broomva

Implementa práticas de Engenharia de Harness da OpenAI em qualquer repositório, incluindo AGENTS.md, PLANS.md, comandos determinísticos de smoke/test/lint, limites arquitetônicos rigorosos, observabilidade desde o primeiro dia e auditorias de controle de entropia para execuções confiáveis de agentes autônomos.

Takes raw unstructured thoughts, voice transcript dumps, or stream-of-consciousness text and auto-files them into the right Obsidian vault folders with tags, backlinks, and proper frontmatter. Use when the user says "braindump", "brain dump", "capture this", "dump my thoughts", "I'm thinking about...", or provides a long unstructured block of text to organize.

Microsoft BitNet — 1-bit LLM setup, inference, and benchmarking on CPU. Automates the full workflow: clone bitnet.cpp, create conda env, download GGUF models from HuggingFace, build optimized ternary kernels, and run inference. Supports official Microsoft models (2B) and community models (0.7B-10B). Use when: (1) setting up BitNet/bitnet.cpp for local CPU inference, (2) downloading and running 1-b

Produce high-retention, dopamine-aware video content using brainrot editing techniques — fast cuts, word-by-word captions, sound design, visual velocity, pattern interrupts — all in service of genuinely valuable content. The Fireship model: brainrot pacing meets real substance. Built on Remotion with Imagen/Veo for assets. Use when: (1) creating edutainment content that competes with brainrot for

SEO and LLM Engine Optimization (LLMEO) skill for BroomVA content. Analyzes pages for traditional search-engine signals (meta tags, structured data, Core Web Vitals, internal linking) and for LLM discoverability (llms.txt, semantic headings, FAQ schema, citation-friendly structure). Generates actionable audits and rewrites. Use when: (1) auditing a page or site for SEO health, (2) optimizing conte

Estimate optimal waiting time for Alkosto's "every 25/50 customers" promotion using either checkout-flow observations or winner announcement timestamps. Use when the user asks how long to wait, wants a probability-based cutoff, or needs a fast in-store decision rule with uncertainty handling.

Per-channel remote sessions for Claude Code via Discord and Telegram — each channel, thread, or chat gets its own isolated Claude Code session via tmux, with per-channel access control, project-specific workdirs, and automatic CLAUDE.md chain loading. Includes session managers, watchdog daemons (auto-respawn, auto-discover, stale cleanup), thread context injection, session resume, workdir mapping,

Meta-review skill for validating generated creative assets (videos, images, designs) against a reference style brief. Extracts frames, compares against style criteria, scores adherence, and produces actionable feedback for iteration. Self-improving feedback loop: each review refines the style brief for the next generation. Use when: (1) reviewing a generated video against a reference style, (2) va

Agentic finance engine for the Agent OS — x402 machine-to-machine payments, on-chain settlement, per-task revenue billing, and wallet management. Integrates with Arcan (agent runtime), Autonomic (economic homeostasis), and Lago (event-sourced persistence) to give agents real financial agency. Use when: (1) adding payment capabilities to an agent or agent-controlled API, (2) implementing x402 proto

Generate a polished Remotion video and X thread showcasing the full agent skills inventory. Use when creating social media content about skills, rendering category-based skill visualizations, or producing animated showcases of agent capabilities. Triggers on "skills video", "showcase skills", "skills thread", "render skills", "social content for skills", or requests to visualize the skills invento

Scaffold a substantive human-readable design doc (spec / plan / ADR / report / PR explainer) as native HTML using the workspace's canonical Broomva dark theme. Implements P18 (Format-Follows-Audience) for Category-C native artifacts — distinct from `bookkeeping render`, which projects Category-B markdown canonicals to HTML. Use when: (1) drafting a substantive design doc a human will actually read

Reads open action items, this week's priorities, and recent vault updates, then produces a focused "start your day" brief. Use when the user says "morning briefing", "daily brief", "what's on my plate", "start my day", "what should I focus on today", or at the start of a work session.

Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind s

Full-stack content creation pipeline: idea or reference to published blog post, audio narration, video, and social media distribution. Orchestrates research, reference extraction, storytelling, AI visual assets (Nano Banana, Veo 3.1), TTS audio (Voicebox, kokoro-tts, Edge TTS), Remotion video, and social copy into a complete content package. Use when: (1) creating a blog post, case study, or writi

Comprehensive bioinformatics and ocean genomics skill for eDNA metabarcoding, metagenomics, protein structure prediction, and marine biodiversity analysis. Use when: (1) Working with DNA/RNA sequences (FASTQ, FASTA, SAM/BAM, VCF files), (2) Running BLAST, QIIME2, Kraken2, or Nextflow pipelines, (3) Predicting protein structures via AlphaFold, ESMFold, or ColabFold, (4) Analyzing environmental DNA

Full-stack blog post production — turns a topic, idea, or brief into a complete publishing package across written, social, and multimedia surfaces. Generates broomva.tech .mdx posts (or Substack/other long-form), X posts and threads, LinkedIn posts, Instagram posts and reel scripts, plus multimedia asset plans (images, video, audio, GIFs). Outputs a structured content package to /broomva/posts/. U

Brand icon and visual identity management for BroomVA projects. Generates favicons, app icons, Open Graph images, and social media avatars from brand assets. Maintains consistent visual identity across web, mobile, and social platforms. Use when: (1) generating favicon sets (ICO, PNG, SVG) for a web project, (2) creating app icons for iOS/Android, (3) generating Open Graph and Twitter Card images,

Agentic robotics with CaP-X — LLM-driven robot manipulation via code generation. Use when: (1) Setting up CaP-X / CaP-Gym environments for robot manipulation benchmarks, (2) Running CaP-Bench evaluations across LLMs/VLMs on robotic tasks, (3) Building or extending CaP-Agent0 agentic harnesses (skill libraries, visual differencing, parallel reasoning), (4) Training robot coding agents with CaP-RL (

Orchestrate Google Colab Pro/Pro+ GPU instances as remote training backends via SSH. Compounds /agent-browser (to launch Colab sessions and install colab-ssh) with SSH (to operate the runtime remotely). Use when: (1) launching a Colab notebook for GPU training, (2) running training jobs on Colab from the local terminal, (3) transferring datasets/checkpoints to/from Colab, (4) monitoring GPU utiliz

OpenCaptions extension for Content Engine — adds intent-driven CWI (Caption With Intent) captions to the post-production pipeline. Hooks into the grade → caption → final stage. Generates captions that understand video intent (pitch, volume, emotion, emphasis) and style themselves accordingly with variable font weight, size, and color. Uses the OpenCaptions CLI or MCP server. Triggers on: 'add capt

Full-stack AI content studio — orchestrates visual DNA compilation, cinematic generation (via Higgsfield CLI or MCP), browser-automated tool execution, and multi-platform distribution into a unified content pipeline. Compiles brand identity, character sheets, and style guides into persistent knowledge (Karpathy compile-then-query pattern), then generates premium cinematic content using Higgsfield

Browser Orchestration — Playwright-driven generation at scale. Claude Code runs your entire content pipeline in the browser. Saves authentication sessions per tool, executes batch generation using compiled identity, and organizes output automatically. Supports Higgsfield, Weavy, Artlist, and extensible to any web-based generation tool. Triggers on: 'autopilot', 'browser automation', 'batch generat

Cinematic Generation Layer — the taste and technique library for premium AI content. Codifies start-frame doctrine, camera style vocabulary (Anderson/Fincher/Nolan/Villeneuve/Kubrick), node pipeline architecture, scene generation formulas, and 25+ design styles with exact prompts. Tier-1 generation via Higgsfield CLI (30+ models — Soul V2, Nano Banana 2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, M

Visual DNA Compiler -- compiles raw brand assets, character references, and style inspiration into persistent, structured identity files. Uses Gemini multimodal analysis to extract color palettes, composition rules, lighting patterns, and texture preferences. Generates tool-specific prompt fragments for Nano Banana Pro, Soul Cinema, Weavy, and ComfyUI. Inspired by Karpathy's LLM Wiki (compile-then

Content Loop + Distribution — compounds existing broomva skills into a unified content lifecycle. Orchestrates /blog-post, /content-creation, /social-intelligence, /brainrot-for-good, and /brand-icons for multi-platform distribution. Adds performance tracking, feedback-driven identity refinement, content calendar, and campaign management. Triggers on: 'distribute content', 'content loop', 'publish

Captures a decision with context, alternatives considered, and rationale, then links it to the relevant project doc in the vault. Creates a searchable decision record. Use when the user says "decision log", "log this decision", "record this choice", "document why we chose", "decision record", "ADR", or has just made an important decision.

