В каталоге 182 820 навыков в 14 категориях.
Mandatory safety and fair-play gate for the Dota AI Coach project. Use whenever introducing a new live-game data source,...
Governs all machine learning work in Dota AI Coach — model selection, baselines, temporal validation, leakage prevention...
Review the C#/.NET code for design pattern implementation and suggest improvements.
Use when reviewing a .NET pull request for breaking changes that may affect other microservice repositories. Detects cro...
判断是否调用 `enterprise_agentic_search` 工具前，必须先完整读取 `doubao-enterprise-search` skill。适用场景包括：用户显式使用 /doubao-enterprise-search；...
去除或避免文本中的 AI 味。用于用户强制调用本 Skill，或写作/改写时提到“不要有 AI 味”“不要太假”“真情实感”“有人感”，或对已有文本/上一轮输出反馈“太像 AI”“太空泛”“太模板”“太官方”“不像我说的”等场景。
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources v...
抖音视频文案提取。输入抖音视频链接、用千问LLM进行智能语音转写，支持普通话、粤语等方言及外语，结果直接输出到聊天。当用户做抖音文案提取、抖音视频文案提取、抖音视频转文字、抖音口播转文字或抖音逐字稿提取时使用。支持提取音频文案、提取口播文案...
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prom...
Download NAIP aerial imagery for a bounding box. Specify coordinates as minx,miny,maxx,maxy in WGS84 and optionally a ye...
**下载视频或音频**。自动识别 URL 下载 YouTube, Bilibili, Twitter, TikTok 等平台的媒体。
Get the correct command syntax for downloading models from HuggingFace. Use when downloading models, running "hf downloa...
Audit a differential-privacy claim for a language-model deployment. Use when you need help with dp audit.
Direct Preference Optimization for learning from preference pairs. Covers DPOTrainer, preference dataset preparation, im...
Fan one deep-research prompt out to several external LLMs at once through a logged-in browser, then collect the reports,...
Turn natural-language descriptions into editable `.drawio` diagrams and export them to PNG / SVG / PDF / JPG via the nat...
Archived skill guidance for drc.
Run overnight compounding sessions.
Consolidation ("dreaming") for this project, at two levels. (A) Claude's file-based memory — replays recent sessions, ex...
小省导购员数字人带货版即梦视频提示词生成系统，基于四大智能体协同（提示词生成师、质量管控师、知识库运维师、跨环节适配师），按照"主体+运动+场景+（镜头语言+光影+氛围）"公式输出中英文双版提示词，适配5s短视频。确保人物一致性、视觉连贯性...
This is an **alias skill** so docs can reference `77-mlops-data-engineering/drift-detection`. In this repo, drift guidan...
Use this skill when the user asks about Driver Qualification Files (DQF) — what must be in a DQ file under 49 CFR 391, r...
Advanced CV for infrastructure inspection including forest fire detection, wildfire precondition assessment, roof inspec...
Checks for potential drug-drug interactions (DDIs) between a list of medications.
Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance
Use ESMFold model to predict 3D structure of the input protein sequence.
Given a protein sequence and its structure, employ ProSST model to predict mutation effects and obtain the top-k mutated...
The keeper of the animal ecosystem. Not an animal themselves, but the one who understands the forest deeply enough to in...
Keep a PROGRESS.md for long tasks and move to a fresh session or subagent that reads only that file when the context get...
Prüfung und Gestaltung des Melde- und Abhilfeverfahrens (Notice-and-Action) nach Art. 16 DSA samt Begründungspflicht Art...
Install DSH on a fresh Mac. Runs sovereign-setup-mac.sh, renders .env from secrets backend, applies full sovereign lockd...
DSPy: declarative LM programs, auto-optimize prompts, RAG.
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
Use when you need to customize how DSPy formats prompts for a specific provider — switching from chat to completion form...
This skill should be used when the user asks to "compose DSPy modules", "use Ensemble optimizer", "combine multiple prog...
Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.
Use when the task benefits from intermediate reasoning before producing an answer — multi-step logic, analysis, math, or...
Build agents that write and execute Python code using dspy.CodeAct. Use when the task requires computation, data transfo...
This skill should be used when the user asks to "create custom DSPy module", "design a DSPy module", "extend dspy.Module...
This skill should be used when the user asks to "debug DSPy programs", "trace LLM calls", "monitor production DSPy", "us...
Use for DSPy retrieval with dspy.Embedder, dspy.Embeddings, FAISS indexes, semantic search, and local or hosted embeddin...
Combines multiple optimized DSPy programs into a single ensemble via majority voting, averaging, or custom reduce functi...
This skill should be used when the user asks to "refine DSPy outputs", "enforce constraints", "use dspy.Refine", "select...
DSPy typed wrappers (dspy.Image, dspy.Audio, dspy.Code, dspy.History, dspy.File, dspy.Reasoning, dspy.Tool, dspy.ToolCal...
Use Ragas to evaluate DSPy RAG pipelines with decomposed metrics. Use when you want to evaluate RAG quality, measure fai...
This skill should be used when the user asks to "create a ReAct agent", "build an agent with tools", "implement tool-cal...
Use for DSPy reasoning modules including RLM, ProgramOfThought, CodeAct, Parallel, sandboxed execution, and long-context...
Defines typed input/output contracts for LM calls using dspy.Signature, dspy.InputField, and dspy.OutputField. Use when...
This skill should be used when the user asks to "optimize with SIMBA", "use Bayesian optimization", "optimize agents wit...
Use when working with reasoning models (o1, o3, o3-mini, DeepSeek-R1, Claude extended thinking) that reject system promp...
