Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

opper-ai

@opper-ai source repo

5 published skills

  1. ▌
    Opper · opper-ai
    Main entry point for working with Opper (https://opper.ai) — the AI gateway for agents, 300+ models through one EU-hosted gateway, GDPR-compliant. Use this skill whenever the user mentions Opper without naming a specific surface: "set up Opper", "try Opper", "build with Opper", "migrate to Opper", "help me with Opper". This skill scans the user's context to detect state (new user / existing integration / migration candidate) and API surface (compat / multimodal / realtime / CLI), proposes a concrete plan, then routes to the right sub-skill: `opper-cli` for terminal work, `opper-sdks` for Python/TypeScript code, `opper-api` for raw HTTP and platform concepts, or `opper-multimodal` for media generation (images, audio, video, OCR), files, and realtime voice. It owns the full lifecycle — explore, propose, guide, test, and follow-up tied to Opper's Control Plane (Route, Observe, Steer, Guard, Comply).
    0
    installs
  2. ▌
    Opper API · opper-ai bundle
    Use the Opper REST API directly (HTTP / curl / fetch) and as the source of truth for Opper platform concepts: the gateway, the control plane, available models, the OpenAI / Anthropic / Google / OpenResponses-compatible endpoints under /v3/compat, structured output, server-side tools (web search), roundtable, streaming via SSE, tracing, and migration from other LLM gateways. Use this skill whenever the user asks about Opper concepts, what models Opper supports, API endpoints or signatures, raw HTTP integration, gateway behaviour, integrating Opper with a coding assistant, or compatibility / migration from OpenAI / OpenRouter / Anthropic, or migrating off Opper's own legacy /v3/call (opper.call) — even if they only say "Opper" without "API". For media generation (images, audio, video, OCR), files, and realtime voice, use the `opper-multimodal` skill instead. For any endpoint signature or payload question always recommend fetching the live OpenAPI spec at https://api.opper.ai/v3/openapi.yaml first.
    0
    installs
  3. ▌
    Opper CLI · opper-ai
    Use the Opper CLI (`opper` command, npm package `@opperai/cli`) for terminal work with Opper: signing in, calling functions, managing knowledge bases (indexes), inspecting traces, tracking usage and costs, generating images, installing bundled skills, configuring AI code editors, and launching coding agents (Claude Code, OpenCode, Codex, Hermes, Pi) with their inference routed through Opper. Use this skill whenever the user mentions the `opper` command, the Opper CLI, opper-ai/cli, `@opperai/cli`, `opper launch`, or wants to do anything Opper-related from a terminal — even if they don't explicitly say "CLI". For exact arguments, always run `opper <subcommand> --help`; the help output is the authoritative reference.
    0
    installs
  4. ▌
    Opper Sdks · opper-ai bundle
    Use the unified Opper SDKs (`opperai` package for both Python and TypeScript, with built-in agent support) for AI task completion, structured output with Pydantic / Zod / JSON Schema, knowledge base semantic search, streaming, tracing, tool use, and multi-agent composition. Use this skill whenever the user is writing Python or TypeScript code that imports `opperai`, builds an Opper agent, needs to migrate code off the legacy `opper.call`, or asks how to do anything Opper-related in code — even if they don't explicitly name the SDK. Both languages live in one repo with parallel numbered examples; agents are part of the SDK, not a separate package.
    0
    installs
  5. ▌
    Opper Multimodal · opper-ai
    Use the Opper multimodal and realtime surfaces — everything beyond text. Covers media generation (images, audio speech / TTS, transcription / STT, video, OCR), the /v3/files storage API and file_id reuse, vision / PDF input on chat models, and realtime two-way voice / audio over WebSocket (wss://api.opper.ai/v3/realtime, browser tickets via /v3/realtime-sessions, function-scoped /v3/realtime/{name}). Use this skill whenever the user wants to generate or edit an image, do text-to-speech or speech-to-text, transcribe audio, generate video, run OCR on a PDF / image, upload or reuse media files, send images / PDFs to a model, or build a voice / realtime app on Opper — even if they only say "Opper". For text / chat, structured output, migration, and server-side tools like web_search, use the `opper-api` skill instead. For any endpoint signature or payload question, fetch the live OpenAPI spec at https://api.opper.ai/v3/openapi.yaml first.
    0
    installs