Ensure designs specify failure modes, timeouts, error contracts, and observability for critical flows.
Audit all failure paths, edge cases, and non-happy-path states -- empty states, validation errors, permission failures, loading, undo, and recovery.
Audit failure paths and create Beads issues from the findings. Converts unhandled failure states, missing empty states, and broken recovery paths into trackable Beads tasks with…
What happens when an agent fails — retry, fallback, escalate, or graceful degradation.
Use when a test, build, install, CI job, tool call, or repeated attempt fails and the task must continue reliably.
Trigger: empty list state, loader skeleton, error boundary layout, offline indicator, system fallback UI. Scope: UI fallback layouts, skeleton placeholders, client recovery views.
Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.
BA Core: Planning, elicitation, requirements lifecycle, strategy analysis, solution evaluation. 21 methodologies.
BA Modeling: Use cases, user stories, process models (BPMN), data models, decision tables, interfaces, acceptance criteria. 7 methodologies.
Backend orchestrator: coordinates systems (Go, Rust, DB) and enterprise (Java, C#, PHP, Ruby).
LLM APIs: OpenAI, Claude, Gemini, local LLMs, prompt engineering, function calling.
Creates, edits, updates, or modifies Claude Code custom agents (subagents). Use when user asks to create agent, edit agent, update agent, subagent.
ML operations: fine-tuning (LoRA, QLoRA), model evaluation, cost optimization, observability.
Multimodal AI: vision, image/video generation, speech-to-text, text-to-speech, voice synthesis.
RAG engineering: embeddings, chunking, vector databases, hybrid search, reranking.
SDD execution: quality gates, reflexion learning, pattern/mistake memory, code review.
Audit manuscript and replication package against FAIR open-science principles.
Fair Disclosure und Knowledge-Qualifikation in M&A-Vertraegen: Anwendungsfall Vertragsparteien verhandeln Wissenszurechnung, Kenntnis-Definitionen und Fair-Disclosure-Mechanismus…
Für Fair Disclosure und Knowledge Management: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Corporate-Kanzlei.
Für Fair Disclosure und Knowledge: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Mittelstands-Corporate/M&A.
Create FAIR-minded reproducibility bundles for materials simulations by collecting input/output file inventories, hashes, units, engine versions, structure identifiers,…
Divide things that cannot be divided — an inherited house, a dissolved partnership, the furniture after a breakup — using sealed-bid fair division (Knaster), computed by the…
Drafts FRCP 23(e)-compliant class action fairness hearing notices. Extracts settlement terms, class definition, deadlines, and court-mandated language from case documents to…
Solana wallet reputation. Ask anything in plain English — "is this a bot?", "whale?", "diamond hands?" — get instant answers.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HN — from…
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HN — from…
Navigate questioning, leaving, or changing your religion — especially a high-control or all-encompassing one — with the relationship-preservation scripts for family who stayed, a…
Für Fake-Shop und Chargeback: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
VN-realistic seed data via @faker-js/faker + custom VN pools (names, addresses, phones, VND, product categories).
Använd när hon vill bygga, fylla på eller rätta sin faktabank – det alla CV och brev hämtar från. Till exempel "lägg in mitt gamla CV", "här är min LinkedIn-export", "jag vill…
Prüft unzitierte Tatsachenbehauptungen über die reale Außenwelt – Produkte, Institutionen, Zahlen, Funktionsansprüche –, die keine Quellenangabe tragen und deshalb für Teil-Check…
Für Faktencheck Quellenmatrix: ordnet Akte, Belege und Lücken; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Faktoora integration. Manage Organizations. Use when the user wants to interact with Faktoora data.
Use when creating a static digital DIN A1 portrait poster as editable HTML in the design of the Fakultät für Sportwissenschaft, including event, number, image, quote, closing, or…
Prüft Zuständigkeit von Fakultätsrat, Dekanat, Senat und Präsidium im Hochschulrecht Länder.
Search, explore, and run fal.ai generative AI models (image generation, video, audio, 3D). Use when user wants to generate images, videos, or other media with AI models.
