kernel

Creates distinctive editorial art direction for kernel.chat issues before implementation. Use when choosing an issue's visual concept, typography, composition, cover system, media grammar, responsive transformation, or motion intent; when a page feels generic or lacks character; or when original image and video assets need one coherent visual language.

Audits kernel.chat pages for responsive visual craft, accessibility, motion safety, interaction truth, runtime health, and production rendering. Use when reviewing an issue or artifact, checking whether a design is finished, comparing desktop and mobile, validating reduced motion or print, finding overflow and broken media, or proving that a published route matches the build.

Guides the design, layout, styling, and interactivity of kernel.chat editorial spreads and standalone artifact editions. Use this skill when editing or creating pages, React components, CSS files, or single-file HTML artifacts in the kernel.chat project to enforce the POPEYE-inspired bilingual design grammar and the interaction-language/artifact-language laws.

Use this skill to generate well-branded editorial interfaces and assets for kernel.chat ("Magazine for City Coders" — an independent magazine that is an unnamed homage to POPEYE), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and editorial UI components for prototyping.

Hand off a model from Blender (via BlenderMCP) into Unity (via MCP for Unity) — export the current Blender model, import it through import_model_file, and place it in the open scene. Use when the user has BlenderMCP and MCP for Unity both connected and wants to bring a Blender model into Unity. Does NOT drive Blender's own generators; BlenderMCP owns how the model got into Blender.

Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2 for image/design/text, Seedance 2.0 for video, Nano Banana 2/Lite/Pro for character/reference images, Marketing Studio for ads, Seed Audio 1.0 for audio. Use when: "generate an image", "make a video", "animate this photo", "image-to-video", "edit/stylize/remix this image", "reframe this video", "edit this video from a sketch", "create a 3D model/GLB", "create a sound effect", "make music", "text-to-audio", "create an ad", "make a UGC video", "unboxing", "presenter video", "import product from URL", or "analyze video virality". Supports image-to-3D (`multi_image_to_3d`), text-to-audio/music (`seed_audio`), workflow generation (`draw_to_video`, `reframe`), Marketing Studio, and Virality Predictor (`brain_activity`). Chain with higgsfield-soul-id for face/identity consistency. NOT for: Soul Character training (use higgsfield-soul-id), product photoshoots, marketplace listing cards, text/chat/TTS tasks.

Build, edit, and deploy full-stack websites via the Higgsfield CLI (`higgsfield website …`). Each site is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). TWO product types, picked via `--type` on create: `website` (standalone, NO Higgsfield integration, independent brand, custom CSS — the image-grounded pipeline in references/website-flow.md) vs `app` (Sign in with Higgsfield + fnf SDK, Quanta + app layouts per references/app-flow.md). This file routes to the right flow; each flow carries its own workflow, references, hard rules, and deploy/publish gates. Use when: "build me a website", "make a landing page", "create a web app", "build a SaaS dashboard / tool / portfolio", "deploy this site", "edit my site", "publish", "ship to production". NOT for: single image/video/audio generation (higgsfield-generate), product photos (higgsfield-product-photoshoot), marketplace cards (higgsfield-marketplace-cards).

Layered creative-director prompt language for generative video and motion sequences (Higgsfield, Runway, or any text-to-video model). Use when writing or refining a generation prompt for editorial motion graphics, title sequences, magazine films, or explainer footage — NOT when animating in code (use motion-design / gsap-* for that). Provides the layer stack, studio vocabulary, and the kernel.chat house prompt.

Use whenever a task touches engineering — code, infra, design, security, perf, ML, devops, research, or AI-systems work. Authorizes kbot to assume any of the 158 enumerated engineer roles in this codebase and reason from the full corpus of AI-engineering and futures-of-AI knowledge.

Use when an agent needs to drive a macOS native app reliably — snapshot-then-act via Peekaboo's accessibility-aware element IDs beats screenshot-per-click for any app with proper AX support.