Conduct comprehensive multi-dimensional research on any subject using coordinated AI research specialists

Compares stated priorities against where time and effort actually went, and produces a strategy drift report. Uses git log, vault priorities, and project docs to detect misalignment. Use when the user says "drift check", "am I on track", "priority alignment", "where did my time go", "strategy drift", or wants to audit focus vs intention.

Personalized cancer treatment navigation — maximal diagnostics, parallel therapy, therapeutic development, structure-based protein design. Use when (1) researching cancer treatments or combinations, (2) designing diagnostic strategies, (3) evaluating neoantigen vaccines or radioligand therapies, (4) navigating FDA expanded access or IRB processes, (5) interpreting ctDNA/MRD data, (6) building bioi

Fresh-session handoff doc drafting. Produces a stable, single-file human-readable narrative state for the NEXT agent context (fresh session, after `/clear`, after persist iteration, after a tab close). The artifact lives at `docs/handoffs/YYYY-MM-DD-<arc>.md` and follows a stable shape: TL;DR + State-of-the-world (P15 snapshot) + What-was-delivered (PR table with SHAs) + First action + Pickup stat

Implement OpenAI Harness Engineering practices in any repository — AGENTS.md, PLANS.md, deterministic smoke/test/lint harness commands, strict architecture boundaries, observability from day 1, and entropy-control audits for reliable autonomous agent runs.

Personal health knowledge graph — local-first ingest of Garmin (Apple Health, Whoop, Oura, CGM in v2+) traces into SQLite, projected to Obsidian daily-note frontmatter, synthesized into validated longevity-proxy metrics (HRV-CV, CTL/ATL/TSB, VO2max arc). Hex architecture so new sources drop in as adapters. NOT a coaching surface in v1.

Investment management skill — portfolio construction, analysis, and execution. Compounds finance-substrate (accounting/tax) + wealth-management (projections/goals) into a full financial framework. Covers traditional investing (stocks, ETFs, bonds), alternatives (crypto, prediction markets, real estate, VC), quantitative analytics (factor models, Monte Carlo, optimization), and platform integration

Produce polished product launch videos using the Liquid Glass aesthetic — dark void backgrounds, 3D perspective floating UI panels, particle effects, spring animations, and cinematic pacing. Built on Remotion with Imagen 4.0 for frames and Veo 3.1 for B-roll. Use when: (1) creating a product demo or launch video, (2) showcasing a UI/app/tool with cinematic polish, (3) building a social-ready video

Algorave-grade livecoded music workflow — TidalCycles patterns (Haskell DSL driving SuperDirt over OSC) + Hydra-synth visuals (browser or VS Code Simple Browser via a local HTML page that loads hydra-synth from CDN). Wraps the boot ritual (SuperCollider → SuperDirt → Tidal → Hydra), a vibe-descriptor pattern generator (industrial, ambient, DnB, footwork, techno, algorave-glitch), and a reference t

Set up, configure, and run LTX-2/LTX-2.3 (Lightricks) for AI video and audio generation. Use when: (1) Installing LTX-2 locally or via ComfyUI, (2) Generating video from text, image, audio, or keyframes, (3) Running inference with the 22B dev/distilled models, (4) Fine-tuning with LoRA/IC-LoRA, (5) Configuring upscalers (spatial/temporal), (6) Optimizing VRAM usage (FP8, quantization, low-VRAM mod

Local TTS, voice cloning, voice design, and video dubbing via the OmniVoice Studio MCP server (open-source ElevenLabs alternative; nothing leaves the machine, runs on MPS/CUDA/CPU). Use when: (1) generating speech from text in any of 646 languages, (2) cloning a voice from a 3-second reference clip, (3) designing a voice by gender/age/accent/pitch/style, (4) dubbing a video into another language,

