В каталоге 182 820 навыков в 14 категориях.
Đồng bộ Master Feature Registry và shared contract trong .sdd
Truy vết yêu cầu và phân tích tác động từ SPEC đến PLAN, TASKS, code, test và contract
Validates the user's environment for SageMaker AI operations — checks SDK version, AWS region, and execution role. Use w...
Investigate external facts, options, mechanisms, and references; deliver usable evidence for a question, comparison, or...
Search the web using Tavily's LLM-optimized search API. Returns relevant results with content snippets, scores, and meta...
Full-text keyword search across every conversation at once (Telegram, Facebook, ChatGPT, Claude, notes, transcripts) ove...
搜索工具调用决策指南。明确定义 Agent 何时应调用搜索工具（如实时信息、具体事实），何时应依赖内部知识。作为参考规范，优化 Agent 的工具使用策略。
Search previous Claude Code conversations for a keyword or topic and return matching context. Use when the user asks "wh...
Search local documentation in the docs/ folder for content related to a topic
과거 세션 대화를 검색하는 스킬. CLAUDE_GATEWAY_SESSION_MEMORY 환경변수가 local 또는 external일 때만 사용 가능. none이면 이 스킬을 선택하지 마라. 사용자가 과거/이전/기억/...
Search the hierarchical memory system for relevant memories. Searches across all tiers (working, episodic, semantic) and...
Owns live-web retrieval through Tavily CLI (`tvly`), search, extract, map, crawl, research, on the cheapest verb that an...
Search past Claude Code conversation history and tool logs to recall previous solutions, commands, and approaches. ALWAY...
Use when replacing a seat's occupant (rebuild/handover/swap), reasoning about stable-seat-identity vs fluid-occupant-ide...
Knowledge base synthesized from the Guide to the Systems Engineering Body of Knowledge (SEBoK) v2.14 by the BKCASE Proje...
Anticipates the second- and third-order effects of a strategic decision or AI solution — how it changes customer behavio...
Use this skill when managing persistent user memory in ~/.memory/ - a structured, hierarchical second brain for AI agent...
Get a second opinion from an external LLM at three checkpoints: T1 is the plan valid, T2 which path at a fork, T3 finish...
Rotates a Thistle Commons service secret without downtime. Use when asked to "rotate the signing key", "rotate a secret"...
生成机器学习与 AI 类教程 (.rmd/.qmd)，涵盖算法原理、工程实践、模型评估、可解释性，强调 "问题定义 → 数据准备 → 模型训练 → 评估优化 → 可解释性"。
Med-sector overview across med.medicines_biotech and med.medical_devices with med trends, catalysts, FDA-decision contex...
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descri...
Expert guide for prompting ByteDance's Seedance 2.0 AI video model (text-to-video, image-to-video, first/last-frame, mul...
船长AI视界整理维护的 Seedance 2.0 二次元打戏视频提示词技能，用于设计、诊断和改写角色对战、武打动作链与镜头调度。
把用户的自然语言视频需求转换为符合 Doubao Seedance 2.0 进阶公式的提示词（8 要素：精准主体+动作细节+场景环境+光影色调+镜头运镜+视觉风格+画质+约束条件）。用于"帮我写一个 Seedance 提示词"、"生成视频提...
Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images,...
Generate AI dance and motion videos with Seedance (ByteDance) via AceDataCloud API. Use when creating videos from text p...
Generate and edit AI images with Seedream (ByteDance) via AceDataCloud API. Use when creating images from text prompts,...
Augmented vision tools for analyzing images beyond native visual capabilities. Use when tasked with describing images in...
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using...
SAM: zero-shot image segmentation via points, boxes, masks.
社会情感学习（SEL）专家系统——基于CASEL框架的完整知识体系与实践指南。 涵盖五大核心能力（自我意识/自我管理/社会意识/人际关系/负责任决策）、 课程设计、教学策略、评估工具及全球本土化实践。 触发词：「SEL」「社会情感学习」「情...
Prüfung der strafbefreienden Selbstanzeige bei Steuerhinterziehung – Wirksamkeitsvoraussetzungen und Vollständigkeitsgeb...
Detect signatures of natural selection using Fst, Tajima's D, iHS, XP-EHH, and other selection statistics. Calculate pop...
Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md. Use when the use...
The single config quality skill. Two modes: (1) Default — review/wire pending self-improvement proposals. (2) Audit — an...
Darwin Gödel Machine patterns for self-improving AI agents with open-ended
Self-hosted AI — run your own LLM inference, image generation, speech-to-text, and embeddings. No cloud APIs, no SaaS su...
Extract lessons from the current session and route them to the appropriate knowledge layer (project AGENTS.md, auto memo...
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for...
Capture user feedback and corrections to enhance repository documentation and skills. Transforms conversational feedback...
