Намерете инструкция, прочетете оригиналния файл и подгответе команда за своя инструмент.
31 301 skills в каталога
Как подбирам и измервамДанните имат нужда от нова проверка.Последна успешна проверка: 23.09.2026 г.
Проверката на източника не означава, че всяка инструкция е изпробвана от Level8. Каталогът не обхваща непременно всички публични хранилища.
Търсене в целия индекс. Метаданните показват посоченото от източника; липсващите стойности остават означени.
Датата в GitHub е отделна от първата поява в моя индекс. Филтърът по дата изключва записите без посочено обновяване.
Страница 93: 24 записа в 17 групи по репозиторий. Всички записи от страницата са показани. Номерът пази позицията от избраната подредба.
1 skill от този източник на тази страница
Deep architectural analysis of a Next.js frontend repository, performed at Staff/Principal Engineer level (Frontend Architect + Design Systems + Platform/DX + Domain Tech Lead perspectives combined). Use this skill whenever the user wants to audit, refactor, or redesign the structure of a Next.js or
1 skill от този източник на тази страница
Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
1 skill от този източник на тази страница
Build production-quality visual game assets for this Three.js + Colyseus MMO: rigged characters, monsters/mobs and NPCs (rigged GLTF + skeletal animation via the game-core animation state machine), equipped-weapon/bone attachments, combat and world VFX, UI/item icons, and environment props. Use when asked to create or add a character, monster, mob, creature or NPC; skin the player or remote players; replace a capsule; attach or show an equipped weapon; add a skill, hit, death, level-up, target-r
3 skills от този източник на тази страница
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.
Use when the user is doing AI/ML work in a scientific domain — biology, chemistry, physics, astronomy, climate, genomics, materials science, medicine, ecology, energy, conservation, engineering, mathematics, scientific reasoning, drug discovery, protein design, weather modeling, theorem proving, single-cell, PDE solving, or anything similar. Hugging Science (huggingscience.co) is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces; the `hugging-science` org on Hu
2 skills от този източник на тази страница
A relentless interview to sharpen a plan or design.
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
1 skill от този източник на тази страница
The house design system for Halderworks products. Load it BEFORE writing or restyling any user interface - a screen, a route, a component, a form, a table, a landing page, an email sign-in, a settings page, a chart, an icon row, a piece of UI copy - and before proposing a colour, a size, a radius, a
2 skills от този източник на тази страница
Package a finished design so that any implementer - a coding agent or a developer, in any stack (web frameworks, Flutter, SwiftUI, Compose, HarmonyOS ArkUI, mini-programs, Electron, Tauri, native desktop) - can build it faithfully without guessing. Produces acceptance screenshots at the target's logical size, portable HTML/CSS mockups, platform-neutral tokens, a measured spec with every state, the asset list, the motion spec, platform notes and acceptance criteria; then reviews the implementatio
Maintain the design-skill-lab repository - add or correct entries in the curated design resource catalogue, absorb a new authoritative source (article, guideline, book, open-source project, another AI design skill) as a digest plus analysis, refresh a source against its new version, run the link and freshness check, or apply a skill-only improvement to the design-studio suite. Codifies the catalogue schema, tiering rules, generated views, versioning, CHANGELOG, SOURCE_INDEX metadata, analysis fo
1 skill от този източник на тази страница
Turn a technical topic into a hand-drawn notebook-style explainer infographic that shows BOTH how the thing works and what it costs you. Produces a validated content spec and a copy-paste image-generation prompt (for Designer, ChatGPT, Gemini, Midjourney or any image model), plus a proofread checklist for catching dropped text and broken numbering. Use whenever the user wants a handwritten or hand-drawn infographic, a notebook-style explainer, a 'how X works' poster with trade-offs, a LinkedIn c
1 skill от този източник на тази страница
Use when the user needs embedded hardware architecture, MCU/SoC selection, power tree design, interface planning, sensor/actuator selection, RF/connectivity, BOM risk assessment, PCB/layout constraints, schematic-ready proposals, validation plans, or hardware design review.
