Menu
Wire a new FrameProcessor into ORBIS's pipecat pipeline at the correct hook point
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
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 | pipecat-frame-processor-integration |
| description | Wire a new FrameProcessor into ORBIS's pipecat pipeline at the correct hook point |
Use this when adding a new processing stage to the ORBIS voice pipeline — e.g. intent classification, content filtering, transcription transformation — that needs to intercept frames between existing pipeline stages.
audio_tags and user_agg (i.e. after transcription frames exist but before the LLM user aggregator consumes them). For post-LLM work, hook after the LLM service.agent/intent.py). Override process_frame: inspect the frame type (e.g. TranscriptionFrame), perform the logic, then either pass the frame downstream via await self.push_frame(frame) or swallow/replace it.app.py — Insert the processor instance into the pipeline tuple/list in the correct position. Order matters: place it between the two stages identified in step 1. Confirm the processor receives the expected frame types by checking adjacent stage outputs.audio_tags and user_agg. Reads TranscriptionFrame, classifies intent, optionally injects a SystemFrame or routes to a different handler before passing the frame along.user_agg and llm. Reads LLMMessagesFrame, redacts sensitive content, then pushes the sanitized frame downstream.