Results for “vision-doc”

Translate visa application documents from images to English and generate a bilingual PDF with the original and translation side by side.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Configures a self-driving development loop for JavaScript/TypeScript projects, generating configuration files and preparing OpenTangl to run autonomously.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

Transform text plans into interactive visual documents with diagrams, code snippets, and review surfaces for coding agents.

Orquestrador do Time Reversa Docs. Gera um mini-site HTML autocontido em .reversa/documentation/ com arquitetura 3D, dashboards, glossário, deck e páginas por feature, a partir do conhecimento já extraído pelo core do Reversa. Ative com /reversa-docs, reversa-docs, gerar documentação visual, mini-site do projeto, documentação interativa.

The pre-share gate for a Superhuman Docs (Coda) document. Before a doc reaches a reader, run the QA checklist, choose the interaction mode, set the publish frame, and confirm the share. Catches the broken formula, the wall of text, the orphaned bullet, the missing cover, the wrong audience. Trigger on "is this doc ready to share", "publish this doc", "QA this doc", "ship-check", "final pass before I send", "which interaction mode", or any moment a Superhuman Doc is about to leave the building.

Builds Vue 3 components, composables, and Vite projects using JavaScript with JSDoc type annotations instead of TypeScript.

Scans repositories for markdown and HTML documentation, classifies files as repo-local or centralizable content, generates an inventory report, and optionally consolidates content into a centralized docs repository.

COCO: Microsoft COCO: Common Objects in Context

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Apply world-class developer documentation principles (Stripe, Snowflake, Databricks, TiDB Cloud) to structure, write, review, or refactor technical documentation. Use this skill whenever the user mentions documentation, docs, sidebar or navigation, information architecture, restructuring a section, writing or editing a guide, reviewing docs, where content belongs, English doc prose, headings, code comments, link text, docs home pages, section landing pages, long-form guides mixing content types, cross-referencing, or making docs readable for AI agents and LLMs. Covers VeloDB Cloud docs work (Monitoring restructure, sidebar, EN/中文 alignment, writing style, landing pages, LLM-friendly docs) and any SaaS or database documentation task. Trigger broadly: if the conversation touches doc organization, page structure, doc quality, doc sentences, landing pages, or AI-readable docs, consult this skill rather than answering from intuition.

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Author a new docs-native canonical or working document by choosing the correct location, filename, viewpoint template, metadata header, stable claims, and embedded rationale without creating spec.md.

Agent profile for inspect screenshots, viewports, layout overlaps, visual regressions, spacing, typography, and interaction states. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Creates, edits, and formats DOCX documents using OpenXML SDK (.NET) with CLI tools and C# scripts, supporting creation, content editing, and template application.

Ingest, index, search, edit, and generate video and audio assets from files, URLs, RTSP feeds, or desktop capture, with real-time alerts and stream links.

Document datasets, variables, sources, and merge keys for replication

Ingests video and audio from files, URLs, RTSP feeds, or desktop capture; indexes and searches moments with timestamps; transcodes, edits timelines, generates media assets, and creates real-time alerts for live streams.

Ingests video and audio from files, URLs, live feeds, or desktop capture; indexes and searches moments with timestamps; transcodes, edits timelines, generates media assets, and emits real-time alerts.

Bootstraps a two-part _docs directory (_build/ for technical docs, _public/ for research and proposals) with a CONSTITUTION.md governing the split, and can audit or migrate an existing structure.

Meeting to doc

LongVA: Long Context Transfer from Language to Vision

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.