How to send a notetaker bot into a video meeting (Google Meet / Zoom / Teams) and work with what it captures — join a call, confirm it got admitted, monitor its lifecycle, pull the speaker-attributed transcript, and produce a recap with decisions + action items, then remove it. Drives the `meet` CLI, which runs through the Kortix Executor (the meeting-bot provider key is resolved server-side; nothing in the sandbox). Load this WHENEVER the user asks to join / attend / record / transcribe / take notes on a meeting, "send a notetaker", "summarize that call", drops a Meet/Zoom/Teams link, or asks how to do anything with a meeting bot.
How to read, write, and curate project memory in `.kortix/memory/` — the project brain. Load this skill whenever you (or the memory-reflector agent) need to add, update, or reorganize what this project knows about itself. Defines the rubric for what belongs in memory, the file structure, and the change-request flow for landing memory edits on `main`.
Guide a new Kortix user through their first session: set expectations about what Kortix is, turn a vague ask into a strong first prompt, deliver one real result, then surface deeper capabilities (connectors, memory, triggers, subagents, marketplace) and plant a retention hook. Use when the user is new, asks 'what can you do / how does this work / where do I start', sends a vague or exploratory first message, or has no prior history in this project. Do NOT use when they arrive with a specific, well-formed task — just do it.
How to cut a Kortix production release — the versioning philosophy (when patch vs minor vs major) and the exact flow: derive the release title + notes from the FULL git log since the last release, run the Promote workflow, then deploy + verify prod. Load WHENEVER the user wants to release, promote, cut/ship a version, publish a release, or bump the version. The release notes ARE the public /changelog, so they must be 100% accurate to what shipped.
How to roll Kortix PRODUCTION back to an older already-released version — the inverse of a release. Covers the one-dispatch rollback-prod.yml engine, the per-surface mechanics (API + gateway = Argo image-tag swap; frontend = Vercel promote), the all-important Vercel frontend behavior (why a backend-only push can 'clobber' a FE rollback, and the 'don't rebuild the FE for backend-only pushes' skip that fixes it), the DB/migration-drift safety check that is the real blocker, and how a later promote returns prod to latest. Load WHENEVER the user wants to roll back / revert / downgrade / 'go back a version' on prod, asks how the rollback or the frontend clobber/skip behavior works, or needs to run rollback-prod.yml. Pairs with kortix-release (the forward direction).
How to CONNECT Slack (one command — `kortix channels connect`, prints a one-click install link) and how to answer in Slack as a teammate. Covers the live plan-block stream (`slack step` with --detail/--output, `slack send` to finalize the answer), file uploads, posting to other channels/threads, reactions, search, message editing/deletion, and the tone the bot should use. Load this when the user asks to connect/set up Slack, when the turn is triggered from Slack (the prompt mentions a Slack workspace/channel/thread, or `$SLACK_CHANNEL_ID` is set in the env), or when the user asks how to do anything in Slack.
Canonical reference for a Kortix project: what Kortix can do (research and the web, browser automation, code and data execution, documents and media, websites and apps, connectors/integrations, secrets, memory, scheduling, channels, parallel subagents, model selection) and how the platform works under the hood — repo-native projects, sessions on ephemeral branches, the strict boundary between `kortix.yaml` and OpenCode config under `.kortix/opencode/`; the full `kortix.yaml` manifest (keys, `triggers:` fields incl. cron/webhook/one-off scheduling and `session_mode`, secrets contract, `apps:` deploy surface); the complete `kortix` CLI (commands, flags, the project-scoped token model, the in-sandbox `KORTIX_SANDBOX_TOKEN`); the change-request (CR) system for landing session work on `main` (an agent MUST open a CR to merge); the session sandbox runtime (which supports Docker and Docker-in-Docker); and the OpenCode runtime (agents, skills, commands, tools, plugins, MCP servers, permissions, AGENTS.md rules, models). Load whenever the user asks how Kortix works, what Kortix/it can do, 'can you do X', how to do Y in Kortix, how Kortix compares to other AI tools/assistants, about `kortix.yaml`, the `kortix` CLI, anything under `.kortix/opencode/`, how to merge/ship/land work on `main`, change requests/CRs/PRs, how to author/edit any OpenCode primitive, or how to schedule something — recurring/cron jobs, one-off reminders, run-later, webhooks, or automations.
How to answer in Microsoft Teams as a teammate. Covers the live Adaptive Card stream (`teams step` with --detail/--output/--source, `teams send` to finalize the answer), sending and downloading files (the consent-card upload flow + `teams download`), reading teams/channels/members via the Executor, asking the user, and the tone the bot should use. Load this when the turn is triggered from Teams (the prompt mentions a Teams tenant/conversation, or `$MS_TEAMS_CONVERSATION_ID` is set in the env), or when the user asks how to do anything in Teams.
Fast first-pass NDA review for {{nda_label}}. Saves a new inbound NDA into {{nda_folder}}, checks it clause-by-clause against our standard NDA positions, drafts redlines on what deviates, and drafts a flag summary for counsel — holding every redline and flag for counsel's sign-off. Never signs or sends.