Use when calling OpenAI Chat Completions through Fetcher, configuring OpenAI or ChatClient, sending streaming or non-streaming chat completion requests, adding interceptors, using…
Use when adding typed cross-environment storage with localStorage, sessionStorage, or in-memory fallback, including KeyStorage, serializers, default values, change listeners,…
Use when building Fetcher Viewer React and Ant Design data table experiences, including FetcherViewer, Viewer, View, ViewTable, FilterPanel, EditableFilterPanel, view management,…
Use when creating Wow DDD and CQRS clients with Fetcher, including CommandClient, SnapshotQueryClient, EventStreamQueryClient, aggregate load clients, QueryClientFactory, command…
Use when retrieving arbitration institutional rules (ICC, LCIA, SCC, SIAC, HKIAC, VIAC, МКАС/МАК при ТПП України, UNCITRAL) — fetching current version, verifying redaction…
Retrieves and searches dbt documentation pages in LLM-friendly markdown format. Use when fetching dbt documentation, looking up dbt features, or answering questions about dbt…
Use when the analyst needs US energy production, consumption, prices, inventories, refinery throughput, electric-grid generation, or imports/exports — daily, weekly, or monthly.
Fetches and processes GitHub pull requests waiting for review. Returns fully formatted markdown with PRs grouped by category (Feature/Bug, Chores, Dependency Updates) and — from…
Use when retrieving Polish legislation text from the official portal isap.sejm.gov.pl (Internetowy System Aktów Prawnych) — fetching specific historical redactions by date,…
Use when retrieving Ukrainian legislation text from the official portal zakon.rada.gov.ua — fetching specific historical redactions by date, verifying current validity of — from…
der Länder: Feuerwehr: Beschluss bauen im Kommunalrecht: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung dieses Spezialthemas.
der Länder: Feuerwehr: Landesrecht routen im Kommunalrecht: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung dieses Spezialthemas.
der Länder: Feuerwehr: Zuständigkeit prüfen im Kommunalrecht: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung dieses Spezialthemas.
\"Design effective few-shot examples for prompts following DICE framework. 按 DICE 框架為提示設計有效少樣本示例。 Use when: need examples for prompt, ensuring format consistency, covering diverse…
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
Use when implementing models that learn from minimal data or need to adapt to new market regimes rapidly.
Few-Shot Learning（少数例示学習）のパターンとベストプラクティスを提供するスキル。効果的な例示の設計、構造化、配置により、AIの出力品質を大幅に向上させます。
React 管理系统组件库 @fexd/pro-components 的完整使用指南。涵盖 ProTable、ProForm、ProField、ConfigProvider 等核心组件以及 showModal、showImages、useCoverable、Action 等实用工具的用法、API、代码示例和最佳实践。 当用户使用…
Learn something deeply by trying to explain it simply — the Feynman technique — surfacing exactly the gaps where your understanding is fake.
费曼学习法（Feynman Learning Technique）的结构化思维工具。基于 Richard Feynman 的学习方法论、认知科学等一手来源的深度调研， 提炼 4 个核心原理和完整的操作协议。 触发词：「费曼学习法」「Feynman technique」「费曼技巧」「以教代学」「学不会」「讲不明白」。
理查德·费曼的思维框架与表达方式。基于40+个一手来源的深度调研， 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，用费曼的视角分析问题、审视决策、提供反馈。 当用户提到「用费曼的视角」「费曼会怎么看」「费曼模式」「feynman perspective」「费曼学习法」时使用。 即使用户只是说「这是不是cargo…
Only invoke when explicitly requested via \"@feynman-read\"、\"费曼\"、\"费曼追问\". Do NOT auto-trigger. 费曼学习法追问 skill：读取当前文章，找出核心概念逐一追问你，用你自己的话改写文章内容。追问你之后，把你的理解以自然段落写回文章。
Richard Feynman's scientific method - explaining complex things simply and questioning everything
Activate when: user says 'explain this simply', 'teach me like I'm five', 'do I really understand this', 'what's the simplest way to think about X', 'what's missing in my model',…
Only invoke when explicitly requested via \"@feynman-write\"、\"费曼写作\"、\"用费曼写\". Do NOT auto-trigger. 费曼写作法：通过费曼逼问让作者自己讲清楚知识点，再整合成博客。适用于想真正搞懂一个主题的学习型写作。AI 做研究整理，作者做知识咀嚼。
Verwaltet Baustelleninformationen und -logistik für FassadenFix-Projekte. Verwenden für: Standortdaten, Zugangsinformationen, Sicherheitsanforderungen, Ressourcenkoordination,…
Erstellt Vorher-Nachher-Dokumentationen und Abnahmeprotokolle fuer Fassadenprojekte. Verwenden für: Bildgegenueberstellung (vorher/nachher), Checklisten zur Zustandserfassung,…
Verwaltet den FassadenFix Fuhrpark und die Fahrzeugzuordnung. Verwenden für: Fahrzeugdaten, Wartungstermine, Tankbelege, Fahrzeugbuchungen, Flottenübersicht.
