Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Media
5,297 results · page 64 of 177
- View details
simpleitk-image-registrationSkillMedia
Register, segment, filter, resample 3D medical images (MRI, CT, microscopy) via SimpleITK Python; DICOM, NIfTI, multi-modal. Rigid/affine/deformable registration, threshold/region-growing segmentation, Gaussian/morph filtering, label stats, format conversion. Use to align volumes across timepoints/m
Ready to connect★ 363
- View details
trackpy-particle-trackingSkillMedia
Python library for single-particle tracking (SPT) in video microscopy via the Crocker-Grier algorithm. Locate particles (fluorescent spots, colloids, vesicles, cells) per frame, link into trajectories, filter short tracks, and compute MSD for diffusion analysis. 2D/3D with subpixel accuracy; reads T
Ready to connect★ 363
- View details
viennarna-structure-predictionSkillMedia
Predict RNA secondary structure, MFE folding, base-pair probabilities, RNA-RNA interactions via ViennaRNA Python bindings. Pipeline: sequence → MFE → partition function and pair-probability matrix → dot-bracket → duplex. Use for siRNA/sgRNA targeting, ribozyme design, RNA accessibility. Use RNAfold
Ready to connect★ 363
- View details
kc-entrypoint-changeSkillMedia
Safely edit the workspace pod's boot scripts (start.sh, the entrypoint/ssh-server configmaps) in kube-coder. Use when changing anything that runs at pod start — credential wiring, service launch, tmux/ttyd config, symlinks — where the two-home layout and Helm templating have non-obvious footguns.
Ready to connect★ 361
- View details
videoSkillMedia
Use this skill whenever the user asks to create, improve, audit, or split prompts for AI video generators (Seedance, Kling, Veo, Runway, Luma, Pika, Sora, any image-to-video system). The skill also covers storyboards, shot lists, director treatments, dynamic montage, multi-clip story structure, came
Ready to connect★ 361
- View details
reading-deduction-certSkillMedia
Reads images of deduction certificates (life insurance premiums, earthquake insurance premiums, etc.) and returns structured data. Can be invoked by other skills or called directly by the user.
Ready to connect★ 359
- View details
reading-invoiceSkillMedia
Reads invoice images and returns structured data. Can be called from other skills or directly by the user.
Ready to connect★ 359
- View details
reading-payment-statementSkillMedia
Reads images of payment statements (payment records) and returns structured data. Can be called by other skills or directly by the user.
Ready to connect★ 359
- View details
reading-receiptSkillMedia
Reads images of receipts, invoices, and furusato nozei (hometown tax) donation certificates and returns structured data. Can be called by other skills or directly by the user.
Ready to connect★ 359
- View details
reading-withholdingSkillMedia
Reads an image of a withholding tax slip (gensen choshuhyo) and returns structured data. It can be called from other skills, and users can also invoke it directly.
Ready to connect★ 359
- View details
snapshotSkillMedia
Use swift-snapshot-testing to visually verify SwiftUI views during implementation. Renders views to PNG for comparison against design references. Fast feedback loop (~25s/cycle).
Ready to connect★ 359
- View details
arrangeSkillMedia
Lets your agent follow a set of design guidelines so the interfaces and layouts it produces look polished.
Ready to connect★ 358
- View details
captureSkillMedia
Record already-confirmed multi-context designs into a handoff-ready, controllably revisable SPEC. Use when work needs to span sessions or agents, or when design decisions must be preserved; do not use it to redo decisions on the user's behalf.
