SDK (Python / JS / .NET / Java / Go / Ruby), openai CLI, Chat Completions / Assistants 移行, deprecations。

中文简介正在准备中。当前显示原文说明。

将人物、风景和商品构想整理成包含画风、构图、光线与颜色的指令，并通过 Python 脚本生成图片。支持多张参考图引导外观与构图，也可指定宽高比。

• 按服装、年代和外观生成人物图片
• 按氛围、天气和光线生成风景
• 按材质和拍摄角度生成商品图片

Set up Langfuse to record LLM application activity, costs, and response times. Manage prompt versions, organize evaluation datasets, and compare results to investigate failures and guide improvements using recorded evidence.

中文简介正在准备中。当前显示英语简介。

• Investigating failures in LLM applications
• Comparing prompt versions and evaluation scores
• Monitoring LLM costs and response times

Set up cognee and run a first Python example that stores information and retrieves it with a question. Covers virtual environments, API key configuration, optional packages, and basic troubleshooting.

中文简介正在准备中。当前显示英语简介。

• Installing cognee in a new Python environment
• Trying a minimal example that stores and retrieves information
• Separating stored information by project

Let a NanoClaw container agent call local models running in Atomic Chat. The skill adds an MCP server, a connection that exposes model listing and text generation as tools, while Claude continues to coordinate the work.

中文简介正在准备中。当前显示英语简介。

• Delegate part of Claude's work to a local model
• List models available in Atomic Chat
• Generate an answer with a specified local model

Compare SDK implementation with English documentation to find missing features, incorrect defaults, and outdated behavior descriptions. Report evidence and suggested locations, or make requested updates while keeping navigation consistent and following the repository’s documentation checks.

中文简介正在准备中。当前显示英语简介。

• Auditing documentation for a specific SDK feature
• Updating English docs after implementation changes
• Correcting outdated settings and default values

Compare a Python SDK release plan or candidate with the previous release to assess compatibility, versioning, and proven regressions. Produce a ship-or-block recommendation, documentation handoff, and key changes for minor releases.

中文简介正在准备中。当前显示英语简介。

• Plan the next patch or minor SDK release
• Assess whether a release candidate can ship
• Check compatibility and migration paths

Plan SDK behavior changes by defining required outcomes, compatibility boundaries, and unsupported cases. Reuse existing implementation paths, assess review feedback, and reconsider designs when repeated fixes introduce complexity beyond the original requirement.

中文简介正在准备中。当前显示英语简介。

• Define the scope of an SDK behavior change
• Assess compatibility with released APIs
• Reconsider a design after repeated review findings

Generate photos, illustrations, product mockups, and other bitmap images, or edit existing pictures with background changes, object removal, and transparent cutouts. Use reference images to guide variations and save selected assets for the project.

中文简介正在准备中。当前显示英语简介。

• Create a website hero image or illustration
• Replace a product photo background or remove objects
• Make a transparent cutout

Work with Linear issues through Symphony’s authenticated client. Retrieve issue details, update workflow states, create or edit comments, link GitHub pull requests, and upload videos using GraphQL, an API language for requesting specific data.

中文简介正在准备中。当前显示英语简介。

• Retrieve Linear issue details
• Create or edit issue comments
• Change an issue's workflow state

Generate images from text or reference images using multiple image services. Choose aspect ratios, sizes, and quality settings, or generate a collection of images in batches from saved prompt files.

中文简介正在准备中。当前显示英语简介。

• Create illustrations from text descriptions
• Change scenes using reference images
• Generate images in specific aspect ratios

Retrieve focused genome, assembly, and taxonomy metadata from NCBI Datasets v2, a biological data service. Get concise Markdown summaries by default, with raw JSON or text available when requested.

中文简介正在准备中。当前显示英语简介。

• Checking genome metadata for a specific organism
• Looking up an assembly by its accession identifier
• Checking taxonomy information by taxon ID

Retrieve concise metadata for preprints, papers shared before formal publication, from bioRxiv and medRxiv. Look up records by date range or DOI, check links to published papers, and save full responses when needed.

中文简介正在准备中。当前显示英语简介。

• Review preprint metadata for a specified date range
• Look up a preprint by DOI
• Check a preprint's link to a published paper

Retrieve concise summaries from GWAS Catalog, a resource for studies linking genetic variants to traits. Look up studies, associations, genes, variants, and publications, with JSON output or saved full responses when needed.

中文简介正在准备中。当前显示英语简介。

• Finding GWAS studies related to asthma
• Checking associations mapped to BRCA1
• Looking up genetic variants and related publications

Query EpiGraphDB for trait classifications, related literature, genetic evidence, and gene–drug relationships. Get concise summaries with limited result counts, or save the complete response when you need the underlying data.

中文简介正在准备中。当前显示英语简介。

• Find ontology terms for a disease or trait
• Look up drugs associated with a gene
• Summarize literature and genetic evidence

Build browser-based 3D games with Three.js, TypeScript, and Vite. Structure scene and camera control, model loading, physics, and interface overlays separately from game rules, with guidance for WebGL rendering diagnostics and performance.

中文简介正在准备中。当前显示英语简介。

• Build a browser-based 3D exploration demo
• Prototype vehicle movement or character traversal
• Load GLB models and integrate Rapier physics

Create editable FigJam diagrams for workflows, system architecture, data relationships, and schedules. The skill selects a suitable diagram type and guides Mermaid, a text format for diagrams, while accounting for rendering limits.

中文简介正在准备中。当前显示英语简介。

• Visualizing a workflow or decision tree
• Mapping services and data stores
• Showing API interactions over time

Build remote MCP servers, which let AI agents call external tools, on Cloudflare Workers. This skill covers server code, tool definitions, OAuth authentication, local testing, deployment, and connecting a Codex client.

中文简介正在准备中。当前显示英语简介。

• Building a remote MCP server
• Adding OAuth authentication to MCP tools
• Exposing external APIs as tools for AI agents

Define the scope of SDK behavior changes, including required behavior, compatibility obligations, unsupported cases, and existing alternatives. Guide implementation toward existing code paths, and reassess the design when review feedback introduces repeated complexity or expands supported behavior.

中文简介正在准备中。当前显示英语简介。

• Define the supported scope before changing SDK behavior
• Assess compatibility with released APIs and saved data
• Revisit a design as review findings accumulate

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.

中文简介正在准备中。当前显示原文说明。

Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a provider, use nanobanana-skill instead. Do NOT use for diagrams (架构图/流程图) — draw those with Mermaid or code.

中文简介正在准备中。当前显示原文说明。

Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.

中文简介正在准备中。当前显示原文说明。

Speech-to-text transcription via OpenAI Whisper. Supports two modes — Local CLI (no API key, runs on-device) and Cloud API (fast, scalable, requires OPENAI_API_KEY). Use when the user needs to transcribe audio files, translate speech, or convert audio to text.

中文简介正在准备中。当前显示原文说明。