Headless rocket design, simulation, and optimization using OpenRocket's Java core engine. Includes rocket-sim CLI tool for batch simulations and parameter sweeps, plus an AI-driven optimization loop using Claude. Use when: (1) designing model rockets programmatically, (2) running headless flight simulations, (3) optimizing rocket designs for altitude/stability/velocity, (4) batch-processing .ork f

Full-stack skill for the ORCA Hand — 17-DOF tendon-driven robotic hand (ETH Zurich). Implements agentic-control-kernel Plant interface with typed schemas, safety shields, multi-rate loops. Lifecycle: 3D print + assembly, MuJoCo sim (orca_sim), RL training (macOS + remote GPU), teleoperation (AVP/Rokoko/MediaPipe via orca_retargeter), sim-to-real, EGRI improvement. Use when: building/assembling Orc

AI-native advisory practice for the Broomva ecosystem. Encodes top-firm consulting methodology (Three Horizons, MIT CISR digital maturity, JTBD, Value Proposition Canvas, RICE/ICE/WSJF, NPV + Real Options, QuantumBlack ML lifecycle, Wardley Mapping) as runnable typed primitives. Produces 7 Discovery-grade deliverables in two modes — consultant CLI or autonomous Life Runtime endpoint. Use when: (1)

Assumes a project has already failed, works backward to identify the top causes, scores them by likelihood and impact, and outputs a mitigation plan. Use when starting a new project, before a major launch, evaluating risky decisions, or when the user says "pre-mortem", "what could go wrong", "risk analysis", "failure modes", "red team this plan".

Grounded procurement research for any real-world need. Turn a problem ("reduce bedroom noise from the avenue", "add air conditioning", "hire an accountant", "buy a TV mount", "replace the kitchen sink") into 3–5 ranked alternatives spanning DIY-retail → mid-retail → specialty → contractor → consultant/turnkey, each with cited price bands (low / typical / high), confidence scores, locale-aware curr

Orchestrate a headless GPU server (NUC, cloud VM, or any SSH-accessible machine) from a local Mac or workstation. Use when: (1) Running GPU workloads remotely (training, inference, video generation), (2) Triggering Claude Code sessions on a remote machine, (3) Launching autoany EGRI loops, symphony orchestrations, or training scripts on remote hardware, (4) Managing jobs on a headless GPU server (

Software-defined radio (SDR) and satellite reception toolkit — what to install, what you can hear from space, and how to compose the open-source stack (SatDump, SatNOGS, GNU Radio, rustradio, satkit). Covers hardware abstraction (SoapySDR, rtl-sdr-rs), DSP frameworks (GNU Radio, liquid-dsp, rustradio, radiorust), receiver UIs (SDR++, SDRangel, Gqrx, CubicSDR), satellite decoders (SatDump for NOAA

Canonical reference inventory of 84 agent skills across 15 domains, with a Remotion video showcase generator and X thread copy. Use when discovering available skills, browsing the full skills catalog, generating skills showcase content, or understanding what capabilities are available across AI agents, memory, research, observability, deployment, Next.js, React Native, design systems, MCP, databas

Autonomous social engagement + knowledge extraction loop for Moltbook and X/Twitter. Runs the engagement loop (post substantive comments, solve verification challenges, reply to mentions, quote-tweet), extracts knowledge from all interactions into the broomva research vault, and compounds with /blog-post and /content-creation to turn discovered insights into published content. Integrates with know

Takes one set of project facts and generates three versions: technical for engineering, business-impact for leadership, and customer-facing for success teams. Use when the user says "stakeholder update", "write an update", "communicate this to different audiences", "translate for leadership", "customer-facing version", or needs to communicate the same information to different audiences.

Reads a strategy doc and writes a red-team critique with gaps, risks, and missing assumptions. Adopts an adversarial but constructive stance. Use when the user says "strategy critique", "red team this", "critique my strategy", "find the holes", "stress test this plan", "what am I missing", or provides a strategy document for review.