В каталоге 182 820 навыков в 14 категориях.
Implement real-time streaming UI patterns for AI chat applications. Use when adding response lifecycle handlers, progres...
Implement SSE, WebSockets, LLM token streaming, and real-time broadcasting in FastAPI.
This skill should be used when the user asks about "Effect Stream", "Stream.from", "Stream.map", "Stream.filter", "Strea...
Cognitive training practices for AI agents — short, self-applied exercises that develop attention, calibration, delibera...
Local protein structure prediction with AlphaFold, Boltz, or Chai. Compare predicted structures, compute RMSD, visualise...
Structured Autonomy Implementation Prompt
StructuredDecompositions.jl sheaves on tree decompositions for FPT algorithms with bidirectional navigation
Use when an LLM must return machine-readable data. Covers schema design for models, native structured-output modes, vali...
This skill should be used when the user mentions "structured output", "json mode", "tool schema", "function calling", "j...
This skill should be used when the user requests "get JSON with fields X, Y, Z", "need JSON output from this text", "cre...
A skill for understanding and using the STSBench dataset for modeling neuronal activity in the dorsal stream of primate...
When a learner gets something wrong or feels stuck, require them to diagnose the problem before receiving help. Ensures...
Detect stuck loops and advise recovery strategies
研学营地教育 (研学旅行与营地教育（体验式教育新赛道，从业者 + 运营视角）— 中国 2016 年教育部《关于推进中小学生研学旅行的意见》政策驱动后形成的细分赛道，含 (a) 子赛道：自然教育 / 科技研学 / 红色研学（爱国主义+党史）/...
写前深读真书语料 → 落「腔调锚笔记」→ 与反AI味纪律双管齐下的仿写工序（corpus-grounded style mimicry）。触发场景：写长篇小说、写角色卡卡面文案（简介/开场白/示例对话）、任何「要像真人书的成文」任务，以及「...
Reference guide for 42 interior design styles — use when you need style characteristics, keywords, color palettes (hex c...
Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creatio...
Every skill consists of a required SKILL.md file and optional bundled resources:
Execution skill for delegated tasks. Use this skill when you are a subagent that has been delegated a task by the tech l...
Use when executing a multi-task plan where each task is independent, or when the user wants parallel or isolated task ex...
Use when executing implementation plans in current session. Dispatches fresh subagent per task with two-stage review. Sp...
Use when executing implementation plans with independent tasks in the current session
Execute implementation plan by dispatching fresh subagent per task. Each task gets: Implementer → Spec Review → Quality...
Use fresh agents for focused subtasks to avoid context pollution
This skill should be used when coordinating "multiple specialized agents", "complex workflow orchestration", "autonomous...
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans...
Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent for eac...
（中文）Use when executing implementation plans with independent tasks in the current session
subagent-driven-development
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
(ePost) Use when a plan has 3+ independent tasks, phases have non-overlapping file ownership, or user says "parallel imp...
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for ea...
Use when decomposing complex work. Dispatch fresh subagent per task, review between tasks. Flow: Load plan → Dispatch ta...
Execute implementation plans by dispatching a fresh subagent per task with two-stage review (spec compliance then code q...
Use when a task spans 3+ files or components; You want multiple agents working at the same time
Coordinate quota-aware parallel subagents for large, multi-file Antigravity tasks.
Patterns for when and how to use Claude Code subagents via the Agent tool. Use when the user needs to delegate research,...
Produce a comprehensive prompt that hands off the current session's work to a fresh session for sub-agent-orchestrated e...
Imported skill subagents from langchain
Use when the agent needs the overview of Subnet-EVM stateful precompiles and the shared AllowList interface (Admin/Manag...
自动生成视频字幕。解析配音文案，生成同步字幕，使用 Remotion 组件渲染。支持中英文双语字幕。
Design AI evals that catch regressions before users do: rubrics, test cases, failure modes, acceptance gates, and AI-SPE...
Enables claude to manage sugar's autonomous development workflows. it allows claude to create tasks, view the status of...
現在の状況やタスクに合わせて、今使うべきおススメのスキルを提案する
Use when the user describes any situation, problem, goal, complaint, or question — including when they want to browse av...
Recommends team composition based on outcomes and mode. Invoked by launch commands during team setup.
Repository URL (if exists):
Summarize text using extractive, abstractive, hierarchical, and multi-document techniques, producing concise outputs at...
Autonomous orchestrator for manifest work items through the development lifecycle. Use when running egregore to process...
