Decide o paradigma alvo do produto novo a partir de domínio, restrições e maturidade da equipe. Espelho à frente do Paradigm Advisor do Reversa — onde o Reversa detecta o…
Revisão cruzada de todas as specs geradas. Detecta contradições, gaps de cobertura entre dores e specs, hipóteses 🔴 que escaparam, e prepara material para handoff.
Skill de entrada para qualquer trabalho de integração com a API da Tray. Estabelece as regras invariantes da plataforma (OAuth como query param, payloads envolvidos na chave do…
Visa, Expatriate-Recht und Entsendung nach China: Arbeitserlaubnis und Residence Permit (Punkte-System CN seit 2017), Entsendungsvertrag DE-CN…
Für Visby: Compliance-Dokumentation und Aktenvermerk: ordnet Akte, Belege und Lücken; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Persona boot overlay for Vishwakarma. Loaded at boot step 7 when willow-2.0-active-persona is set to "vishwakarma".
Audit a brand's AI visibility, sentiment, response volume, mentions, and competitor trend in Promptwatch.
checks whether published content is being cited or surfaced by ChatGPT, Gemini, Perplexity, Google AI Overviews, and adjacent answer engines.
VisibleThread integration. Manage data, records, and automate workflows. Use when the user wants to interact with VisibleThread data.
Visily is an AI design canvas that turns text prompts, screenshots, URLs & more into UI designs that are as easy to edit as a Google Slide.
UI/UX creative direction, complete redesign, new design, and trend application. Use when design direction decisions, Design System construction, or orchestration of…
Analyze images using GPT-4o Vision through the verging.ai proxy API, supporting both image URL (JSON) and file upload (multipart) modes.
Design the intelligence system's future state in experiential terms — not feature lists but what it's like to interact with this intelligence.
Use when articulating internal vision — where we're going / why now / why us, founder-mode anchor, distinct from fundraising pitch.
Audit project alignment with VISION.md, identify SDLC gaps, and generate feature proposals. Use when reviewing strategic direction or planning new features.
Скилл для формирования чёткой визии проекта и генерации всей базовой документации. ОБЯЗАТЕЛЬНЫЕ ТРИГГЕРЫ: "сформируй визию", "создай визию", "визия проекта", "формируем проект",…
Check VisionSqueezer installation health and version status. Detects the installed binary or MCP-registered command, parses the pinned npx version, compares against the latest npm…
Specialized instructions for Z.AI Vision MCP to handle UI-to-Code and error diagnosis.
终局愿景探索。用户抛出一个模糊 idea，AI 主导引导，通过"追问价值 → 挖掘动机 → 推导演化 → 画终局"的链路，帮用户看到未来最远的可能性。不设限，不收敛，纯发散。
Transcribe scanned page images into per-page + combined Markdown source text for induction, via a provider-neutral vision adapter (codex CLI or a generic command template for…
Assembles a domain-by-domain life scorecard with score (1-10), trend indicator, open loop count, and 1-line status per installed plugin.
Drafts next quarter's OKRs based on current domain scores, open milestones, and life vision priorities. Identifies 3-5 priority domains and proposes 2-3 key results per domain.
Evaluates progress toward quarterly OKRs across all domains; calculates percent complete per key result and flags OKRs at less than 50% with less than 2 weeks remaining in the…
Image understanding guidance for agents with vision enabled. Instructs agents to use read_file for viewing images directly instead of writing OpenCV/PIL code to parse them…
Vision Helpdesk integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vision Helpdesk data.
GPT-5/4o, Claude 4.5, Gemini 2.5/3, Grok 4 vision patterns for image analysis, document understanding, and visual QA.
让 agent 用桌面软件（macOS / Windows）时**性能更高、长期成本更低**的 skill。 核心机制：把每次视觉操作的路径（截图、估坐标、AX/OCR、点击序列）沉淀成可复用的 vision-mcp.yaml map；下次同任务直接 `run_workflow` 命中，跳过看图估坐标， ~5 步操作从分钟级降到秒级、context…
December annual life review; retrospective on goals achieved across all domains, life vision document refresh, and next year's priority targets.
