Opencode

Drive Kortix itself from the terminal with the `kortix` CLI — preinstalled and pre-authenticated in every session sandbox. Use whenever a task means acting on THIS project's Kortix control plane rather than just editing files: manage secrets, list/spawn/watch/talk-to sessions, open or inspect change requests to land work on main, fire or manage triggers, call connectors, connect Slack, or read project info. This is a discovery stub — the full, always-current reference is served live via `kortix skills get kortix-system` and its reference files.

Route code, repository, and data/SQL work to isolated Kortix sessions instead of burning your main context on it. Use when asked to implement a feature, fix a bug, make failing tests pass, work a ticket/issue, refactor, navigate or change a codebase, ship a PR, review a pull request, or run SQL/warehouse analysis against a dataset — and when the user wants two agents or parallel reviewers/investigators on the same work. Covers the explore-vs-session routing call, deciding where the code lives (this project's repo vs cloning an external GitHub repo) or where the data lives, finding the repo with gh, spawning sessions in parallel, dual PR reviews, and reporting results back. Triggers: 'implement', 'fix the bug', 'make the tests pass', 'work this ticket', 'refactor this', 'open a PR', 'review this PR', 'run two agents on it', 'query the warehouse', 'analyze this dataset'.

Find and read information on the open web — fan-out web/news/finance search plus full-page fetching and source extraction. Use to answer current questions, gather and cite sources, verify a claim, or pull text from specific URLs. Triggers: 'search the web', 'look this up', 'find sources on', 'what's the latest on', 'fetch this page', 'is it true that…', 'compare X vs Y'.

Deploy and operate provider-neutral Kortix Apps through the pre-authenticated CLI or SDK. Use when the user asks to publish, host, deploy, preview, inspect, wake, suspend, roll back, debug, or remove HTML/CSS/JavaScript, a static SPA, Vite or React source, Next.js, a Dockerfile service, or an OCI image on a stable Kortix URL.

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.

How to CONNECT Microsoft Teams (`kortix channels connect --platform teams`, prints a tenant-admin consent URL) and how to answer in 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 through connector calls, 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.

How to read, write, and curate project memory in `.kortix/memory/` — the project brain. Load this skill whenever you (or the harness-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`.

Complete Kortix sandbox system reference. Covers: container image, s6 services, filesystem layout, persistence model, environment variables, secrets management (API for setting/getting/deleting env vars), ports, runtimes, init scripts, cloud mode, desktop environment, deployments (deploy apps to live *.style.dev URLs), cron triggers (scheduled agent execution), semantic search (lss), session search & management (API + on-disk queries), skill creation guide, and all installed tooling. Load this skill when you need to: understand the sandbox, debug services, configure the environment, set API keys/secrets, deploy web apps/APIs/static sites, schedule cron jobs, search files semantically, query session data, or create new skills.

How to reach a CONNECTED MACHINE (a user's laptop/desktop, or any computer paired over the Agent Computer Tunnel) from a Kortix session — read/write files, run shell commands, and drive the desktop (click/type/screenshot) on that machine. It works through the `computer` connector and the same list/discover/show/call path as every other connector, so there is no separate tunnel client and no token. Load this when the task is about acting ON a specific physical/remote computer the user has connected ("on my laptop…", "read ~/Downloads on my machine", "run this on my desktop", "click the button on my screen"), or when the user asks how the agent reaches their computer. For files INSIDE this sandbox, just use normal shell/fs — not this.

Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification (defined terms, cross-references, placeholders, boilerplate, citation format). Triggers on: 'draft a contract', 'write a legal memo', 'create an NDA', 'write a brief', 'legal document about', 'draft a complaint', 'terms of service', 'privacy policy', 'demand letter', 'settlement agreement', 'legal opinion', 'discovery requests', any request to produce a legal or law-related document.

Use Kortix connectors to reach external systems from a session. Use the `kortix connectors` CLI for agent work, `@kortix/sdk` for durable TypeScript workflows, and `kortix connectors mcp` when a stdio MCP server is required. Load this skill to inspect, add, connect, or call external tools without exposing third-party credentials to the sandbox.

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.