Role assignment for Claude Agent
自我反思 + 自我批评 + 自我学习 + 自组织记忆。智能体评估自己的工作，捕捉错误，并永久改进。适用于以下场景：(1) 命令、工具、API 或操作失败时；(2) 用户纠正你或拒绝你的工作成果时；(3) 你发现自己的知识过时或不正确时；(4...
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learning...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails...
General SOP for common requests related to self, nn, torch.
SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcemen...
Turn owner feedback about agent behavior into concrete system changes. Use when the owner says something is off, wants t...
Missing state triggers repair, not failure.
Redis semantic caching for LLM applications. Use when implementing vector similarity caching, optimizing LLM costs throu...
Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fr...
Evaluate semantic consistency between AI-generated clinical notes and expert gold standards using BERTScore and COMET
Create, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific refe...
Build AI applications with Microsoft Semantic Kernel. Create plugins, planners, memory systems, and AI orchestration. Us...
Build AI applications with Microsoft Semantic Kernel. Create plugins, planners, and memory systems. Use for enterprise A...
Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper referenc...
Setup vector embeddings and semantic search for document collections. Use for AI-powered similarity search, finding rela...
Send a message to the orchestrator. Use for blockers, progress updates, requesting review, or communicating status durin...
World-class senior data scientist skill specialising in statistical modeling, experiment design, causal inference, and p...
World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expe...
银发教育 (银发教育) Master OS — automated mastery of 银发教育: top builders' mental models, tool stack, current workflows, jargon, a...
ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment...
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in Py...
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "...
Use when the user asks for STRIDE threat modeling, DREAD risk scoring, data-flow-diagram threat analysis, or a quick sec...
Iteratively improve skill frontmatter to achieve good routing test coverage. WHEN: run sensei, sensei help, improve skil...
Iteratively improve skill frontmatter compliance using the Ralph loop pattern. USE FOR: run sensei, sensei help, improve...
Expert skill for multi-sensor fusion and state estimation using Kalman filtering. Implement EKF/UKF, configure robot_loc...
Combining IoT sensor data using algorithms like Kalman filters for improved accuracy and reliability
This skill covers the implementation of core software systems for autonomous vehicles and drones, including sensor fusio...
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic simi...
Master orchestrator for a full SEO audit suite powered by the Ahrefs MCP. Use this skill when running a comprehensive SE...
Bing Webmaster Tools + IndexNow extension. Microsoft Copilot citations are fed by the Bing index; this skill makes Bing...
Audit robots.txt for AI crawler access policies. Checks GPTBot, ClaudeBot, PerplexityBot, Google-Extended, and other AI...
Create and manipulate Seq, MutableSeq, and SeqRecord objects using Biopython. Use when creating sequences from strings,...
Find homologous sequences using iterative BLAST (PSI-BLAST), profile HMMs (HMMER), and reciprocal best hit analysis. Use...
Interface for long-term memory and context management. Use to store and retrieve user preferences, project context, and...
This skill should be used when the user asks to "create a memory", "read memories", "manage memories", "document pattern...
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Dock...
Service 层架构设计规范。修改 services/ 目录（非 llm 子目录）时必须加载。涉及 Memory、Session、Retrieval、OSS 模块变更时触发。
Orchestration classes that coordinate multiple Actions, external APIs, or domain operations into a cohesive workflow. Se...
セッション管理の総合窓口。初期化・記憶・状態を一手に引き受けます。Use when managing Claude Code sessions, /session command. Do NOT load for: app user ses...
Session lifecycle management. Parent skill for session-related skills: learning (pattern extraction) and compact (contex...
Inspect this agent's stored JSONL session transcripts — list, read, search, or recall recent turns.
Initiates a new session by running the startup sequence, reading required files, adopting the configured persona, and gr...
Project state awareness and session recovery for GSD-managed projects. Use this skill whenever: starting a new work sess...
Complete verification steps before starting any work session
Agent init prompt.
Detect and handle session boundaries for multi-context autopilot workflows.
Universal context persistence across sessions. Auto-saves decisions, conventions, and progress to .rune/ files. Loads st...
This skill should be used when the user says "save checkpoint", "checkpoint", "continue", "resume", "resume work", "save...
[Beta] Retrieves task-relevant prior sessions and returns a short, cited brief of decisions, corrections, failed approac...
Session startup with context recovery. USE WHEN starting session, after /clear, or recovering from autocompact.
Performs smart context summarization when the context window is approaching capacity. Identifies what to keep, what to s...
Project-agnostic guidance for continuing work across Claude sessions. Ensures context recovery, task resumption, and sta...
Resume work from previous session by loading minimal context based on time elapsed
Send messages to and receive replies from another active opencode session. Use when orchestrating multi-session dialogue...
View active session status with progress and context information
End-of-session memory distillation — extracts key decisions, eliminated approaches, new discoveries, and current blocker...