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 198: 24 записа в 14 групи по репозиторий. Всички записи от страницата са показани. Номерът пази позицията от избраната подредба.
1 skill от този източник на тази страница
算法正确性与复杂度核算：循环不变式、DP 状态语义、贪心交换论证、搜索覆盖、归约、近似与随机保证，以及完整复杂度账本。TRIGGER —— 证明正确性、为什么对、复杂度多少、最坏/均摊/期望、空间复杂度、是否最优、近似保证、伪多项式。DO NOT TRIGGER —— 算法选型（→ algorithm-modeling）、跑分与测量（→ algorithm-implementation）、领域前提核查（→ algorithm-domain-checks）。
8 skills от този източник на тази страница
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones
Batch-effect detection and correction for bulk expression data: when to correct, ComBat via pycombat/harmonypy, and the classic mistake of correcting out the biology.
Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.
Brain Imaging Data Structure (BIDS) — the community standard for organizing neuroscience and biomedical datasets (11 modalities: MRI/PET/microscopy, EEG/MEG/iEEG, NIRS, behavioral). Covers BIDS directory/naming conventions, PyBIDS querying, bids-validator compliance checks, and DICOM conversion via
Report verification skill (dsh-bioinfo verify-report style): check a generated report's citations, references, file references, and claims against real sources; produce a structured mismatch list so a writer agent knows exactly what to fix. Use before delivering any report, or when asked to 校验/核实/ve
1 skill от този източник на тази страница
Turn a 3D massing viewport capture (grey boxes from Rhino, SketchUp, Revit, or any modeler) into a photorealistic aerial or perspective rendering prompt while keeping camera, building layout, floor counts and pilotis, and check the result against the capture. Covers how to prepare the capture so the model reads it, how to write the fixed/render/forbidden lists, and how to verify with an outline overlay. Use for Korean requests like 매스 캡처 렌더링해줘, 조감도 뽑아줘, 뷰포트 캡처로 투시도, 층수 그대로 렌더, 매스 스터디 이미지 만들어줘, 렌
1 skill от този източник на тази страница
App Store keyword research (ASO) with the free, open-source aso-mcp MCP server - where the app ranks for each query and country, who leads and with how many ratings, keyword gaps against competitors, off-intent queries to drop, and concrete swaps for the name, subtitle and 100-character keywords field, then measuring the effect a few weeks after release. Use it whenever the user asks "what keywords should I use", "why doesn't my app show up in search", "analyze my competitors on the App Store",
2 skills от този източник на тази страница
Use when an agent needs to decide whether to adopt a structural dependency into a project; checks local pain, architectural fit, feasibility, and governance, then returns adopt, adopt narrowly, defer, or decline rather than planning implementation.
Use when an agent needs to assess a conversation for knowledge worth extracting; identifies topics, maturity, and internalize/externalize tendency without creating artifacts or recommending next steps.
1 skill от този източник на тази страница
Use when the user types /autoheal, or when scheduled jobs or the model connection must repair themselves. Watches for failed jobs and an unreachable model, repairs what it may, and escalates the rest.
1 skill от този източник на тази страница
Build autonomous AI-powered assistant bots for Bale Messenger using Large Language Models (OpenAI, Anthropic Claude, Google Gemini, Ollama, DeepSeek) and LangChain/LlamaIndex. Covers message chunking, typing indicators, context management, and rate-limiting.
1 skill от този източник на тази страница
Coordinate and verify parallel processing of many literature files in pending using bounded subagent assignments, explicit ownership, source-based review, and controlled integration. Use when a batch is being processed in subagent mode, without depending on a particular agent framework.
1 skill от този източник на тази страница
Use when finding Belgian archives online (AGATHA portails, cotes, milice belge, état civil) for family history research.
1 skill от този източник на тази страница
Build a jev-tree taxonomy and knowledge set from raw input (CSV, TSV, JSON, JSONL, MD, TXT, FAQ exports, ticket dumps, chat logs). Use when the tree does not exist yet, when grafting one dataset onto an existing tree, or when verifying a load.
1 skill от този източник на тази страница
Activate this skill when the user wants to brainstorm or validate a **business or product idea** — check the competitive market, research it online, or find problems with it before building anything. Trigger phrases include: "let's brainstorm this business idea", "validate this product idea", "act a
1 skill от този източник на тази страница
Mode bras droit technique. Claude prend le lead complet sur un chantier, comme un directeur technique délégué : il cadre, découpe, délègue à une équipe de sous-agents, vérifie, arbitre et livre, en décidant seul de tout sauf des actions irréversibles. Utiliser quand l'utilisateur dit « prends le lead », « tu pilotes », « fais tout », « gère ça de A à Z », « t'es mon bras droit », « mode chef de projet ». À déclencher aussi pour tout chantier lourd, multi-fichiers ou multi-domaines où l'utilisate
3 skills от този източник на тази страница
Use when approved work involves construction inspections, facility observations, or environmental field reports and needs the bounded responsibilities of the Field Observation Triage Agent.
Use when approved work involves research planning, lab protocol drafting, or grant-background research and needs the bounded responsibilities of the Scientific Literature & Protocol Agent.
Use when approved work involves research-data management, qc traceability, or reproducibility support and needs the bounded responsibilities of the Laboratory Data Steward.
1 skill от този източник на тази страница
Identify evidence-backed Scenarios under confirmed Capabilities, split and promote Processes by business boundaries, and model Process-internal Sub-process/Step flows. Use when distinguishing real business paths from technical entries, workflow stages, error branches, or implementation details.
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