dabit3
- 168 skills
- 0 followers
- 4 hours ago last updated
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Comfyui · dabit3 bundleGenerate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
- ▌
- ▌
- ▌ Inference Sh CLI · dabit3 bundleRun 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
- ▌ Clip · dabit3 bundleOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
- ▌ Peft Fine Tuning · dabit3 bundleParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
- ▌
- ▌ Faiss · dabit3 bundleFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
- ▌ Llava · dabit3 bundleLarge Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
- ▌ Modal Serverless Gpu · dabit3 bundleServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
- ▌ Simpo Training · dabit3 bundleSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
- ▌ Slime Rl Training · dabit3 bundleProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
- ▌
- ▌
- ▌ Chroma · dabit3 bundleOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
- ▌ Qdrant Vector Search · dabit3 bundleHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
- ▌
- ▌ Sparse Autoencoder Training · dabit3 bundleProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
- ▌ Whisper · dabit3 bundleOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
- ▌ Guidance · dabit3 bundleControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
- ▌ Pinecone · dabit3 bundleManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
- ▌ Instructor · dabit3 bundleExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
- ▌ Distributed LLM Pretraining Torchtitan · dabit3 bundleProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
- ▌
- ▌ Dcf Model · dabit3 bundleBuild 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.
- ▌ Lambda Labs Gpu Cloud · dabit3 bundleReserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
- ▌
- ▌ Nemo Curator · dabit3 bundleGPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
- ▌ Tensorrt LLM · dabit3 bundleOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
- ▌
- ▌
- ▌
- ▌
- ▌ Stable Diffusion Image Generation · dabit3 bundleState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
- ▌
- ▌
- ▌ Searxng Search · dabit3 bundleFree meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.
- ▌ Docker Management · dabit3Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.
- ▌
- ▌
- ▌ Duckduckgo Search · dabit3 bundleFree web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime.
- ▌ Huggingface Tokenizers · dabit3 bundleFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
- ▌
- ▌ Testing Vending Machine · dabit3Run and test the Vending Machine app locally (Next.js + Convex + Clerk). Use when verifying admin flows like creating/deleting events, or setting up an authenticated admin session for testing.
- ▌ Cloud Stacked Diffs · dabit3 bundleDeliver multi-step work as a chain of stacked draft pull requests — one branch per step, each branching from and targeting the previous step's branch. Use when the user asks for stacked PRs or stacked diffs, a PR stack or chain, incremental step-by-step review, or wants a large task split into small dependent PRs. Also use when updating, rebasing, or addressing review feedback on any PR that belongs to an existing stack (chained branches, e.g. stack/<name>/NN-* or feature/NN-*). Especially suited to cloud/background coding agents delivering large autonomous changes as reviewable increments.
- ▌ Liquid Glass · dabit3 bundleBuild and migrate websites and web apps with the Liquid Glass design language using HTML, CSS, and JavaScript. Use when creating glass/translucent UI on the web, applying backdrop-filter glass surfaces, glass navbars, glass tab bars, glass dialogs and bottom sheets, morphing transitions with the View Transition API, SVG refraction filters, or any liquid-glass / glassmorphism UI work. Also use when the user asks about frosted glass effects, translucent navigation layers, backdrop-filter best practices, or bringing Apple-style Liquid Glass to the web.
- ▌ Lightning · dabit3Use the active model as a lean planner and reviewer while SWE-1.7 Lightning executes concrete software-engineering work.
- ▌ Google Meet · dabit3 bundleJoin 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.
- ▌
- ▌
- ▌ Pretext · dabit3 bundleUse when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Fastmcp · dabit3 bundleBuild, 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.
- ▌ Kanban Worker · dabit3Pitfalls, examples, and edge cases for Sonic Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
- ▌
- ▌
- ▌ Mcporter · dabit3Use 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.
- ▌ Qmd · dabit3Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Audiocraft Audio Generation · dabit3 bundleAudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
- ▌
- ▌ Agentmail · dabit3Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. sonic-agent@agentmail.to).
- ▌ Macos Computer Use · dabit3Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the `computer_use` tool is available.
- ▌ Huggingface Accelerate · dabit3 bundleSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
- ▌
- ▌
- ▌
- ▌ Plan · dabit3Plan mode: write an actionable markdown plan to .sonic/plans/, no execution. Bite-sized tasks, exact paths, complete code.
- ▌ Solana · dabit3 bundleQuery 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.
- ▌ Lbo Model · dabit3Build 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.
- ▌
- ▌
- ▌ Sherlock · dabit3OSINT username search across 400+ social networks. Hunt down social media accounts by username.
- ▌
- ▌
- ▌ Touchdesigner MCP · dabit3 bundleControl a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
- ▌ Kanban Orchestrator · dabit3Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
- ▌