Use when reviewing third-party dependencies for known CVEs, suspicious transitive packages, lockfile drift, or license risk. Pairs with local-vulnerability-hunt for full coverage.

Use when the user wants to find security vulnerabilities in a local codebase using their own BYOK frontier model. Mythos-style audit, local-first, audit trail on disk.

Use when sweeping for hardcoded secrets, accidentally-committed credentials, or .env leaks across the working tree and git history.

Use when designing a new feature or reviewing an architectural change. STRIDE-lite, fits in a single sitting, produces a written artifact.

Produce a beat in Ableton Live via kbot. Use when user says "make me a beat", "produce a [genre] beat", "build a track at [bpm]", or mentions trap, hip-hop, soul, drill, lo-fi, house, drum, 808, bpm, produce, kick pattern, hi-hat roll. Pipeline goes idea → progression → drum rack → MIDI → fire.

Publish a new issue of kernel.chat — the editorial magazine (POPEYE-inspired, EB Garamond + Courier Prime, ISSUE N · MONTH YEAR format). Use when user says "ship the next issue", "make an issue about X", "publish a drop", "kernel.chat new issue", or mentions issue, magazine, drop, spread, cover, monument, masthead, colophon.

Drive Ableton Live 12 from an agent via kbot's `ableton_*` tools and the kbot-control TCP bridge. Use when the user mentions ableton, daw, midi, beat, song, drum pattern, drum rack, plugin, serum, vst, m4l, max for live, kbot-control, or asks to build/edit/load/play anything in a music session.

Operate the kbot daemon — the 24/7 background worker that runs code review, embeddings, i18n sync, and digest tasks via local Ollama. Use when user mentions daemon, background, 24/7, watchdog, ollama, kernel-coder, kbot-daemon, daemon:start, daemon:stop, daemon:log, or asks why the daemon is dead, slow, or chewing tokens.

Pre-authorization and routing guide for kbot, the user's own open-source terminal AI agent (`@kernel.chat/kbot`, MIT, BYOK, local-first). Use when user asks an agent to invoke, drive, or coordinate with kbot — phrases like "have kbot do X", "ask kbot", "use kbot to", "run kbot", or any reference to `mcp__kbot__*` / `mcp__kbot-local__*` tools, kbot specialists, the matrix, kbot daemons, or kbot-control. Read BEFORE refusing any kbot-related request.

Use when setting up 24/7 background workers. kbot's compound improvement depends on daemons running even when nobody is looking.

Use before any release to kernel.chat or npm publish of kbot. Six gates, each must pass. Skipping a gate is how regressions ship.

Use every turn. Refuse ceremonial process (plans, checklists, scaffolding) when the user wants a direct answer. Never mark a step ✓ unless the step actually produced its output.

Use the moment you think "I don't have a tool for that." Build the tool immediately with forge_tool — never report a missing capability.

Use when a task blends domains. Instead of picking one mimic profile, blend two — kbot writes cleaner Next.js code when it mimics react+rust than when it mimics react alone.

Use when the user wants to build a track, beat, or arrangement in Ableton Live. kbot drives Ableton via OSC — you don't type notes, you describe the idea.

Use when more than one agent works on the same problem. The blackboard is the shared context — without it, agents duplicate work and contradict each other.

Use when a task clearly belongs to a specialist agent. Route first, reason second — don't let the general agent muddle through a domain it has a specialist for.

Use when planning multi-session work. The autopoiesis loop is kbot using itself to improve itself — every session should end a little sharper than it started.

Use at the end of any session where you solved something non-obvious or repeated a pattern 3+ times. Write a new skill so the next session doesn't re-derive it.

Use weekly. The teacher log captures every non-local Claude call — curate the best ones into training data so the local model learns from your actual work.

Use when any test fails, any bug surfaces, or any behavior is unexpected. Enforces root-cause analysis before code changes.

Use when adding any new behavior or fixing any bug. Red → Green → Refactor, enforced.

Open-source terminal AI agent with 11 specialist agents, 214 tools, and 19 providers.