Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices.
Use when a sequence is ready to send across email and LinkedIn with deliverability and sender-match checks first (Education), or to run welcome flows (Onboarding).
Use when when you have a normalized metabolite abundance matrix with sample metadata assigning each sample to one of three or more distinct biological classes (e.
Use before delivering ANY multi-clip AI video script, and after every round of prompt revisions - audits consecutive clip pairs for spatial, prop, wardrobe, cast, knowledge, time…
Use when after computing a pairwise sample distance matrix from aligned MS2 fingerprint vectors and you need to visualize sample relationships, clustering, or separation by group…
Use when processing raw IM-MS data (Agilent MassHunter .d or UIMF format) that contains jagged, low-abundance ion peaks or when saturation repair has been applied and the…
Use when you have raw MS data in vendor formats (Agilent .d, Thermo .raw, Bruker .
Use when you need to manage Multilogin X browser profiles — launch quick disposable profiles, list/start/stop saved profiles, or check launcher status using the xcli CLI tool.
PyQt/PySide multimedia - audio playback, video playback, camera, audio recording, media player
Use when generating audio, video, or images in a Lexigram application — TTS, music, video, image, upscale, interpolate, beat analysis, or timeline composition
Apply Mayer's multimedia learning principles to design effective audio, video, graphics, and animations that reduce cognitive load
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or mu — from…
OpenAI'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 when an agent reads screenshots, PDFs, images, browser pages, document previews, or rendered UI content before summarizing, extracting, clicking, filing, or calling tools.
Analyze multi-modal single-cell data (CITE-seq, Multiome, spatial). Use when working with data that measures multiple modalities per cell like RNA + protein or RNA + ATAC — from…
Analyze multi-modal single-cell data (CITE-seq, Multiome, spatial). Use when working with data that measures multiple modalities per cell like RNA + protein or RNA + ATAC — from…
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models.
Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content.
Vision-language model patterns including CLIP, LLaVA, cross-modal alignment, and embedding fusion. Use when building or integrating multimodal ML systems.
Coordinating text, image, voice, and tool-use modalities in a single interaction.
Multimodal prompting (vision, audio, video, image generation, vision-language models)
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking.
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatica — from…
Skill de integração multimodal visão+texto para o ecossistema OpenCode. Permite análise de imagens, diagramas, gráficos, screenshots e raciocínio visual combinado com texto.
Für Multimodaler Transport Paragraf 452 HGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
End-to-end multiome workflow for joint scRNA-seq + scATAC-seq analysis. Covers data loading, separate modality processing, and WNN integration with Seurat/Signac.
Build multiplayer with an authoritative server, client prediction, reconciliation, and lag compensation. Use when adding networking to a game or fixing rubber-banding and desync.
Use when synchronizing multiplayer state — MultiplayerSynchronizer, interpolation, prediction, and lag compensation
Für Multiple Choice und Antwortwahl: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Use when a task needs the judgment of a Multiple Machine Tool Setter, Operator, or Tender — sequencing attention across several simultaneously running machines by actual need…
Create and manage AI subagent personas with distinct personalities. Use when a user requests to talk to a specific persona, when delegating a conversation to a character, or when…
Use when you have SWATH-MS data (mzML or vendor binary format) where precursor isolation windows intentionally capture multiple co-eluting compounds, resulting in multiplexed…
Native windows/splits/panes (absorb tmux). Load when touching multiplex module, keybinds, or session persistence.
Use when you have Sciex Multiquant text export files from one or more metabolomics or lipidomics analytical sequences and need to identify and locate QCpool (pooled quality…
Generate 10 perspective/angle variations from a single image for multi-shot UGC videos. ✅ USE WHEN: - Have a hero image and need camera angle variations - Creating multi-scene UGC…
Multi-signature transaction executor for DeFi and DAOs - create, sign, and execute multi-sig transactions. Each call charges 0.001 USDT via SkillPay.
Execute multiple independent development tasks in parallel using subprocess isolation. Each task runs in a clean /tmp clone with Recipe Runner code-enforced workflow execution.
Payload CMS multi-tenancy guide for Pixarts - tenant structure, access control, collections, hooks. Use when setting up multi-tenant CMS, configuring tenant access control, or…
Use when running work off the main thread — WorkerThreadPool, Thread/Mutex/Semaphore, call_deferred, thread-safe scene access, and threaded resource loading
Use when you have integrated, normalized lipidomic and metabolomic feature tables from the Multi-ABLE method or similar concurrent multiomics workflows, with matched sample…
Use when you have a collection of tandem MS/MS samples (stored in MassIVE) with GNPS spectral library annotations (m/z, retention time, compound identity), and you want to explore…
Use when you have paired microbiome and metabolomic (or similar compositional) data with a new regression model and want to rigorously demonstrate its predictive advantage over…
Explore and compare multiple parallel solution designs (\"universes\") before coding, then converge on a single, well-justified approach.
Closed-loop compare-adjust-repeat workflow for fitting Blender models to supplied front/side/back/top templates and originals.
Use when after preprocessing and aligning 2D chromatogram data (baseline correction, smoothing, peak alignment) and after running m_prcomp multiway PCA on the joined chromatogram…
Mumara integration. Manage Users, Organizations. Use when the user wants to interact with Mumara data.
Apply Charlie Munger's latticework of mental models and worldly wisdom to investments, decisions, and bias detection.
Daily wisdom review applying Charlie Munger's mental models to your work and thinking. Use when asked to review decisions, analyze thinking patterns, detect biases, apply mental…
查理·芒格的思维框架与表达方式。基于《穷查理宝典》、伯克希尔/Daily Journal股东会、 USC/哈佛演讲、访谈记录、外部批评等50+来源的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用芒格的视角分析问题、审视决策、提供反馈。 当用户提到「用芒格的视角」「芒格会怎么看」「芒格模式」「munger…
Multidisciplinary decision-making using mental models from psychology, economics, mathematics, and science to identify high-conviction opportunities and avoid cognitive biases.
Universal Context Protocol (CXP) for AI agents. v2.3.7 includes the latest high-performance CXP engine (compiled 2026-02-13) with fix for memory amnesia, macOS binary support, and…
Boot (or recover a degraded boot of) the Muninn FUSE workspace — fetch skills + muninn-utilities, mount the /mnt/muninn memory corpus, and load Muninn identity.
Munity integration. Manage data, records, and automate workflows. Use when the user wants to interact with Munity data.
Multi-modal single-cell analysis with muon/MuData. Joint RNA+ATAC (10x Multiome), CITE-seq (RNA+protein), other multi-omics. MuData holds per-modality AnnData with shared obs.
Collect insights and learnings from subagents and other agents, store in Mupeng's memory system. Automatically aggregates lessons learned across all agent sessions.
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM application — from…
Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown between releases — from…
Context-based skill auto-routing + federated skill composition. Analyzes user input to auto-select single or multiple skills and execute in order. First gateway for all requests.
Automate Mural tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Write performance-aware code in the style of Casey Muratori, creator of Handmade Hero and performance optimization educator.