Ready to connect★ 358
- View details
robot-perceptionSkillMedia
Comprehensive best practices for robot perception systems covering cameras, LiDARs, depth sensors, IMUs, and multi-sensor setups. Use this skill when working with RGB image processing, depth maps, point clouds, sensor calibration (intrinsic, extrinsic, hand-eye), object detection, semantic segmentat
Ready to connect★ 358
- View details
robotics-design-patternsSkillMedia
Architecture patterns, design principles, and proven recipes for building robust robotics software. Use this skill when designing robot software architectures, choosing between behavioral frameworks, structuring perception-planning-control pipelines, implementing state machines, designing safety sys
Ready to connect★ 358
- View details
robotics-software-principlesSkillMedia
Foundational software design principles applied specifically to robotics module development. Use this skill when designing robot software modules, structuring codebases, making architecture decisions, reviewing robotics code, or building reusable robotics libraries. Trigger whenever the user mention
Ready to connect★ 358
- View details
V3 DDD ArchitectureSkillMedia
Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
Ready to connect★ 357
- View details
generate-scss-variablesSkillMedia
Quickly generate SCSS variable definition code that complies with the design system specification for new components or features, or check whether existing variables are compliant.
Ready to connect★ 356
- View details
optimize-page-stylesSkillMedia
Optimize the styles in the subPages demo page, replacing hardcoded colors, font sizes, spacing, border radii, etc. with wot-ui design system semantic variables. May directly use the globally injected variable.scss Sass variables, or use CSS custom properties; no need to import variable.scss addition
Ready to connect★ 356
- View details
daily-briefSkillMedia
Operational knowledge for the daily-brief digest pipeline (this project). RSS/API fetchers, pluggable LLM enrichment (default claude CLI on Max; also anthropic/openai/deepseek/minimax API), trading section, HTML rendering, cross-platform scheduler integration (Windows Task Scheduler / macOS launchd
Ready to connect★ 354
- View details
streaming-ssrSkillMedia
Add streaming SSR to a merjs page. Use when the user wants shell-first rendering, skeleton placeholders, or parallel data fetching that resolves inline.
Ready to connect★ 354
- View details
color-palette-generatorSkillMedia
Create an HTML color palette from a mood, description, or image, with swatches, color codes, pairings, and contrast checks. Use for color schemes or brand colors.
Ready to connect★ 353
- View details
product-image-processorSkillMedia
Download, resize, and remove backgrounds from product images at scale. Use when the user asks to "process product images", batch-download images from the schedule, strip backgrounds, or standardize product photos.
Ready to connect★ 353
- View details
product-matchSkillMedia
Find visually or functionally similar products from an image, name, or description. Use when the user asks to "find something like this", match a product from a photo, or source alternates to a given item.
Ready to connect★ 353
- View details
solidity-codingSkillMedia
Write production-quality Solidity contracts. Trigger phrases - write contract, implement function, add feature, add error, gas optimization, event design, contract architecture, or when working in src/ directories.
Ready to connect★ 352
- View details
a-stated-rule-needs-annotated-exceptionsSkillMedia
A design rule with legitimate exceptions survives only if every exception carries its reason at the call site and the rule itself is greppable — otherwise nothing distinguishes an exception from a violation and the rule silently rots. Covers where the rule statement goes, where the reasons go, scopi
Ready to connect★ 315
- View details
ambient-tone-layer-behind-flat-pagesSkillMedia
A reusable top-glow layer that gives pages with no imagery of their own the same tinted ground the image-backed screens get — emitted as the first sibling of a navigation destination's content, with no wrapper, because destinations already stack. Covers why a null tone must collapse the gradient int
Ready to connect★ 315
- View details
artwork-palette-themingSkillMedia
Drive a screen's colours from its artwork — which extracted swatch to use for an accent versus for a large page background, luminance-adaptive darkening so overlaid text stays readable on any image, the hex parsing helper this needs, and what to do when extraction returns nothing or there is no artw
Ready to connect★ 315
- View details
audio-fade-separate-gain-lineSkillMedia
Implement a programmatic audio fade — a sleep timer, an alarm ramp, a duck — on a gain line of its own instead of the user's volume, and restore that gain from the player's own completion path. Use when a fade drags the volume slider down in the UI, when the app comes back permanently silent with a
Ready to connect★ 315
- View details
audio-focus-multiplayerSkillMedia
Hold Android audio focus once at app level when several player instances are alive at the same time — dual-player crossfade, precached players — and keep focus-driven ducking off whatever gain line a fade already owns. Use when background playback dies between tracks, autoplay stalls after the first
Ready to connect★ 315
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.