В каталоге 183 730 навыков в 14 категориях.
Use this skill when working with Mastra - the TypeScript AI framework for building agents, workflows, tools, and AI-powe...
You are an expert in Mastra, the TypeScript framework for building AI agents, RAG pipelines, and workflows. You help dev...
Comprehensive system check for Mastra AI agent projects. Validates configuration, agents, workflows, memory, tools, prom...
Python benchmark suite for materials science property prediction. Use when evaluating ML model performance on materials...
Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization,...
Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity s...
Use this skill when accessing Materials Project for computed materials properties, phase diagrams, battery materials, or...
材料科学筛选技能。用于固态电解质、催化剂等材料的候选筛选、 属性预测和多目标优化排序。触发词包括"材料筛选"、"materials screening"等。
Multi-layer cognitive stack for machine-verified mathematical problem solving across 14 sub-disciplines.
Deterministic router for math cognitive stack - maps user intent to exact CLI commands
Use this skill when fitting accelerated life models, computing mean time to failure (MTTF), B10 life and similar quantit...
Use this skill to classify tabular data end-to-end in MATLAB — load a dataset, prepare and clean it, select promising cl...
Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patt...
Use when engineering or selecting the best features for single-response classification or regression in MATLAB, whatever...
Fit curves and surfaces interactively with the Curve Fitter app for a complete no-code fitting workflow. Invoke this ski...
MATLAB R2026a workflow for signal processing, DSP, image processing, computer vision, lidar, medical imaging, deep learn...
Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (...
Use when the user wants to train, compare, or export machine learning models using Classification Learner or Regression...
Guide authoring of Audio Toolbox plugins (audioPlugin, audioPluginSource) that pass validateAudioPlugin and generate dep...
Matminer - Python library for data mining in materials science. Use when applying machine learning to materials data, ge...
从已确认案件档案整理现状、变化、截止日期和待决问题。
mattergen is a deep learning model for generative design of inorganic materials across the periodic table. It uses diffu...
Northbridge coordination pattern for multi-agent orchestration. Creates convoys, dispatches work via sling, monitors pro...
Audits an MBG AI-assisted analog-design experiment record for reproducibility, prompt independence, bounded LLM refineme...
Fully automated analog design from one request — the /mbg-full-auto command. Parses the specification, runs pre-layout o...
Berufsrechtliche Prüfung ärztlicher Pflichten nach der Musterberufsordnung MBO-Ä und der einschlägigen Landesberufsordnu...
Create, update, and validate repository skills under your agent’s skills directory (Codex: `.codex/skills/`, Claude: `.c...
Coding specialist for COMAP MCM/ICM Problem C (C题数据处理与建模落地). Use when you need to implement reproducible data pipelines,...
Statistical/data-analysis modeling lead for COMAP MCM/ICM Problem C. Use when you need to interpret C题需求、检查题目数据是否足够/是否允许...
Model Context Protocol, client server architecture, and tool definitions.
Working with MCP (Model Context Protocol) servers in Freebuff Desktop: discovering tools via native search_mcp_tools / c...
Operational guide for the NV oOS Model Foundry (Proposal 067) — the cluster fine-tuning flywheel. Phase 1 shipped: the C...
Model Context Protocol (MCP) client - connect to tools, data sources and services
- Quick Start
Model Context Protocol (MCP) memory patterns for agent coordination using Serena memories. Provides file-based memory st...
Skill converted from mcp-create-declarative-agent.prompt.md
Create a custom MCP tool for the documentation manifest. Guides the user through defining the tool's purpose, generating...
Execute and manage 26 Genkit AI flows via MCP with 90% caching. Use when generating KSC responses, creating cover letter...
Complete MCP tool reference and usage patterns. Load this skill to become an expert in all 80+ GoodVibes MCP tools. Use...
> JSON-RPC 2.0 protocol reference for MCP.
Audit Model Context Protocol server configurations and apply least-privilege scoping. Covers MCP inventory, capability r...
Use when building a Model Context Protocol server. Covers tool, resource, and prompt design, transport choice, authentic...
Write effective MCP server instructions for tool compaction support. Use when creating or updating the `instructions` pa...
Using MCP (Model Context Protocol) servers to extend agent capabilities. Read the configured MCP source for the current...
AI-native tutor and onboarding workflow for the MCPA (Model Context Protocol Associate) certification in AI Engineering...
Generate and validate mcpbr configuration files for MCP server benchmarking.
Run an MCP evaluation using mcpbr on SWE-bench or other datasets.
classname: EchoBehaviour
View or change the current member's Egregore profile across Claude Code, Codex, Pi, and Prime. Use for /me, 'who am I',...
Help order food timed to arrive at a specific time. Works backward from target arrival, suggests restaurants, builds car...
Trigger: OpenAI meal plan, prompt, structured output, food restrictions, AI evaluation. Build NutrIA AI safely.