Launch AutoMates agents in separate terminal windows with their identities
Launch a build team (Fetcher + Planner + Builder + Checker) for parallel feature development
Launch a research team (Fetcher + BrainStorm + specialist) for deep investigation
Launch a review team (Checker + Legal + Gal + GitDude) for comprehensive quality assessment
孙宇晨（Justin Sun / 孙割）的思维框架与行为逻辑。基于6个维度（著作、深度采访、表达DNA、 他者视角、决策记录、时间线）共1500+行调研素材的深度蒸馏， 提炼6个核心心智模型、8条决策启发式、5种割味造句公式和完整的表达DN...
Constructs technical Suno V5/V5.5 style prompts, selects genres, and optimizes generation settings. Use when creating or...
Constructs technical Suno V5 style prompts, selects genres, and optimizes generation settings. Use when creating or refi...
Generate AI music lyrics and style tags for Suno AI, calibrated to context. Produces complete song files with lyrics und...
AI音乐生成工具Suno的浏览器自动化Skill。通过Playwright控制Suno网站(https://suno.com)进行：生成歌曲(含自定义歌词)、管理创作、下载音频。触发场景："用suno生成歌曲"、"Suno创作"、"AI音乐...
Super Ralph Wiggum - autonomous iteration loops with templates, PRD support, progress tracking, and browser testing. Thi...
Provides flag definitions and usage rules when double-dash flags (--flag-name) detected in user prompt - describes execu...
Run a superRA task tree autonomously through dispatched implementer and reviewer seats. Requires superRA:using-superra....
Use only after explicit Codex `$superloopy:superloopy-research` or Claude Code `/superloopy:superloopy-research` invocat...
统一开发编排器：将 Superpowers 方法论框架与 AI 代码工厂深度整合， 创建统一的开发工作流，结合 TDD 纪律、SoT 合规和自动化代码生成。
Lab environment for Claude superpowers
Mnemosyne's supersede skill. Applies OpenChronicle supersede semantics to a vault note — strikes outdated entries, adds...
Court-grade intake supervisor. Extracts structured facts, parties, issues, timeline, jurisdiction hints, and missing fie...
Implement supervised MCP/sub-agent worker pools and autoscaling behavior.
供应链与生产运营 (供应链与生产运营 (Supply Chain & Production Operations) — 面向制造业与消费品实体供应链的『计划-制造-交付』运营判断,不是采购谈价技巧,也不是跨境电商发货物流。覆盖: (a) 第...
This skill group covers the calculation of surface energies and the prediction of equilibrium crystal shapes via the Wul...
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted...
Change the embedding model used to index and search documents (OpenAI, Cohere, Voyage, a local server). Use when the use...
Autonomous multi-agent workflow system for complex coding tasks. Use when the user requests non-trivial changes that wou...
Dispatch a swarm using any orchestration pattern. Routes to the appropriate pattern-specific skill based on the selected...
Spawn isolated Codex sub-agents for parallel task execution using the current runtime primitives. Triggers: "swarm", "sp...
N coordinated agents on shared task list with SQLite-based atomic claiming
Use when many beads are independent and file conflicts are rare. No lead agent needed — workers self-coordinate through...
Speculative swarm — forks N agents to explore divergent strategies for the same task, cross-pollinates insights at check...
Parallel task execution using Gemini Flash workers. 200x cheaper than Opus. Use for any parallelizable work to preserve...
Atomic multi-agent batch execution engine. Executes a single concurrent batch of M Interns via subagent_batch and aggreg...
Coordinate multi-agent swarm workflows. Use when working in parallel with other agents, managing shared resources, or or...
Multi-agent swarm coordination patterns. Orchestrates parallel agent execution, manages agent communication, handles tas...
Fan-out parallel specialists for concurrent analysis. Dispatch read-only reviewers, researchers, and analyzers against a...
Initialize a multi-agent swarm with anti-drift configuration
Map-reduce orchestration. Parallel mappers process input chunks independently, then a dedicated reducer merges all outpu...
Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and ant...
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordina...
Pipeline and task-graph orchestration. Sequential stages with dependency edges — linear chain or arbitrary DAG.
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.
Swarm reliability watchdog for OpenClaw — validates gateway/channel and every lane, performs bounded recovery, and emits...
Speculative orchestration. Competing implementations in isolated worktrees, evaluated by a judge who selects the winner.
Become the supervisor of a multi-session agent swarm. Use when handed a batch of work (a fixes list, an upgrade plan, QA...
Self-claiming pool orchestration. Workers race to claim tasks from a shared pool, loop until the pool is empty.
SwarmKit SDK development for TypeScript and Python. Use when building applications with SwarmKit to run AI agents (Claud...
Improve SWE agent RL via execution-free reward models optimized for three metrics beyond TTS: discriminative ability (AU...
Cross-company language sweep via Quartr full-text search — date the adoption curve of a term/phrase across the global tr...
Exposes Claude's reasoning chain as an auditable, decomposable artifact. Quick mode (default) gives assumption inventory...