Iterate on a GitHub PR until latest-head checks are green or a precise blocker is named. Use when a PR still has failing or pending checks after review fixes, including after greploop.

Produce a maintainer-grade PR or contribution report as HTML or Markdown. Use when asked to deeply review a PR, explain a design, compare systems, or prepare a merge recommendation.

Use this skill when the user requests to generate, create, compose, or produce music or songs — background music, theme songs, jingles, or instrumental tracks. Generates a song from a style/mood prompt and optional lyrics via the MiniMax music API.

Use when writing or reviewing Python code in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, entity detection. Same endpoint as plain STT but with analytics params. Covers both REST (`client.listen.v1.media.transcribe_url`/`transcribe_file`) and the WSS-supported subset (`client.listen.v1.connect`). Use `deepgram-python-speech-to-text` for plain transcription, `deepgram-python-text-intelligence` for analytics on already-transcribed text. Triggers include "diarize", "summarize audio", "sentiment from audio", "redact PII", "topic detection audio", "audio intelligence", "detect language audio".

Use when writing or reviewing C# code in this repo that enables Deepgram intelligence overlays on Speech-to-Text requests. Covers `PreRecordedSchema` analytics flags such as `Summarize`, `Topics`, `Intents`, `Sentiment`, `DetectLanguage`, `DetectEntities`, `Diarize`, and `Redact`, plus the smaller live-streaming subset on `LiveSchema`. Use `deepgram-dotnet-speech-to-text` for plain transcription and `deepgram-dotnet-text-intelligence` for analytics on already-transcribed text.

Use when writing or reviewing C# code in this repo that calls Deepgram Text Intelligence / Read (`/read`) for sentiment, summarization, topic detection, and intent recognition on text or hosted text URLs. Covers `ClientFactory.CreateAnalyzeClient()` with `AnalyzeText`, `AnalyzeUrl`, and `AnalyzeFile`. Use `deepgram-dotnet-audio-intelligence` when the source is audio instead of text.

Use when writing or reviewing Go code in this repo that works with Deepgram management endpoints for projects, keys, members, scopes, invitations, usage, balances, or models. Route live voice runtime to deepgram-go-voice-agent and repo workflow questions to deepgram-go-maintaining-sdk.

Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST (`client.speak.v1.audio.generate`) and streaming WebSocket (`client.speak.v1.connect`). Also covers the in-repo `deepgram.helpers.TextBuilder` for incremental text assembly before synthesis. Use `deepgram-python-voice-agent` when you need full-duplex STT + LLM + TTS with barge-in. Triggers include "TTS", "speak", "synthesize voice", "aura", "text to speech", "speak.v1", "TextBuilder".

Use when writing or reviewing Java code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for text analysis. Covers `client.read().v1().text().analyze(...)` with `ReadV1Request` or `TextAnalyzeRequest`. Use `deepgram-java-audio-intelligence` when the source is audio instead of text. Triggers include "read api", "text intelligence", "analyze text", "sentiment", "topics", "intents", and "summarize text".

Use when writing or reviewing Java code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via `client.speak().v1().audio().generate(...)` and streaming synthesis via `client.speak().v1().v1WebSocket()`. Use `deepgram-java-voice-agent` for full-duplex assistants instead of one-way synthesis. Triggers include "tts", "text to speech", "speak", "aura", "streaming tts", and "speak websocket".

Use when writing or reviewing Java code in this repo that calls Deepgram Management APIs for projects, project models, API keys, members, invites, usage, and billing. Covers `client.manage().v1().*` plus related think-model discovery under `client.agent().v1().settings().think().models()`. Use `deepgram-java-voice-agent` for live agent conversations instead of admin APIs. Triggers include "management api", "list projects", "api keys", "members", "invites", "usage", "billing", and "models".

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribeUrl` / `transcribeFile` (REST) plus `client.listen.v1.createConnection()` / `connect()` (WebSocket). Use `deepgram-js-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-js-conversational-stt` for Flux turn-taking on `/v2/listen`, and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "transcribe", "speech to text", "STT", "listen.v1", "nova-3", "live transcription", and "websocket transcription".

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.createConnection()` / `connect()`, Flux models, and turn events like `TurnInfo`. Use `deepgram-js-speech-to-text` for standard v1 ASR and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", and "listen.v2".

Coordinates optimization attempts. Captures baselines, implements changes, invokes review, and records outcomes.

Onboarding and first-run for RuView (WiFi-DensePose) — Docker demo with simulated data, repo build, and the fastest path to a live sensing dashboard. Use when someone is new to RuView or wants the shortest path to "it works on my machine".

ESP32-S3 / ESP32-C6 firmware build, flash, WiFi provisioning, and serial monitoring for RuView CSI sensing nodes. Use when setting up physical hardware, reflashing a node, or debugging a device that isn't streaming CSI.

Evaluate a PR's title and description against its actual implementation, then iteratively suggest and apply updates. Use when the user asks to check, fix, or update a PR title or description.

Use when the user asks Claude Code to read or write Odysseus data (todos, email, calendar, memory, documents) or to launch/monitor/stop a Cookbook model-serve task through the scoped Claude Agent API. Requires ODYSSEUS_URL and ODYSSEUS_API_TOKEN.

Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is complete, what the next release step is, or to continue a release paused for human approval.