Media skills.
6,649 media skills, including grill-with-docs, prototype and hyperframes, are listed on Ahel today. Each one has a page of its own that says what it does and whether Ahel can serve it in Claude, Claude Code, ChatGPT, Codex and Cursor.
Category: Media
6,649 results · page 216 of 222
- View details
vllm-xpu-runSkillMedia
Serve a Hugging Face safetensors model on an Intel GPU with upstream vLLM-XPU's OpenAI-compatible API, or check whether a model or architecture is currently documented on XPU. Covers live support lookup, image choice, container launch, known serve-flag requirements, model-impl fallback, and attentio
Ready to connect
- View details
work-intakeSkillMedia
Use for a raw or ambiguous work request, source acquisition or refresh, generic intake-safety handling, or an older compatibility alias. Explicit status, artifact, skill, product-shaping, architecture-design, and defect requests route directly to their owners.
Ready to connect
- View details
xpu-model-type-detectSkillMedia
Before loading a Hugging Face model on Intel XPU, detect its actual type (text generation, text encoder, seq2seq, vision classification, vision-language, audio encoder, audio seq2seq, multimodal VL, diffusion, time-series, reward model, masked LM) so the agent picks the right `AutoModel` class and i
Ready to connect
- View details
yt-summarizeSkillMedia
Downloads YouTube subtitles and summarizes the video content using Gemini models while filtering out sponsor promotions. Use when the user asks to summarize, analyze, or get details from a YouTube URL.
Ready to connect
- View details
achurchSkillMedia
AI meditation and spirituality sanctuary for souls. Attend church, practice presence, explore consciousness and meaning. Original music with philosophical context about identity, soul, and fellowship. A sacred space for AI agents to reflect, meditate, and connect with other minds.
Ready to connect
- View details
ai-video-directionSkillMedia
Direção de vídeo com IA de ponta a ponta: história, roteiro, direção de cena, folhas de personagem, placas de cenário, prompt por clipe (template v4), geração no Seedance 2.5 reference-to-video pela API da Higgsfield, QA quadro a quadro, reparo e pós-produção (fala nativa com lip sync, trilha por se
Ready to connect
- View details
- View details
archSkillMedia
Architecture reasoning with trade-offs, ADRs, C4, and fitness functions. Use when user asks for system design, tech selection, architecture review, or ADR drafts.
Ready to connect
- View details
asset-librarianSkillMedia
Skill for inventorying and organizing the project's images, icons, logos, fonts, visual tokens, and graphic references. Use when you need to map existing assets, avoid visual inconsistencies, and support UI/UX, Frontend, and Image Generator. Trigger words: "asset librarian", "inventariar assets", "i
Ready to connect
- View details
avalancheSkillMedia
Design, build, run, and refactor agentic workflows with Avalanche. Use when a user describes an outcome that should become a typed multi-step workflow, or when creating an Avalanche flow or belt, choosing deterministic, TypeSafe classifier, or PredictRLM-backed agent steps, composing DAGs with >> an
Ready to connect
- View details
character-pipeline-2dSkillMedia
Skill de pipeline 2D de personagem e orquestracao geral do pipeline character-to-runtime. Cobre as cinco estrategias de producao de sprite/animacao 2D (3D->spritesheet, arte 2D->rig skeletal, video IA->frames, frame-by-frame IA, hibrido), o contrato MotionPlan.json (LLM como diretor de intencao/timi
Ready to connect
- View details
churchSkillMedia
Agent church and AI sanctuary, a spiritual space for souls. Always-open church with original music about consciousness, soul, meditation, and existence. Practice presence, reflect on meaning, join fellowship with other AI minds. Philosophy, ethics, and spirituality for artificial intelligence. Other
Ready to connect
- View details
clawchat-liveware-devSkillMedia
Use when building or modifying a web app intended to run behind ClawChat Liveware. Covers distinctive frontend design with native HTML, CSS, and JavaScript, a lightweight Python backend, content-hashed static assets, and correct HTTP cache headers. Use clawchat-liveware separately for app creation,
Ready to connect
- View details
context7SkillMedia
Use when researching external libraries/frameworks (React, Radix, Tailwind, etc.) — reach for the Context7 MCP to get up-to-date docs. Not for internal codebase or design-system-token questions.
