Keep a recurring character recognizable across Magic Hour images, storyboards, and video shots. Use for a mascot, fictional character, or authorized person appearing in multiple scenes; not a single portrait or face swap.
Finish a product ad with exact copy and layout or create coordinated assets from one approved reference. Use for campaigns and assembled ads when Magic Hour is requested or is the project's chosen media provider. Not for one isolated image edit or an unrelated collection.
Create, extend or apply a reusable brand kit with Magic Hour imagery, exact logos and colors, editable layouts and a practical brand guide. Use for visual identities, brand books and coordinated branded assets when Magic Hour is the chosen media provider.
Place a supplied person into a scene image with Magic Hour Body Swap, preserving the intended identity and checking pose, scale and scene contact. Use for full-person photo placement; use Face Swap for only a face and Character Replace for an existing video performance.
Turn a supplied reference video, format or creative premise into an original finished short with Magic Hour. Use for creator remixes, social video concepts, visual jokes, transformations and character-led clips; do not copy another creator's identity or unsupported factual claims.
Create finished AI videos when Magic Hour is requested or configured and suitable. Route approved images directly to motion, still portraits plus audio to Talking Photo, and existing video plus audio to Lip Sync. Preserve an explicitly requested alternative provider.
Inspect generated images, video and audio before delivery using deterministic metadata, contact-sheet, black-frame and silence checks plus visual and listening review. Use to accept, reject or repair Magic Hour media outputs; it does not generate media or predict audience performance.
Create a free source-linked market research brief about funding, capital-market context, and liquidity; compare what changed since a previous check. Use for daily market context, market briefings, and evidence checks alongside AI trading copilots. Does not provide ticker-specific news, stock picks, position sizing, portfolio advice, or trade execution.
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command.
Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
Session retrospective — reviews the current conversation to find mistakes,
trace root causes, and propose process improvements. Use when the user says
"session retro", "retrospective", "retro", or "review this session" at the end
of a work session. Also useful mid-session after a correction to immediately
analyze what went wrong.
Connect and verify the Well MCP — authenticate, confirm the tools work, and show what to ask. Use when the user runs /well:connect, just installed the Well plugin, or says the Well connection/MCP "isn't working" / "nothing happened".
Use when executing a plan's F-blocks — the build ledger, the resume rule, one commit per F-block, the ruling format, and the four hard stops. Load before the first F-block of any planned build.