2 skills от този източник на тази страница
Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX/PDF brandbooks. Preserves official suppl
Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2 for image/design/text, Seedance 2.0 for video, Nano Banana 2/Lite/Pro for character/reference images, Marketing Studio for ads, Seed Audio 1.0 for audio. Use when: "generate an image", "make a video", "animate this photo
1 skill от този източник на тази страница
Clone an existing Power BI PBIR/PBIP report and reproduce a supplied HTML dashboard design, including CSS token extraction, model-backed visual mapping, theme/layout authoring, and structural/runtime verification.
1 skill от този източник на тази страница
Read a ClickUp task in full (task, subtasks, comments, attachments), study the matching repo, grill the user until the design is settled, then implement it and optionally commit and open a PR. Use this whenever the user points at a ClickUp task and wants it built — for example "implement PROJ-412", "do this ClickUp task", "pick up ABC-1234", or when they paste an app.clickup.com task URL and ask for code. Also use it when the user wants a ClickUp ticket analysed properly before any code is writt
1 skill от този източник на тази страница
Answer "how does X work" and "why is it like this" from cited evidence, changing no code. Use before changing unfamiliar code, for walkthroughs, placement and ownership questions, design rationale, and regressions.
3 skills от този източник на тази страница
客户发现：围绕决策缺口设计并综合用户访谈、行为观察与反馈，得到可引用的用户洞察。 适用于：需要理解真实行为、痛点、替代方案或购买/使用障碍时。 不适用于：仅需验证一个已定义的量化假设；转 validation-design。
史诗与用户故事设计：将战略与 PRD 拆成可验证的史诗、最小切片、用户/任务故事和验收条件。 适用于：需求太大、团队无法并行交付或需要形成可测试的工作项时。 不适用于：还没有问题/范围决定；先做 prd-development。
实验分析：用预设假说、样本、显著性、效应量与护栏判断实验结果，并给出下一步决策。 适用于：A/B 实验、准实验或上线试验结束后。 不适用于：尚未定义实验与阈值；转 validation-design。
1 skill от този източник на тази страница
Automatically convert a natural-language world-model task into a validated JEPA Anything design and inspectable, no-training code skeleton. Use whenever a user provides, designs, or asks to adapt a world model, latent-dynamics model, action-conditioned predictor, predictive-state model, or rollout task—even when they do not mention JEPA or this Skill. Do not use it for ordinary static prediction with no world-state intent, model training, or semantic naming of prediction coordinates.
1 skill от този източник на тази страница
Chinese K-12 core-literacy course design for a single OpenMAIC classroom. Use when a teacher asks for 中小学课程、核心素养、素养导向、2022 课标、真实情境、任务群、表现性评价, or wants a grade-and-subject lesson designed around authentic tasks rather than content delivery. Covers Chinese, mathematics, languages, science, humanities, technology, arts, PE and labor education across primary, junior-high and senior-high stages.
1 skill от този източник на тази страница
Design the runtime agent's responsibilities, instructions and tool access inside a reusable SimSense kit.
Пазя съществуващия каталог и добавям намерени SKILL.md файлове след прочит на метаданните. Наличният индекс остава използваем, когато проверката е частична.
Платформата и нивото описват записаното в източника. Те не са гаранция за съвместимост. Български текст се показва само когато в каталога има отделен превод; иначе виждате оригинала с означен език.
Общите звезди показват натрупана популярност. За „Набират интерес“ се сравнява измереният темп при достатъчен интервал. ≥ означава непълна извадка. Под един час не изчислявам дневен темп; методът и изминалият период се показват до записа.
Проверете файла, лиценза и нужния достъп преди употреба. Нито каталогът, нито четенето на SKILL.md изпълняват външни инструкции.
Темата Agent Skills в GitHub