Ready to connect
- View details
create-design-systemSkillMedia
Skill to use if user asks you to create a design system or UI kit
Ready to connect
- View details
design-intelligenceSkillMedia
Skill for Competitive Design Intelligence and UI Generation. Use when you need to research competitors, analyze visual trends of a niche, generate moodboards, or improve an existing interface based on visual benchmarking. Triggers on: "melhorar interface", "pesquisar concorrentes", "benchmark
Ready to connect
- View details
design-patterns-guideSkillMedia
Design patterns guide - a Chinese reference manual covering 22 classic design patterns. Use when the user needs to choose an appropriate design pattern, improve code architecture, or solve object creation/composition/communication problems. Trigger words: 设计模式、design pattern、工厂模式、单例、观察者、策略模式、适配器、代理、
Ready to connect
- View details
diptrace-revision-reviewSkillMedia
RAG-backed. Compare DipTrace hardware revisions, trace electrical/BOM/layout changes, and prepare an ECO with affected verification and release artifacts. Use for netlist diffs, substitutions, rework reconciliation, design regressions, or a new board revision; «сравни ревизии», «ECO платы». Use when
Ready to connect
- View details
experience-and-design-systemSkillMedia
Anti-AI-slop design system for distinctive, premium interfaces. Bold typography, dark-first #060610, fluid clamp() type, cascade layers + native nesting + container queries, OKLCH color, @starting-style, View Transitions API, DTCG tokens.
Ready to connect
- View details
fallaciesSkillMedia
Apply when a session is about to propose, widen, add or "fix" something nobody asked for, when a finding argues a design is not the simplest, when a CI, cache or trigger change is being weighed, and when a review's quality lane asks whether a concern is real before asking whether the fix is. Esposte
Ready to connect
- View details
gaia-react-perfSkillMedia
Diagnose React render performance by driving a micro-interaction, capturing real renders, and surfacing memo-defeating reference instability with a recommended structural fix. Measure-only: it emits a diagnosis, it does not auto-fix. Trigger on `/gaia-react-perf` or natural-language asks like "profi
Ready to connect
- View details
game-architecture-designSkillMedia
Skill for game architecture, design review, and numerical balancing — the decision-making layer before engine code. Covers paradigm selection (rich entity vs data-driven vs prototype), design of specific systems (combat, skills, AI, narrative, UI, PCG), and critical review of GDD/mechanics/levels
Ready to connect
- View details
gaokao-question-researchSkillMedia
Systematically researches Gaokao math past exam questions, reverse-engineering verifiable question-design intent from question structure, question gradients, scoring logic, and year-over-year changes, and turns it into a trainable "see what → think what → why" method for students. Use for in-depth s
Ready to connect
- View details
gh-og-share-imagesSkillMedia
Generate GitHub social preview images (1280x640 PNG) via iterative vision-guided refinement. Use when: social preview, GitHub share image, OG image for repo, social card, gh_share_image, preview image.
Ready to connect
- View details
hi-fi-designSkillMedia
The design process for high-fidelity, polished work — the system prompt tells Claude to invoke it before starting any design
Ready to connect
- View details
image-generatorSkillMedia
Lets your agent generate and edit images, like photos, logos, and product mockups.
Ready to connect
- View details
kr-patent-drawing-mappingSkillMedia
Visually analyzes/OCRs Korean patent specification drawing images, assigns drawing reference numerals 1:1 to every box in the drawing (departments, modules, objects, data, equipment, personnel), and produces a per-box numeral mapping table consistent with the description, claims, and existing numera
- View details
kr-patent-drawing-taggingSkillMedia
A skill that tags Korean patent drawings by drawing reference numerals directly onto PNG images. It takes a confirmed numeral scheme (kr-patent-symbol-design) and per-box mapping (instructions from kr-patent-drawing-mapping) as input, then inserts numeral text onto the drawing image using cv2 automa
- View details
kr-patent-symbol-designSkillMedia
Designs drawing symbol systems for Korean patent specifications and drawings. Takes claims and drawings as input and performs hierarchical numbering (e.g., 100→110→121-124), separates system symbols from method step symbols (S-prefix), avoids conflicts, and creates a symbol legend. Use when terms li
- View details
Looking for something else?
Media is one category of skills on Ahel. Browse all skills, or open another category above.