Generate 3D models from text or images. Use when the user requests "Create 3D model", "Text to 3D", "Image to 3D", "3D generation", "Generate mesh", "3D asset".
Generate images, videos, and audio with fal.ai serverless AI. Use when building AI image generation, video generation, image editing, or real-time AI features.
Generate/edit images via fal.ai. Supports Google Nano Banana Pro and OpenAI GPT Image 2 selected from config/.env. Supports reference images and strong text rendering.
Generate game assets with fal (fal.ai) through the fal MCP server, the `um fal` CLI (REST) or `fal api`.
Text-to-speech and speech-to-text using fal.ai audio models. Use when the user requests "Convert text to speech", "Transcribe audio", "Generate voice", "Speech to text", "TTS",…
审计 fal 账号消耗与用户扣费的一致性。查询 fal 官方账单，交叉比对 fal_tasks 中的用户消耗，汇总积分/现金明细，检测异常。当用户提到"消耗审计"、"账单核对"、"fal 对账"、"用量异常"时使用此 skill。
Generate images and videos using fal.ai AI models with queue support. Use when the user requests "Generate image", "Create video", "Make a picture of...", "Text to image", "Image…
Edit images using AI on fal.ai. Style transfer, object removal, background changes, and more. Use when the user requests "Edit image", "Remove object", "Change background", "Apply…
Complete fal.ai image-to-image system. PROACTIVELY activate for: (1) FLUX image-to-image transformation, (2) ControlNet (canny, depth, pose), (3) Inpainting with masks, (4)…
Complete fal.ai image-to-video system. PROACTIVELY activate for: (1) Kling 2.5/2.6 Pro image animation, (2) MiniMax Hailuo with prompt optimizer, (3) LTX image-to-video, (4)…
Create talking head videos, lip sync audio to video, and animate portraits with expressions. Use when the user requests "Talking head", "Lip sync", "Make this person talk",…
获取 fal.ai 模型系列的所有变体及其 llms.txt 链接。当用户提供 fal.ai 模型链接并要求获取 llms.txt、查看模型文档、或查看模型变体时使用此 skill。
Complete fal.ai model selection system. PROACTIVELY activate for: (1) Choosing image generation models (FLUX, SDXL), (2) Choosing video models (Kling, Sora, LTX), (3) Choosing…
fal.ai Platform APIs for model management, pricing, usage tracking, and cost estimation. Use when user asks "show pricing", "check usage", "estimate cost", "setup fal", "add API…
Real-time and streaming AI image generation — instant results for interactive use. Use when the user requests "Real-time generation", "Fast generation", "Streaming image",…
Restore and fix image quality — deblur, denoise, dehaze, fix faces, restore documents. Use when the user requests "Fix blurry image", "Remove noise", "Fix face", "Restore photo",…
Complete fal.ai text-to-image system. PROACTIVELY activate for: (1) FLUX.1/2 Pro/Dev/Schnell generation, (2) SDXL and Fast SDXL, (3) Image size presets (square_hd,…
Generate, remix, and edit images using fal.ai's AI models. Supports text-to-image generation, image-to-image remixing, and targeted inpainting/editing.
Complete fal.ai text-to-video system. PROACTIVELY activate for: (1) Kling 2.0/2.5/2.6 Pro video generation, (2) Sora 2 for creative videos, (3) LTX Video with audio, (4) Runway…
Train custom AI models (LoRA) on fal.ai — personalize image generation for specific people, styles, objects, or video generation.
Virtual try-on — see how clothes look on a person. Use when the user requests "Try on clothes", "Virtual try-on", "How does this look on me", "Fashion try-on", "Garment transfer".
Upscale and enhance image resolution using AI. Use when the user requests "Upscale image", "Enhance resolution", "Make image bigger", "Increase quality", or similar upscaling…
Analyze images using AI — segment objects, detect objects, extract text (OCR), describe images, ask questions about images.
Generate production-ready fal.ai workflow JSON files. Use when user requests "create workflow", "chain models", "multi-step generation", "image to video pipeline", or complex AI…