Deep research agent skill. Use when the user needs thorough, scientific, truth-seeking research on any topic -- investigating claims, finding primary sources, synthesizing evidence, producing cited reports. Triggers on: 'research this', 'investigate', 'deep dive', 'find sources', 'what does the evidence say', 'literature review', 'fact check', 'analyze the research on', any request requiring multi-source investigation with citations.

The Kortix marketplace — how to discover capabilities and IMPORT them into this project. The marketplace is a catalog of open git repos: whole ready-made PROJECTS (registry:project) and individual skills/agents/tools. There is no deterministic 'installer' — you (the agent) import an item by reading its source and merging the files that fit into this project, then opening a change request. Use when the user wants to browse/search the Kortix catalog, 'add/clone the <X> project', 'import that skill/agent', pull in a marketplace capability, or add a new source.

Use for structured review, fact-checking, annotation, and correction of documents such as PDF, DOCX, PPTX, and XLSX files.

Free domain research and availability checking. No API keys or credentials required. Uses RDAP (1195+ TLDs) with whois CLI fallback for universal coverage. Checks if domains are available, searches keywords across TLDs, performs WHOIS/RDAP lookups, checks expiry dates, and finds nameservers. Use when the agent needs to: check if a domain is available, search for domains, find who owns a domain, check domain expiration, get nameservers, bulk check domains, or do any domain research. Triggers on: 'check domain', 'is domain available', 'search domains', 'domain availability', 'who owns this domain', 'whois', 'domain expiry', 'when does domain expire', 'nameservers for', 'domain research', 'find domains for', 'domain ideas', 'bulk domain check'.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, or general coding tasks unrelated to document generation.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like 'the xlsx in my downloads') — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Use for fullstack web apps built with the bundled Express, Vite, React, Tailwind, and Drizzle template.

The continual-harness refinement protocol — how an agent inspects its recent trajectory for failure signatures and improves its own harness (agent prompts, sub-agents, skills, memory) in place, mid-session, landing changes on the session branch immediately and promoting them to `main` only through a change request. Load this skill when a refinement prompt arrives mid-session, when the `harness-reflector` agent runs, or whenever you decide your own scaffolding needs repair. The sub-agent fan-out in this skill is for the top-level `harness-reflector` run only; if you loaded this as a subagent, do the four passes yourself and skip the fan-out.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Use this skill any time the user wants to create, edit, or export a slide deck presentation. This includes any task involving slides, decks, pitch decks, keynotes, or visual presentations. Trigger when the user says anything like 'create a presentation', 'make slides', 'build a deck', 'presentation about X'. The deliverable is a set of HTML slides (1920x1080) created via the presentation-gen tool, with optional PDF/PPTX export. Do NOT trigger for documents, reports, spreadsheets, or web pages — only slide deck presentations.

Use for distinctive production-grade websites, landing pages, and interactive web experiences with strong design and QA discipline.

Artifact-agnostic design guidance — works for CSS, PowerPoint, matplotlib, PDF, or any visual output. Also includes a curated catalog of named font/color themes for slides, docs, and reports (non-web assets).

Convert Word (.doc, .docx), PowerPoint (.ppt, .pptx), Excel (.xls, .xlsx), OpenDocument (.odt, .ods, .odp), RTF, EPUB, CSV, and PDF files to GitHub-Flavored Markdown. Use when a task needs the contents of an office document, spreadsheet, presentation, ebook, or PDF you cannot read directly.

Publish a website or web app from the sandbox to a public URL, and deploy to cloud providers — get a live link to share, ship a static site or SPA, put a built site online, or deploy a framework app / container. Use when the user says 'publish this', 'deploy it', 'put it online', 'give me a live URL', 'host this', 'share a preview link', or wants to make a site/app they (or you) just built reachable on the web. Covers the zero-account instant path (Cloudflare) and permanent hosting (Vercel, incl. any Dockerfile). Also owns the publish GUARDRAILS: never publish unprompted, how to honestly take a site down, the runtime-dependency and data-persistence checks, and the mandatory pre-publish security review. Points at kortix-marketplace for other providers and deeper provider-specific skills.