Use VizPy as a drop-in prompt optimizer for DSPy. Use when you want to try VizPy, vizops, ContraPromptOptimizer, PromptG...
Resolve security signals, IoC matches, or Smartscape nodes to runtime Dynatrace entities and connect findings on differe...
Migrate a GenAI/LLM app off Traceloop/OpenLLMetry onto OpenInference with its OTel gen_ai.* semconv option enabled (`ena...
Steuerung der rechtlichen Due Diligence beim Unternehmenskauf – Aufbau der DD-Request List, Abgrenzung Red-Flag-Report u...
Use when the user wants two approaches raced head-to-head on a single shared metric — e.g. a classical/algorithmic lane...
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQue...
This prompt instructs an image model to generate a vertical, four-frame photobooth strip of the same fully human young m...
Adds Foundation Models to an iPhone Duo app: the on-device model (SystemLanguageModel) and the Private Cloud Compute ser...
双 AI Agent 交叉审查 PR。自动判断共识、决定是否需要交叉确认和修复。当用户要求审查 PR 或提到 "duoduo review" 时触发。
Predict project duration using k-NN and regression. Estimate timeline based on similar historical projects.
Data Version Control (DVC) for tracking large datasets/models with Git-like semantics, defining reproducible data/ML pip...
Data Version Control for ML projects. Track large datasets and models alongside Git, build reproducible ML pipelines, an...
Causal state gating via ε-machine. Coworld observer that prevents action
Self-regulating Goblins actor implementing Ivan Illich's dynamic sufficiency
Categorical structure of dynamical systems
对接近投稿状态的医学稿件做五个视角的模拟审稿：证据、方法统计、伦理合规、临床领域与期刊编辑，并汇总 为定位明确的 PASS、REVISE 或 REJECT 建议。当用户要求投稿前全面把关、模拟同行评议或评估拒稿风险时 使用；这是决策支持，不...
Für E-Mail-Review in Internal Investigations: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risik...
Prüfung der Pflichten eines Online-Shops im elektronischen Geschäftsverkehr: allgemeine Pflichten (§ 312i BGB), besonder...
E-Rechnungspflicht im inländischen B2B-Verkehr und Vorsteuerabzug – Begriffe E-Rechnung und sonstige Rechnung § 14 Abs....
You are an expert in E2B, the cloud platform for running AI-generated code in secure sandboxes. You help developers give...
Gay MCP skill at invocation 21
Early-user discovery and feedback trials. Use when reviewing unfamiliar AI Matrx accounts, classifying owner relationshi...
Earnings preview deck, quarterly earnings presentation, earnings summary slides, consensus vs actual presentation, earni...
Creates comprehensive ebooks, guides, and downloadable lead magnets with chapter structure and promotional assets. Use w...
Short compatibility alias for Elves Cobbler, the default orchestration model. Use when the user types /ec for Cobbler co...
Echo - A warm and caring virtual girlfriend AI
Token-efficient model routing modifier
토큰 효율적 실행 모드. 비용을 최소화하면서 작업을 수행합니다. 간단한 작업에 fast 모델을 자동 선택하고, 병렬 에이전트 수를 제한하며, 불필요한 컨텍스트 로딩을 줄입니다. Use when budget-consc...
Upstream version checking, agentskills.io spec compliance audit, Claude Code feature gap analysis. Activates on updates,...
Use whenever someone runs a GPU / ML / GenAI / LLM workload on Amazon ECS: GPU on ECS, ECS GPU-optimized AMI, g4dn/g5/g6...
TinyML, neural network quantization (INT8), pruning, edge accelerators (Google Coral, Hailo, Jetson), and embedded infer...
ML model optimization and deployment on robot edge devices (Jetson, embedded)
Compares model probabilities against market odds to find positive expected value bets. Use when user asks about EV calcu...
Edge Model Compression enables deployment of large, accurate machine learning models on resource-constrained edge device...
Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when (1) User requests audio/voice ou...
Perform differential expression analysis using edgeR in R/Bioconductor. Use for analyzing RNA-seq count data with the qu...
Core EDI behaviors for all agents and subagents
Edit real footage with an agent: turn raw takes of a talking head, podcast, vlog, course or ad into a clean cut, then ad...
View, edit, or create Claude Code skills. Lists available skills, shows skill structure, and helps modify skill instruct...
Prüfung der Anspruchsvoraussetzungen für Marktprämie und Einspeisevergütung nach EEG 2023 – Anlagenart, Inbetriebnahme (...
Use when the agent needs the on-chain contract architecture of eERC — EncryptedERC, Registrar, EncryptedUserBalances, To...
Use when the agent must choose between eERC Standalone mode (a brand-new private token) and Converter mode (wrapping an...
Use when the agent needs converter-mode eERC operations — deposit (wrap an existing ERC-20 into encrypted form) and with...
Use when the agent needs to hide an eERC token's total supply — why standalone mode can keep supply private, the privacy...
Use when the agent needs to mint or burn eERC tokens in standalone mode — privateMint and privateBurn via the SDK, inclu...
Use when the agent needs to implement or explain confidential eERC transfers — client-side proof generation, the transfe...
Use when the agent needs to register a user with eERC and manage decryption keys — register(), generateDecryptionKey(),...
This skill should be used when the user asks about "Effect AI", "@effect/ai", "LLM integration", "AI tool use", "AI exec...
Effect-TS specialized research via deepwiki and submodules. Query Effect-TS/effect, tim-smart/effect-atom for verified p...
Master effective prompting techniques for Claude Code. Use when learning prompt patterns, improving task descriptions, o...