Monthly life scorecard; scores each active life domain (1-10) based on open loops resolved, goals on pace, and positive milestones.
Structured quarterly planning session. Reviews prior quarter OKRs, runs a retrospective, and sets new OKRs for the next quarter aligned to the life vision.
Monthly vision review brief. Compiles 13-domain life scorecard, top 3 at-risk goals, and alignment flags into a single strategic briefing.
Use when a task needs the judgment of a vision rehabilitation therapist / orientation and mobility specialist / low vision therapist — running a functional vision assessment,…
Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.
Create a vision statement with structured process, quality checks, and system integration
Show VisionSqueezer cumulative token & byte savings analytics. Zero MCP overhead — reads directly from local stats.db via CLI binary.
High-level orchestrator (the supervisor above vision-orchestrator). Holds the WHOLE vision + WHOLE backlog and grooms it so the per-task executor always has a small,…
Tag and annotate images using Apple Vision framework (macOS only). Detects faces, bodies, hands, text (OCR), barcodes, objects, scene labels, and saliency regions.
Writes a stalled goal flag to vault/vision/open-loops.md when a goal has had no progress for more than 42 days.
Records a life milestone to vault/vision/00_current/ with domain, description, date achieved, and notes.
Writes all vision flags (stalled goals, OKRs off-pace, domain score declines) to vault/vision/open-loops.md and resolves completed items.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — from…
Guide for using vision utilities in speedy_utils, including fast GPU image loading, memory-mapped datasets, and notebook visualization.
Parses and analyzes project vision to extract structured requirements. Use at project start to understand goals, scope, and constraints.
Vision6 integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vision6 data.
Generate images and videos via Agnes AI. Triggers on any request to create, draw, render, design, edit, restyle, or animate visual content — pictures, posters, illustrations,…
Apple Human Interface Guidelines for Apple Vision Pro. Use when building spatial computing apps, implementing eye/hand input, or designing immersive experiences.
Native visionOS spatial computing, SwiftUI volumetric interfaces, and Liquid Glass design implementation
Use when reviewing changed email templates in a PR or branch, or spot-checking a specific email file.
Nutzt die Lobbyregister-Visitenkarte, Registerauszug und interne Nachweise für Kontaktaufnahme, Hausausweis, Anhoerung und Compliance-Akte. Output Nachweispack.
Visitor Queue integration. Manage data, records, and automate workflows. Use when the user wants to interact with Visitor Queue data.
Automate Visme tasks via Rube MCP (Composio). Always search tools first for current schemas. — from general/automation
Search and recommend real fashion products and brands across thousands of online stores via the Vistoya MCP.
Use when visual work needs art-direction judgment, AI-image prompt shaping, candidate critique, asset / animation pass selection, promotion decisions before runtime…
Run this as the FINAL review step once you have finished a UI change you can load in a browser — it is the visual-regression gate, run once at the end (not after every edit), and…
Assert that a page or element still looks right with Biloba's Go/Gomega visual regression matcher (b.HaveScreenshot) — writing the assertion, the golden-master workflow for…
Use when MySocialsAssistant needs to define the visual asset required for Instagram or other visual-first publishing, including image, graphic, carousel, reel cover, or visual…
Generate distinctive educational visuals using creative brief methodology. Use when creating chapter illustrations, diagrams, or teaching visuals with Gemini.
Create and manage visual assets. Use when creating graphics, icons, or images. Covers asset formats and optimization.
Generate visual assets (ASCII art, diagrams, banners) for repos and documentation
Author the visuals for HCI lessons — `:::diagram` blocks (rendered at runtime with Mermaid) and `:::animation` blocks (self-contained HTML played in a sandboxed iframe).