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 178 of 222
- View details
produce-ai-videoSkillMedia
Produce or revise an actual playable AI video when the user explicitly requests video generation, an actual video test, or a finished film. Interpret the story, preserve locked directing and storyboard decisions, then generate, edit, add authorized sound, review playback, and repair within scope. Cr
Ready to connect★ 62
- View details
prop-assetSkillMedia
Preset for generating prop asset reference images. Trigger words: 道具, 物品, 物件, 道具设计, 道具资产, prop, 物品图. Outputs a static reference image task brief and an asset contract. This Skill independently completes the static reference image task brief, asset locking, review fields, negative constraints, and an
Ready to connect★ 62
- View details
react-best-practicesSkillMedia
Diagnose React performance problems or review and improve state and effect design.
Ready to connect★ 62
- View details
research-grillSkillMedia
Interviews a researcher, in rounds, until a research idea, design, or draft has no silently assumed decision left — every question numbered, each with a plain-language "why this matters" and a recommended answer, facts fetched by the assistant rather than asked, and every settled decision written to
Ready to connect★ 61
- View details
research-wayfinderSkillMedia
Plan a research project as a durable decision map, resolving one design decision per session until the destination is a defensible, pre-registerable design. Not for executing analyses or writing the paper. Use at the start of a project, when a design has more open decisions than one conversation hol
Ready to connect★ 61
- View details
romance-designSkillMedia
Romance-genre visual design preset. Trigger words: love, romance, warmth, intimacy, heart-flutter, confession. For visual design, image/video prompts, and visual parameter queries and diagnostics that explicitly require this genre; preserves photography, lighting and color, space, motion, materials,
★ 62
- View details
rust-design-patternsSkillMedia
Resolve Rust ownership and lifetime problems or design Rust APIs, resource lifecycles, and FFI boundaries.
Ready to connect★ 62
- View details
scene-assetSkillMedia
Designs believable scene assets based on the script, story setting, and signs of use; defaults to photographic realism when no art style is specified. Use for scenes, environments, locations, scene design, scene assets, scene, environment images; outputs static reference image task briefs and asset
Ready to connect★ 62
- View details
vlm-ocrSkillMedia
OCR scanned or image-only corpora with vision-language models, in three phases. Use `evaluate` to compare candidate OCR systems against stratified human ground truth and pick one on measured CER/WER, `run` to build the production pipeline (model selection, image handling, prompts, architecture, batc
Ready to connect★ 61
- View details
war-designSkillMedia
Provides a unified cinematic visual consultant for war and military themes: war-genre lighting and color, spatial materials, character costumes and equipment, scene props, key story frames, combat and squad shots, image prompts, realistic image generation, and review; preserves the style_route/style
Ready to connect★ 62
- View details
whitebox-previs-executorSkillMedia
When the user explicitly requests 3D whitebox previs, compiles existing video prompts, shot descriptions, or storyboards into a playable previs of camera positions and basic blocking; creative shot ideas, plan discussions, or Skill testing itself do not trigger rendering. Action-heavy fight scenes m
Ready to connect★ 62
- View details
wuxia-designSkillMedia
Visual design preset for the wuxia genre. Trigger words: 武侠, 江湖, 剑客, 功夫, 东方, 侠客. Used for explicit genre-specific scene design, image/video prompts, and visual parameter queries and diagnostics; preserves photography, lighting and color, space, action, materials, continuity, and the style_route/styl
★ 62
- View details
ai-short-drama-studio-femaleSkillMedia
Develop and direct female-audience AI short dramas through role-specific workflows for showrunning, screenwriting, casting and original character design, art, performance, cinematography, storyboarding, sound, post, continuity, and asset handoff. Use when the user asks for 女频短剧、微短剧、言情或非言情女性向故事、女主成长、
Ready to connect★ 57
- View details
ai-short-drama-studio-maleSkillMedia
Develop and direct male-audience AI short dramas through role-specific workflows for showrunning, screenwriting, casting and original character design, art, performance, cinematography, storyboarding, sound, post, continuity, and asset handoff. Use when the user asks for 男频短剧、微短剧、玄幻修仙、都市逆袭、职业创业、历史权谋
Ready to connect★ 57
- View details
campaign-structureSkillMedia
Orient within a camp's directory structure. Use when deciding where work belongs (intents vs festivals vs design vs docs vs dungeon), especially when a task is not yet planned or folder ownership is unclear.
