ワンクリックで
wire-pipecat-processor
Step-by-step workflow for designing and wiring a new FrameProcessor into the ORBIS pipecat pipeline in app.py
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Step-by-step workflow for designing and wiring a new FrameProcessor into the ORBIS pipecat pipeline in app.py
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Full clean rebuild of ORBIS — wipes web/dist, dist-sdist, src-tauri bundle, staged sidecar binary, pyapp env cache, WKWebView state, sidecar.log, and stale unix sockets, then rebuilds frontend → sdist → pyapp sidecar → tauri bundle in the correct order, and launches with stderr captured. Use when voice doesn't work, the orb shows weird state, "Load failed" appears anywhere in the UI, or anything feels off after a code change.
Step-by-step workflow for adding a new processing component to the ORBIS agent pipeline
Step-by-step workflow for integrating a new stage into the ORBIS audio/processing pipeline
Integrate a new ML component (classifier, reranker, etc.) into an existing agent pipeline by reading the codebase, identifying hook points, implementing the module, and wiring it in.
Commit pending changes, bump the patch version tag, and publish a beta release
Scaffold and plan a new marketing site — branding audit, stack selection, hero design, and deployment config
| name | wire-pipecat-processor |
| description | Step-by-step workflow for designing and wiring a new FrameProcessor into the ORBIS pipecat pipeline in app.py |
Use this when adding a new FrameProcessor (or subclass) to the ORBIS pipeline — e.g., intent routers, filters, interceptors. Covers design, placement, import wiring, and closure-ordering pitfalls.
audio_tags and user_agg, before LLM, after STT). Verify no existing pipecat hook (like before_generate) already covers the need.FrameProcessor (not a thin wrapper). Override process_frame and handle both the target frame type and passthrough for all others.app.py — Add the import for the new processor class at the top of app.py.run_bot — Instantiate the processor in the run_bot function, after all dependencies it needs (tools schema, session delegates, skill config, etc.) are available.task (or other objects created after the pipeline), confirm the callback is an async closure that captures by reference — it will resolve correctly at call time even if task is assigned later.IntentRouterProcessor between audio_tags and user_agg to intercept TranscriptionFrame before it reaches the LLM aggregator. Its _command_bypass_handler can safely reference task via closure even though task is created after pipeline construction.FrameProcessor between the transport input and audio_tags to drop frames below an energy threshold before any downstream processing.