fabric

Delegate coding to xAI Grok Build CLI (features, PRs).

Configure and use Honcho memory with Fabric -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

Hyperliquid market data, account history, trade review.

Article illustrations: type × style × palette consistency.

Knowledge comics (知识漫画): educational, biography, tutorial.

Create HTML-based video compositions, animated title cards, social overlays, captioned talking-head videos, audio-reactive visuals, and shader transitions using HyperFrames. HTML is the source of truth for video. Use when the user wants a rendered MP4/WebM from an HTML composition, wants to animate text/logos/charts over media, needs captions synced to audio, wants TTS narration, or wants to convert a website into a video.

Plan, set up, and monitor a multi-agent video production pipeline backed by Fabric Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Fabric profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Fabric rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.

Modify, debug, or extend the s6-overlay supervision tree inside the Fabric Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.

Zero-install localhost tunnels over SSH via Pinggy.

Poll RSS, JSON APIs, and GitHub with watermark dedup.

Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. fabric-agent@agentmail.to).

Migrate a user's OpenClaw customization footprint into Fabric. Imports Fabric-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

Agent payments via Stripe Link — cards, SPT, approvals.

Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.

Publish static sites to {slug}.here.now and store private files in cloud Drives for agent-to-agent handoff.

Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.

Give Fabric phone capabilities without core tool changes. Provision and persist a Twilio number, send and receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi.

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

Public-records OSINT investigation framework — SEC EDGAR filings, USAspending contracts, Senate lobbying, OFAC sanctions, ICIJ offshore leaks, NYC property records (ACRIS), OpenCorporates registries, CourtListener court records, Wayback Machine archives, Wikipedia + Wikidata, GDELT news monitoring. Entity resolution across sources, cross-link analysis, timing correlation, evidence chains. Python stdlib only.

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Autonomously remove your info from data-broker sites.

Authorized web application penetration testing — reconnaissance, vulnerability analysis, proof-based exploitation, and professional reporting. Adapts Shannon's "No Exploit, No Report" methodology with hard guardrails for scope, authorization, and aux-client leakage. Active testing against running applications you own or have written authorization to test.

Generate wiki docs + Mermaid diagrams for any codebase.

Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script> tag or npm package and lets end-users of your site drive the UI with natural language ("click login, fill username as John"). No Python, no headless browser, no extension required. Use this skill when the user is a web developer who wants to add an AI copilot to their SaaS / admin panel / B2B tool, make a legacy web app accessible via natural language, or evaluate page-agent against a local (Ollama) or cloud (Qwen / OpenAI / OpenRouter) LLM. NOT for server-side browser automation — point those users to Fabric's built-in browser tool instead.

Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

Configure, extend, or contribute to Fabric.

ASCII video: convert video/audio to colored ASCII MP4/GIF.

Throwaway HTML mockups: 2-3 design variants to compare.

Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

Himalaya CLI: IMAP/SMTP email from terminal.

File approved Fabric bug reports and feature requests.

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.

Notion API + ntn CLI: pages, databases, markdown, Workers.

Author governed Fabric skills and evaluation contracts.

Parallel 3-agent cleanup of recent code changes.

Throwaway experiments to validate an idea before build.

Run a two-layer Mixture-of-Agents software workflow: one-shot GPT/Grok advisory planning, independent subscription-backed coding workers in isolated git worktrees, deterministic viability gates, and a blinded final MoA review owned by one merge agent. Use for difficult cross-module, architectural, security-sensitive, or genuinely disputed repository changes where independent implementations are worth the cost.

Front door for multi-agent work — decide when to orchestrate at all, then route between subagent ensembles, parallel fan-out, staged pipelines, a builder crew, adversarial verification, isolated GPT/Grok coding worktrees, kanban worker lanes for durable boards, and Mixture of Agents for multi-model answers. Use when a task feels too big for one context, the user asks for parallel work, subagents, a team of agents, or an ensemble.