Ready to connect★ 61
- View details
cv-attention-lstm-image-captioningSkillMedia
Show-Attend-Tell decoder: Bahdanau additive attention over CNN spatial features driving a gated LSTMCell for autoregressive image-to-sequence generation.
Ready to connect★ 61
- View details
cv-bbox-interpolation-temporal-trackingSkillMedia
Interpolate missing bounding boxes across video frames using bidirectional pandas interpolation to maintain smooth tracking through occlusions
Ready to connect★ 61
- View details
cv-black-border-autocropSkillMedia
Crops uninformative black or dark borders from images by deriving a binary mask from the grayscale channel and trimming rows/columns.
Ready to connect★ 61
- View details
cv-centroid-distance-anomaly-scoreSkillMedia
Score each face in a video as anomalous by computing L2 distance from the embedding centroid of all faces, then convert to probability via logistic function
Ready to connect★ 61
- View details
cv-class-density-threshold-patch-samplingSkillMedia
Sample training patches from large images using per-class area-fraction thresholds to ensure each patch contains meaningful object coverage
Ready to connect★ 61
- View details
cv-classifier-free-guidance-diffusionSkillMedia
Manual stable diffusion inference loop with classifier-free guidance that interpolates between unconditional and conditional noise predictions for controllable image generation
Ready to connect★ 61
- View details
cv-clip-aesthetic-scoringSkillMedia
Scores image aesthetic quality by passing L2-normalized CLIP ViT-L/14 embeddings through a trained MLP regressor head.
Ready to connect★ 61
- View details
cv-clip-interrogator-captioningSkillMedia
Generate descriptive text prompts from images by combining BLIP captioning with CLIP cosine similarity against curated label banks for medium, movement, and flavor attributes
Ready to connect★ 61
- View details
cv-cnn-metadata-fusion-headSkillMedia
Fuse CNN image features with a small tabular MLP branch via concat before a final classifier, training both branches end-to-end
Ready to connect★ 61
- View details
cv-cnn-rnn-video-classificationSkillMedia
Extract per-frame CNN features then classify the temporal sequence with stacked GRU layers and a boolean mask for variable-length video inputs
Ready to connect★ 61
- View details
cv-cumulative-sum-channelSkillMedia
Add a cumulative sum channel along the vertical axis to capture directional structural trends in grayscale images for segmentation
Ready to connect★ 61
- View details
cv-dot-annotation-blob-diff-extractionSkillMedia
Recover (x, y, class) point labels from color-coded dot-annotation image pairs via absdiff + blackout masking + Laplacian-of-Gaussian blob detection + center-pixel RGB classification
Ready to connect★ 61
- View details
cv-embedding-knn-regressionSkillMedia
GPU-accelerated k-NN regression on CLIP image embeddings using cosine distance and inverse-distance-power weighting to predict target embedding vectors
Ready to connect★ 61
- View details
cv-frame-prediction-averagingSkillMedia
Average per-frame sigmoid predictions across sampled video frames to produce a stable video-level classification probability
Ready to connect★ 61
- View details
cv-hair-overlay-augmentationSkillMedia
Overlay real hair PNGs (masked via threshold) onto dermoscopy images to simulate body-hair occlusion as a domain-specific augmentation
Ready to connect★ 61
Looking for something else?
Media is one category of skills on Ahel. Browse all skills, or open another category above.