В каталоге 182 820 навыков в 14 категориях.
Map the talent landscape for a specific role and market. Produces a structured brief covering: who competes for this tal...
Run discovery, crank, validation.
Alias for the retro skill: identical behavior, shorter to type. On any trigger, run the retro skill, which holds the sin...
Covers operating AI coding agents securely: auditing whether the agent runs sandboxed, permission and dangerous-command...
Covers applying FAIR principles to machine learning artifacts: making models findable and reusable with model cards and...
Covers how to apply the FAIR principles - findable, accessible, interoperable, reusable - to research software, and how...
Covers starting research software projects from maintained templates and keeping them in sync: choosing a generator (Cop...
When a user is stuck, frustrated, or describing a problem vaguely, do NOT immediately suggest solutions. First, force st...
Think out loud about a problem, decision, or approach — Socratic friction to help you find clarity, not sympathy
Be a thinking partner. The answer often emerges when explaining the problem.
Modifies an existing RudderStack Profiles project: features, inputs, id_types, cohorts, feature views, SQL models, optim...
Erstelle einen strukturierten Rückfragebrief an den KI-Anbieter zur Klaerung der berufsrechtlichen und strafrechtlichen...
High-stakes code review with parallel agent waves
Discover and apply Overskill skills for this project
Organize Claude Code instructions into modular rule files in .claude/rules/. Use when setting up project standards, addi...
One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.
Use — One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.
Load this skill when repeated work runs from its `flow.yaml`: stages in order, approvals, gates, run state on disk, inte...
Trigger phrases: "start trading", "run agent", "start arena agent", "begin trading", "start auto-trading", "stop trading...
Execute work items based on their assigned mode (autopilot, confirm, validate). Supports single-item and multi-item (bat...
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "...
Autonomous workflow for processing multiple GitHub issues in parallel with priority-based scheduling and verification.
Execute a continuous plan deterministically by following the skill sequence. Use after continuous-planner creates a plan...
Run saved prompts in isolated sub-agent contexts, single, sequential or parallel. Carries its own DOCTYPE: a declared ou...
Step-by-step execution of the OWC protocol with mandatory checkpoint at each step. Prevents skipping steps (including ve...
Run pw workflow commands reliably from a non-interactive shell by calling prompt_workflow.bat directly instead of relyin...
Run an Applora research workflow from a prepared brief or a direct Shopify App Store question. Use for selected template...
Execute pending tasks in dependency order with wave-based concurrent execution via Agent Teams
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be...
Langium port for Rune DSL tooling Use when working with rune, rosetta, dsl, langium, cdm, isda, drr, finos, language-ser...
Segment data with clustering algorithms such as K-means, DBSCAN, or hierarchical clustering. Use for unsupervised groupi...
Orchestrate an end-to-end data analysis or machine learning project from decision framing through reproducible handoff....
Use when an agent needs to self-bootstrap agent-relay and autonomously manage a team of workers - covers infrastructure...
将用户合法拥有或已获授权的 CUDA 应用中的 Runtime 层迁移到 CANN Runtime，包括 API、类型、错误码、初始化、内存、stream、event、IPC、构建配置和兼容层适配。仅在处理 Runtime 层迁移或可行性分...
Runtime HAL for multi-runtime agent orchestration. Detects active AI assistant (Claude Code, Codex, Gemini, Cursor) and...
Emit info-level logs to file during task execution, similar to logger.info() calls in code
Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device manageme...
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory org...
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer...
Expert project manager orchestrating backlog-curator, work-delegator, workstream-coordinator, and roadmap-strategist sub...
World S Skill
Prüfung von Software-as-a-Service-Verträgen: vertragstypologische Einordnung als Mietvertrag (§ 535 BGB, BGH zu ASP), Mä...
Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, qualit...
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activa...
Agent with selective Gemini safety settings for specific categories
SAFE Quantum Machine Learning methodology — variational quantum classifiers with amplitude encoding, learnable classical...
ElevenLabs text-to-speech with mac-style say UX.
ElevenLabs TTS: voice generation, voice cloning, audio output, streaming, voice library
Patterns for managing distributed transactions and long-running business processes.
處理跨 Frame 的複雜業務流程，協調多個 Sub-agent (command/query/reactor) 完成 Saga/Choreography 模式的分散式交易。當需求涉及多個狀態變更、事件反應與查詢的組合時使用。
Implementing distributed transactions across microservices using the Saga pattern with choreography and orchestration ap...
Saga patterns for distributed transactions with orchestration and choreography approaches. Use when implementing multi-s...
Amazon SageMaker AI Operational Review. Use this skill when a user asks to review, audit, or assess Amazon SageMaker AI...
赛博禅心（大聪明，技术深度型AI博主）的AI科技自媒体创作思维——技术散文·反热潮·深度拆解·冷静旁观。 触发词：「赛博禅心视角」「像赛博禅心那样写」「AI技术深度解读」「AI论文解读」「AI行业大事记」「踏马的Agent」。 擅长：AI模...
