Generative UI for Kortix: the agent writes typed UI blocks (cards, comparisons, charts, maps, tabs) in OpenUI Lang inside its replies, and web, mobile, and SDK hosts render them through `@kortix/sdk/genui`. Load WHENEVER you design, build, review, or debug generative UI, the `openui` code fence, the `genui` project flag, the genui prompt instructions, a genui component, or the `@kortix/sdk/genui` or `/genui/react` subpaths.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
genui)Status (2026-10-10): built on branch genui, not merged to dev. SDK (@kortix/sdk/genui, /genui/react), runtime (genui flag, prompt on OpenCode and pi, channel guards), web, and mobile are implemented. Plans 1–5 are built. Open: plan-4 task 8 (full pnpm test attestation, browser checks), and plan-5 task 7's device check and OTA publish, which wait on Jay (references/mobile-device-check.md).
Phase 0 (provisional, local stand-in models): GO (2026-10-09, prompt 00a9030e). Valid: deepseek-v4.1-flash 100.0%, glm-5.3-flash 100.0%, gate 97.0%; kimi-k3 unavailable (503); Jay's 4 models untested. See references/eval-results.md.
| Path | What it is |
|---|---|
references/spec.md | The product spec: problem, goals, architecture, the 17 v1 components, streaming contract, toggle, requirements with acceptance criteria, Phase 4 guards, metrics, phases, risks, open questions |
references/plan.md | Master implementation plan: architecture, global constraints, review focus, spec deltas D1–D12, file map, interface contracts, order of work, delivery |
references/plan-1-sdk.md | @kortix/sdk/genui + /genui/react + default components (9 tasks; code verified before writing) |
references/plan-2-eval.md | Phase 0 evaluation of 4 models on 46 synthetic cases, go/no-go gate (2 tasks) |
references/plan-3-runtime.md | genui flag, GENUI_ENABLED kill switch, prompt on OpenCode and pi, channel guards (5 tasks) |
references/plan-4-web.md | Web and desktop renderer, components, charts, map, settings, copy/export, telemetry, verification (8 tasks) |
references/plan-5-mobile.md | Mobile renderer, components, charts, map, settings, copy, device check, OTA (7 tasks) |
references/eval-results.md | Phase 0 results: one summary table per eval run, appended by scripts/eval.ts |
references/mobile-device-check.md | On-device checklist for mobile (Jay runs it), the OTA publish procedure, the old-build check |
scripts/eval.ts | Phase 0 runner: every case against each model through the LLM gateway; writes output/genui-eval/ and appends eval-results.md |
scripts/eval-prompts.json | The 46 synthetic eval cases: prompt, optional tool result (context), expected UI use (expect), forbidden components (forbid) |
scripts/score.ts, scripts/score.test.ts | Scores one reply (valid blocks, overuse, underuse, forbidden components) and applies the go/no-go gate |
openui fenced block inside the existing text part.
kortix.transcript.v1 does not change.@kortix/sdk/genui imports @openuidev/*. Pin it to an exact version.toMarkdown. A component enters the prompt only when all four exist.kortix-genui managed system skill
(packages/starter/templates/managed/skills/kortix-genui/SKILL.md), generated from
buildGenuiPrompt() by bun packages/sdk/scripts/genui-skill.ts; packages/sdk/src/genui/skill.test.ts
fails while it is stale. It is never in the system prompt. Project flag off = kortixd hides the skill
(apps/kortix-sandbox-agent-server/src/lib/config/genui.ts).toMarkdown.references/spec.md §9.NEXT_PUBLIC_GENUI_MAP_STYLE_URL (optional NEXT_PUBLIC_GENUI_MAP_STYLE_URL_DARK),
mobile EXPO_PUBLIC_GENUI_MAP_STYLE_URL. Unset, it renders the place list with
OpenStreetMap links. Never mapcn's CARTO default (commercial license). Web
loads MapLibre only with a style set, and serves its worker from /maplibre/
(copied out of node_modules by apps/web/scripts/viewer-wasm.mjs).sanitizeTree
(packages/sdk/src/genui/validate.ts) puts its valid subtrees in its place, in
source order. A subtree the parent slot cannot hold rises to the nearest ancestor
that can (any block fits a Stack); a non-block gives up its own children. A root
that fails becomes a Stack of its subtrees. Only a block with no valid subtree
has root: null.separateGenuiClosers (@kortix/sdk/genui/fence) on reply text
before it looks for fences: it moves a closer the model glued to the last
statement (…")````) onto its own line. genuiToMarkdown runs it itself. The web (unified-markdown.tsx), mobile (selectable-markdown.tsx) and scripts/score.ts` call it directly.まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Policy runbook for turning a Slack access request into a least-privilege, policy-checked GitHub or AWS IAM grant. Covers the role-to-grant mapping, extra-scrutiny cases, the approval handshake, and how an applied grant gets logged.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
Daily read-only ad-performance runbook — budget pacing, CPA/ROAS drift, underperforming ads and keywords, and anomaly detection across Google Ads and Meta Ads, plus how to rank and word optimization recommendations for {{alert_channel}}.
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。
Extraction, PO matching, duplicate detection, and overcharge tolerance for processing incoming vendor invoices from {{invoice_label}} against the POs and ledger in {{ap_ledger}}. Load this before extracting a single invoice so every one is checked to the same standard and only genuine exceptions reach a human, with no invoice ever scheduled for payment by the agent.
日本語の概要は準備中です。原文の説明を表示しています。
Kortix billing: plans (Free, Credits, Enterprise), credits and the wallet, compute and model pricing, trials, enterprise contracts, entitlement overrides and who may manage billing. Load before changing anything under apps/api/src/billing, the admin account billing routes, the web billing/pricing UI, or plan copy.
日本語の概要は準備中です。原文の説明を表示しています。