This skill group covers calculations of mechanical properties of crystalline materials. Two main approaches are availabl...
Generates Mermaid flowchart code and visual diagrams for pathophysiological mechanisms. Converts medical concepts into c...
- Overview
Post-event analyst note (conferences, KOL events, site visits) with the professional note anatomy — headline verdict, pe...
Invoke MEDCOM for military medical advisory, ACGME interpretation, and domain expertise. Advisory-only agent that surfac...
Generate images and videos using fal.ai models through Cloudflare AI Gateway — understand the API, craft prompts, and co...
[AI & Tools] Use when processing multimedia files with FFmpeg (video/audio encoding, conversion, streaming), ImageMagick...
Specialized visual and multimedia processing tools. Use this skill whenever a task involves complex visual content — UI...
分镜设计专家包：从剧本文本到标准分镜表格转换（镜号/景别/拍摄角度/画面内容/人物/音效）与电影感镜头运动设计（推拉摇移/景别/构图），到 AI 视频提示词与分镜脚本构思（文生视频/图生视频/多模态参考）与 AI 绘画视频提示词参数化构建，...
- Using or debugging @mediapipe/tasks-vision, Pose Landmarker, or pose detection in a web app.
Medical evidence grading orchestrator. 当用户需要评估医学文献的证据强度、比较多篇论文的质量、查找某疾病的高等级证据(指南或 RCT)、或验证临床声明的证据支持度时,调用本 skill。整合 6 个原子...
Process meeting transcripts to extract reports, tasks, and memory. Handles "Process this meeting", action item extractio...
Analyze a Granola meeting into an evidence-backed briefing, decisions, findings, patterns, actions, and continuity. Use...
This skill should be used when the user asks to "회의 준비해줘", "회의 브리핑", "미팅 전 정리해줘", "오늘 회의 뭐 챙겨야 해", "회의 안건 정리", "메일이랑 일정...
Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave o...
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use w...
MAGI 1號機 - 科學家視角分析 (Claude Opus 4.5)。作為 MAGI 三機平行討論的一員，從架構、可行性、技術深度角度分析任務。觸發條件：MAGI 系統啟動時自動平行調用。
You are an expert in Mem0, the memory infrastructure for AI applications. You help developers add persistent, personaliz...
Intelligent memory layer for Clawdbot using Mem0. Provides semantic search and automatic storage of user preferences, pa...
Adds persistent, personalized long-term memory to LLM apps and agents with Mem0, the open-source memory layer: it extrac...
Add persistent, intelligent memory to AI agents with Mem0 — add/search/update/delete memories per user/agent/session, su...
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and p...
Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information acros...
Mem0 episodic memory write/read patterns for Beamix agents: mandatory metadata fields, retry policy, and fallback to Ant...
Auto-sync session context, decisions, and patterns to Mem0 for cross-session continuity
BDB local-first long-term memory engine (memB). Use when querying, remembering, or adapting preferences, code architectu...
Meme-format graphic generator — top + bottom text + optional centerpiece image. Impact-style bold typography. 5 template...
This skill should be used when the user asks to "search the KB", "find documentation", "add to knowledge base", "documen...
Optimize agent long-term memory by treating it as an information bottleneck problem. Dynamically compress redundant info...
SQLite 기반 메모 저장, 조회, 삭제 (사용자 선호도, 중요 정보 기억)
双层结构化长效记忆专家 (Kontext-Aware)
Update agent memory (Sessions, Lessons, Preferences, Checkpoint, Context) and Brief.md
MONAD-grounded cognitive architecture for AI memory as morphemic substrate navigation. Memory is not storage but substra...
Persistent memory system for preferences, facts, and notes
Route memory operations to appropriate backends (Graphiti for knowledge, AgentDB for coordination).
Store and recall long-term memory. Use when persisting facts learned during conversations or recalling stored knowledge...
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memor...
Execute extract and use project memories from previous sessions for context-aware assistance. Use when recalling past de...
Persistent key-value storage for session data, conversation context, and agent state. Use this skill when the user reque...
Persistent memory across sessions. Save project state and user preferences. Never save secrets.
Two-layer memory system with grep-based recall.
Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file
Manages cross-session knowledge persistence. Triggers on "remember", "recall", "what did we", "save this decision", "tod...
Filesystem-based knowledge management. Triggers on "remember", "save context", "knowledge base", "document decision".
State tracking, semantic cache, memory compaction, and agent histories.
Permanent memory using Lisa.
Cross-session memory — store, recall and query project knowledge across sessions. Detects whatever persistent memory is...
Establishes a persistent "Long-Term Memory" file to prevent context amnesia across sessions.
记忆检索服务。让 Agent 自主决定是否需要回忆过去的对话。 **使用场景**： 1. 用户问"之前我们讨论过什么"、"上次说的那个..." 2. 需要参考之前的上下文来回答当前问题 3. 用户提到某个之前讨论过的主题 **不要滥用**：...