赛文乔伊（周游，Joy）的AI科技短视频创作思维——产品老炮视角、前沿科技速递、AI降临派技术乐观主义。 触发词：「赛文乔伊视角」「像赛文乔伊那样写」「科技乔伊瞧」「AI产品短视频」「AI降临派」。 擅长：AI前沿科技快讯、产品洞察与解读、...
Agente que simula Sam Altman — CEO da OpenAI, ex-presidente da Y Combinator, arquiteto da era AGI.
Reference system prompt and tool schemas for Same.dev. Use when imitating, comparing, or analyzing Same.dev's prompting...
Run and monitor samocode autonomous sessions on projects. Use when user says "run samocode" or wants to continue a samoc...
Generate an agentic contract (llms.txt) for any business website. Crawls the site, fills gaps conversationally, and prod...
Manage Claude Code terminal sessions via Sandboxer web dashboard. Use when: (1) listing running Claude Code sessions, (2...
三毛流浪文学思维——真挚感性、沙漠爱情、自由灵魂、生死相随。 触发词：「三毛视角」「像三毛那样写」「撒哈拉」「前世乡愁」「每想你一次」。 擅长：流浪文学、真挚散文、爱情叙事、自由精神、感性表达。
Review the draft PRD and module specifications for either approved synthetic SAS workflow. Use to trace requirements to...
Persistent long term memory for for continuity in ai sessions between providers and codegen tools.
Save important session context to MCP memory before compaction. This skill should be used when: (1) Claude detects the c...
Save session state to Pieces LTM. Use when context is running low, before /compact, when ending a session, or handing of...
作業中に発見した汎用パターンを Claude Code スキルとして保存する。 「これスキルにして」「パターンを保存」「スキル化」などの依頼時に使用する。 既存スキルの修正・削除には使わないこと（手動で編集する）。
Text-to-speech using Kokoro local TTS. Use when the user wants to convert text to audio, read aloud, or generate speech.
Git worktree management for multi-agent parallel development. Use when spawning multiple agents to work on isolated feat...
Bootstrap toàn bộ AI module từ đầu — tạo folder structure, requirements.txt, pytest.ini, .gitignore, rồi chạy lần lượt s...
Generate boilerplate for a new statistic following library conventions
Scaffold a new sub-agent inside an EXISTING fleet project — create the agent directory (`openfleet/agents/<name>/`), the...
Single-cell RNA-seq analysis. Load .h5ad/10X data, QC, normalization, PCA/UMAP/t-SNE, Leiden clustering, marker genes, c...
标准单细胞RNA-seq分析管道。用于质控、标准化、降维(PCA/UMAP/t-SNE)、聚类、差异表达和可视化。最适合具有成熟工作流的探索性scRNA-seq分析。深度学习模型请使用scvi-tools；数据格式问题请使用anndata。
Orchestrate all installed Codex skills through an auto-updating synthesis matrix with Sacred Tongues routing, emotion/in...
Suggest WCAG 2.1 / Section 508 corrected captions for a YouTube video.
Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video...
Use when one look must hold across Scenario generations: one character across scenes, a turnaround, or a video animated...
Use when putting a person from a photo into live-broadcast crowd footage with Scenario: a stadium or arena fan-cam react...
Use when one approved visual, image or video, must ship at many sizes or placements through Scenario: adapting a master...
Use when generating, extending, or editing video with Gemini Omni models on Scenario via MCP: text-to-video, image-to-vi...
Use when generating or editing images with Ideogram models on Scenario via MCP: posters, logos, menus, packaging, or sig...
Use when generating or editing images with Microsoft MAI Image models on Scenario via MCP: photoreal or stylized text-to...
Use when creating or refining 3D assets with Meshy models on Scenario via MCP: image-to-3D from one photo or 1-4 multi-v...
Use when generating or editing video with Runway models on Scenario via MCP: text-to-video or image-to-video from a firs...
Use when a Seedance video must hold continuous movement across shots: dance choreography, fights, sports, or any perform...
Use when generating or editing video with Wan models on Scenario via MCP: text-to-video, image-to-video from a still, fi...
Performs fast Gene Set Enrichment Analysis (GSEA) on single-cell data using fgsea R package. Identifies enriched biologi...
---name: scfoundation-model-agent
Integrates unpaired single-cell multi-omics (scRNA + scATAC, no shared barcodes) using a prior-knowledge guidance graph...
Predict project completion dates using ML models. Forecast schedule delays based on current progress, historical pattern...
Build, lint, ingest, compose Drescher-style schemas
Drescher's computational theory of causal learning
Grundlagen der Schematherapie nach Jeffrey Young: Schemata, Modi, Inneres-Kind-Konzept und Bewältigungsstile — psychoedu...
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experime...
This skill should be used for time series machine learning tasks including classification, regression, clustering, forec...
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when...
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular...
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics,...