Write, fix, or review the browser journeys in tests/stand/ui/ — Playwright (Python, sync API) against a deployed Insight stand with a real Keycloak sign-in. Covers the governing UI-vs-API rule and how to justify a browser test in writing, accessibility-first locators, the page-object/flows split, manifest-derived expectations, URL/deep-link validation, and real browser downloads. Use for any request to write, add, fix or review a committed browser test in this repository — 'add a Playwright test for X', 'the UI test is failing', 'turn this scenario into a browser journey', 'add a deep-link or download regression' — and for anything under tests/stand/ui/. For HTTP contract tests use stand-api-test; playwright-cli is for driving a browser interactively at a prompt and for Playwright's own CLI — reach for it only when nothing will be committed under tests/stand/ui/; drive-ui is for looking at a stand by hand.

Automate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.

Automate ClickUp project management including tasks, spaces, folders, lists, comments, and team operations via Rube MCP (Composio). Always search tools first for current schemas.

Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.

Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says \"robotics idea discovery\", \"机器人找idea\", \"embodied AI idea\", \"机器人方向探索\", \"sim2real 选题\", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.

This skill should be used when the user asks to "search memory", "what do you remember about X", "check claude-mem", "mem search", "find past observations", "what did we do last session", or wants prior-session context about a project, decision, file, or task. Searches the user's Claude-Mem (cmem.ai) memory.

Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text for prerecorded or live transcription. Covers `ClientFactory.CreateListenRESTClient()` with `TranscribeUrl` / `TranscribeFile`, and `ClientFactory.CreateListenWebSocketClient()` with `Connect`, `Subscribe`, and `Send`. Use `deepgram-dotnet-audio-intelligence` for summaries/sentiment/topics overlays, `deepgram-dotnet-conversational-stt` for Flux-specific work, and `deepgram-dotnet-voice-agent` for full-duplex assistants.

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 Java code in this repo that builds an interactive voice agent over `agent.deepgram.com/v1/agent/converse`. Covers `client.agent().v1().v1WebSocket()`, `AgentV1Settings`, `sendSettings`, `sendMedia`, event handlers, provider configuration, and message injection. Use `deepgram-java-text-to-speech` for one-way synthesis or the STT skills for transcription-only flows. Triggers include "voice agent", "agent converse", "full duplex", "barge in", "function call", and "agent websocket".

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 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".

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

Capture frames or clips from RTSP/ONVIF cameras.

Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.

Operate, inspect, and optimize the Daily SHITRAT loop. Use when running Daily SHITRAT, reviewing a Daily SHITRAT attempt, doing a Daily SHITRAT Dream/optimizer pass, checking brain daily artifacts, fixing report/Discord metadata, or preparing ShitRat-authored PR plans.

Contribute fixes, bug reports, and upstream discussions to badlogic/pi-mono without wasting maintainer time. Use when filing pi issues, preparing pi PRs, debugging whether a bug belongs upstream, or responding to maintainer pushback. Triggers on: 'contribute to pi', 'pi-mono issue', 'upstream pi fix', 'open a pi issue', 'why did Mario reject this', or any work in ~/Code/badlogic/pi-mono meant for upstream.

Diagnose gateway failures by reading daemon logs, session transcripts, Redis state, and OTEL telemetry. Full Telegram path triage: daemon process → Redis channel → command queue → pi session → model API → Telegram delivery. Use when: 'gateway broken', 'telegram not working', 'why is gateway down', 'gateway not responding', 'check gateway logs', 'what happened to gateway', 'gateway diagnose', 'gateway errors', 'review gateway logs', 'fallback activated', 'gateway stuck', or any request to understand why the gateway failed. Distinct from the gateway skill (operations) — this skill is diagnostic.