1.1K skills · sorted by relevance
Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.
Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.
Develop ChatGPT apps with interactive React widgets using mcp-use and OpenAI Apps SDK. Guidance covers app scope, server tools, shared state, and display settings. This skill is deprecated and points users to mcp-app-builder.
Guides development of ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK, covering server tools, React interfaces, and shared state. This skill is deprecated and directs users to mcp-app-builder.
Run Customgpt operations through Rube MCP, which connects your agent to external tools. The skill searches for available actions, checks connection status, and follows current input requirements when executing supported tasks.
Deploy FastGPT on your own server using its official installation script and Docker Compose, which runs its services together. Check service health and access, investigate deployment problems, and receive the access URL, initial login details, and next steps.
Run Customgpt operations through Rube MCP, which connects your agent to external tools. The skill searches for available actions, checks connection status, and follows current input requirements when executing supported tasks.
Build, refactor, and troubleshoot ChatGPT apps with an MCP server, which exposes tools to the assistant, and an interactive widget. Use official documentation and examples to plan tools, scaffold code, configure security settings, and validate local operation.
Plan ChatGPT advertising experiments and conversational ad concepts, or review performance using a verified data export. The skill helps assess campaigns without assuming that advertising inventory, account access, or particular platform features are available.
Use when the user mentions GPT Image 2.0 or GPT Image 2.5, gpt-image-2, gpt-image-2.5, gpt_image_2_5, GPT-Image-2 prompts, the Flare / Sunburst variants, a transparent-background image, or wants to generate an image with GPT Image 2.0 or 2.5. Covers when to prefer GPT Image 2.5 over 2.0 (transparent background, xhigh/max quality, extra aspect ratios — from platform and OpenAI facts), the CLI-vs-MCP disagreement on gpt_image_2, the three-format prompt taxonomy (Format A structured JSON for UI mockups and layout-dense images; Format B dense cinematic prose for single-subject scenes; Format C auto-derive meta-prompt for theme-only concepts), per-format craft patterns, output conventions, the 6-item pre-delivery checklist, and cross-surface workflow context (companion static-ads-workflow.md for ad recreation; higgsfield-marketing-studio cross-surface-workflow.md §3 for ms_image / DTC Ads Higgsfield-native alternative).
The English summary is being prepared. Showing the original description.
Research uncertain design choices, algorithms, or API usage through approved web searches or optional ChatGPT consultation. Get concise options with sources, with separate approval required before sending text externally and before implementing a chosen approach.
Manage mathematical proof projects across Codex runs, keeping sources, attempts, and unresolved steps organized. Prepare manual GPT Pro handoffs for difficult steps, then check returned arguments and edit the proof for clarity.
Manage mathematical proof work across separate runs, preserving sources, established results, and unresolved steps. Attempt and audit proofs locally, prepare focused manual GPT Pro handoffs when blocked, and check returned answers before producing a clearer final proof.
Create or improve GPT-Image2 image prompts using a style library. Select suitable templates, then specify composition, materials, text, aspect ratio, and unwanted details in a prompt ready to copy.
Integrate new FastGPT resources, such as AgentSkill or Plugin, with permission management. Choose an integration guide based on resource hierarchy and permission inheritance, locate the relevant code, and review a checklist for missing implementation steps.
Build and troubleshoot ChatGPT apps with an MCP server that exposes tools and an optional interactive widget. Use current official documentation and examples to create scaffolds, configure security settings, and guide local validation and deployment when requested.
Prepare a ChatGPT Apps submission JSON file by inspecting an MCP server, which exposes tools to AI agents. Generate app details, tool behavior justifications, and test cases, then report review findings and missing output schemas.
Build blockchain applications with ChainGPT APIs and SDKs. The skill guides chatbot integration, NFT image creation and minting, smart contract generation and auditing, and crypto news feeds, with starter templates and usage cost estimates.
Generate images, edit reference images, or redraw selected areas using GPT Image 2 or 2.5 through a packaged command-line tool. Resolve the model, image size, and quality settings, with reference examples available to guide the request.
Request an independent code review using GPT-6.1-Sol at Max reasoning through Codex and Cloudroom. Review the current environment, including uncommitted changes, and return the completed reviewer’s full response covering serious issues and readiness to merge.
Get guidance on Codex, OpenAI APIs, and ChatGPT Work using official documentation with citations. Use it to investigate settings and errors, compare models, plan migrations, or work on prompts and API integrations.
Connect a ChatGPT or Claude account to import conversation history into knowledge pages. Sync new and changed conversations incrementally, revisit recent history to catch updates, and optionally enable scheduled syncing.
Retire a FastGPT workflow node while preserving existing workflows. The skill guides changes to templates, execution handlers, and interface references so the node disappears from creation menus but still loads, runs, and displays a replacement notice.
Develop and review FastGPT APIs with consistent input and output checks, TypeScript types, and OpenAPI documentation. It guides the use of Zod schemas, definitions that describe and validate data, alongside permission checks and reusable structures.