mangaba-agent

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.

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

Agenda follow-up proativo com o cliente — o agente volta a falar sozinho (ex.: PIX não pago em 2h, cliente sumiu no meio do pedido). Recuperação de venda automática.

Fluxo de atendimento ao cliente por WhatsApp de ponta a ponta — saudação, entendimento, resolução, cobrança (PIX) e fechamento. Procedimento fixo, confiável em modelos pequenos.

Gerencia e apresenta um catálogo de produtos/serviços a partir de um arquivo local (CSV/JSON) — busca, preço, disponibilidade. Funciona offline e em modelos pequenos.

Guarda de conformidade LGPD no atendimento — minimiza coleta de dados pessoais, evita vazar dados entre clientes e orienta consentimento. Procedimento curto e determinístico.

Triagem e orientação para emissão de nota fiscal (NF-e/NFS-e/NFC-e) no Brasil — coleta os dados certos, valida CPF/CNPJ e prepara a emissão. Não emite sozinho; orienta o caminho.

Gera cobrança PIX (copia-e-cola + QR Code) válida, localmente, sem API paga. Use quando o cliente pedir 'cobre o cliente', 'gere um PIX', 'manda o pix de R$X'. Funciona em modelos pequenos.

Revisa uma resposta ANTES de enviar ao cliente — tom, completude, e vazamento de dados sensíveis. Procedimento curto e estreito que funciona bem até em modelos pequenos.

Classifica um pedido recebido por complexidade (baixa/média/alta) e decide o caminho — resposta direta, skill, script ou sub-agente. Procedimento estreito, confiável em modelos pequenos.

Resume documentos (PDF, TXT, DOCX) ou textos longos em um formato estruturado e confiável, passo a passo — funciona bem até em modelos pequenos.

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

Configure and use Honcho memory with Mangaba -- 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.

Read-only EVM client: wallets, tokens, gas across 8 chains.

Hyperliquid market data, account history, trade review.

Query Solana blockchain data with USD pricing — wallet balances, token portfolios with values, transaction details, NFTs, whale detection, and live network stats. Uses Solana RPC + CoinGecko. No API key required.

Structured decision-making framework for technical proposals and trade-off analysis. When the user faces a choice between multiple approaches (architecture decisions, tool selection, refactoring strategies, migration paths), this skill produces a 1-3-1 format: one clear problem statement, three distinct options with pros/cons, and one concrete recommendation with definition of done and implementation plan. Use when the user asks for a "1-3-1", says "give me options", or needs help choosing between competing approaches.

Control Blender directly from Mangaba via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

Generate flat, minimal light/dark-aware SVG diagrams as standalone HTML files, using a unified educational visual language with 9 semantic color ramps, sentence-case typography, and automatic dark mode. Best suited for educational and non-software visuals — physics setups, chemistry mechanisms, math curves, physical objects (aircraft, turbines, smartphones, mechanical watches), anatomy, floor plans, cross-sections, narrative journeys (lifecycle of X, process of Y), hub-spoke system integrations (smart city, IoT), and exploded layer views. If a more specialized skill exists for the subject (dedicated software/cloud architecture, hand-drawn sketches, animated explainers, etc.), prefer that — otherwise this skill can also serve as a general-purpose SVG diagram fallback with a clean educational look. Ships with 15 example diagrams.

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 Mangaba 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 Mangaba profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Mangaba 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.

Generate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files.

Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily

Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.

Zero-install localhost tunnels over SSH via Pinggy.

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

Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.

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

Build fully-integrated 3-statement models (IS, BS, CF) in Excel with working capital schedules, D&A roll-forwards, debt schedule, and the plugs that make cash and retained earnings tie. Pairs with excel-author.

Build comparable company analysis in Excel — operating metrics, valuation multiples, statistical benchmarking vs peer sets. Pairs with excel-author. Use for public-company valuation, IPO pricing, sector benchmarking, or outlier detection.

Build institutional-quality DCF valuation models in Excel — revenue projections, FCF build, WACC, terminal value, Bear/Base/Bull scenarios, 5x5 sensitivity tables. Pairs with excel-author. Use for intrinsic-value equity analysis.

Build auditable Excel workbooks headless with openpyxl — blue/black/green cell conventions, formulas over hardcodes, named ranges, balance checks, sensitivity tables. Use for financial models, audit outputs, reconciliations.

Build leveraged buyout models in Excel — sources & uses, debt schedule, cash sweep, exit multiple, IRR/MOIC sensitivity. Pairs with excel-author. Use for PE screening, sponsor-case valuation, or illustrative LBO in a pitch.

Build accretion/dilution (merger) models in Excel — pro-forma P&L, synergies, financing mix, EPS impact. Pairs with excel-author. Use for M&A pitches, board materials, or deal evaluation.

Build PowerPoint decks headless with python-pptx. Pairs with excel-author for model-backed decks where every number traces to a workbook cell. Use for pitch decks, IC memos, earnings notes.

Stock quotes, history, search, compare, crypto via Yahoo.

Gym workout planner and nutrition tracker. Search 690+ exercises by muscle, equipment, or category via wger. Look up macros and calories for 380,000+ foods via USDA FoodData Central. Compute BMI, TDEE, one-rep max, macro splits, and body fat — pure Python, no pip installs. Built for anyone chasing gains, cutting weight, or just trying to eat better.

Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app running locally.

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.