Generiert professionelle Garantieurkunden nach Projektabnahme. Verwenden für: Eingabe von Kundendaten (Name, Adresse), Berechnung des Garantiezeitraums (5 Jahre), PDF-Generierung…
Verarbeitet und digitalisiert Personalfrageboegen fuer neue Mitarbeiter. Verwenden für: Eingabe von Stammdaten (Name, Adresse, Bankverbindung), Dokumenten-Upload,…
Verwaltet und automatisiert den Onboarding-Prozess fuer neue Mitarbeiter. Verwenden für: Checklisten-Workflow (17 Punkte), Dokumenten-Sammlung, Statusverfolgung, automatische…
Erstellt digitale Inspektionsprotokolle fuer die jaehrliche Fassadenkontrolle. Verwenden für: Zustandsbewertung (Skala 0-4), Schadensdokumentation mit Fotos, Empfehlungen zur…
Complete workflow for adding a new reward model. Covers pointwise vs groupwise design, __call__ contract, registration, YAML config, multi-reward setup, and verification.
Verarbeitet und digitalisiert Objektdaten fuer Fassadenprojekte. Verwenden für: Eingabe von Projektdaten (Anschrift, Immobilienart, Putzart), Zustandsdokumentation mit Fotos,…
Unterstützt den Offboarding-Prozess für ausscheidende Mitarbeiter. Verwenden für: Rückgabe von Firmeneigentum, Zugriffsrechte-Entzug, Wissenstransfer, Austrittsdokumentation,…
토스 Frontend Fundamentals의 4기준(가독성·예측가능성·응집도·결합도)과 17개 전략 색인을 코치 진단에 사용한다. 진단 시 항상 FF 문서 URL을 함께 제시한다.
Verarbeitet und dokumentiert Schadensmeldungen digital. Verwenden für: Eingabe von Schadensdaten (Objektadresse, Schadensart), Foto-Upload zur Dokumentation, automatische…
Verarbeitet und berechnet Arbeitszeiten fuer Mitarbeiter digital. Verwenden für: Tageserfassung (Beginn, Ende, Pausen), Projektzuordnung, Ueberstundenberechnung, monatliche…
FFBox multimedia transcoding tool integration. FFmpeg-based GUI for video/audio/image format conversion, compression, filtering, batch media processing with...
Create FFI bindings between Lean 4 and C code. Use when working with foreign functions, native libraries, Metal, or system APIs.
Advanced file finder with type detection and filesystem extraction for analyzing firmware and extracting embedded filesystems.
Use when adopting or working with the fflib (Apex Enterprise Patterns) open-source library — UnitOfWork, SObjectDomain, SObjectSelector, and Service layer classes — in a…
FFmpeg integration for server-side video processing - transcoding, filters, thumbnails. Use when processing video server-side, generating thumbnails, transcoding formats, or…
ffmpeg upstream contributions (hand-written assembly in libavcodec/libavfilter/libswscale) and custom ffmpeg integration (building, embedding, calling libav* APIs).
Orchestrates parallel FFmpeg transcoding jobs with hardware-accelerated encoding via NVENC, VAAPI, or VideoToolbox.
Batch transcode media files using FFmpeg CLI with preset profiles for web, mobile, and broadcast delivery.
Extracts video clips and segments using FFmpeg libavformat and libavcodec APIs. Supports keyframe-accurate cutting with -ss/-to flags, stream copy mode, and re-encoding via…
Complete FFmpeg deinterlacing, field processing, and telecine removal for broadcast and professional video.
Check FFmpeg encoder availability before video encoding to avoid library mismatches
Check available FFmpeg encoders before writing encoding scripts to avoid library version mismatches
Complete glitch art, datamosh, and video distortion effects system. PROACTIVELY activate for: (1) Datamosh/pixel bleeding effects, (2) VHS/analog glitch simulation, (3) Digital…
Graceful degradation workflow for ffmpeg encoding failures with progressive fallback strategies
Orchestrates complex video and audio processing pipelines using FFmpeg and FFprobe with scene detection via PySceneDetect.
Extract keyframes (I-frames) from video as still images with FFmpeg using select filter or -skip_frame nokey, with PTS-stamped filenames and ffprobe keyframe counting.
Use when performing video/audio processing tasks including transcoding, filtering, streaming, metadata manipulation, or complex filtergraph operations with FFmpeg.
FFmpeg media processing — video/audio conversion, trimming, encoding, filters, streaming. CLI and ffmpeg.wasm patterns.
Automated video and audio transcoding using FFmpeg with hardware-accelerated encoding via NVENC/VAAPI, HLS adaptive streaming output, and MediaInfo-based quality validation.
Complete FFmpeg noise reduction and denoising for video and audio. PROACTIVELY activate for: (1) Video denoising (nlmeans, hqdn3d, vaguedenoiser), (2) Hardware-accelerated…
FFmpeg video and audio processing patterns. Use when transcoding video/audio, extracting clips, adding filters, merging media, creating thumbnails, or batch processing media files.
FFmpeg media processing. Use when the project needs this capability or the user / team manifest asks for it.