В каталоге 182 820 навыков в 14 категориях.
Genera un resumen de entrega (handoff) para cambiar de LLM entre fases sin perder contexto ni reglas.
タスクの複雑さに応じて Claude のモデルを自動的に切り替える。複雑なタスク（アーキテクチャ設計、大規模リファクタリング、難解なバグ修正）では opus を、単純なタスク（小さな修正、フォーマット、簡単な質問）では sonnet を自動...
Generates a curated supplementary reading list from any course syllabus using Consensus academic search. Grill-me intake...
Trans-architectural pair-inquiry — state a finding to another LLM, ask for the next experimental move, execute it, repor...
Translate text accurately between languages with pronunciation guidance for non-Latin scripts.
MANDATORY sync rules for CLAUDE.md and agents.md files. This skill MUST be activated whenever editing CLAUDE.md, agents....
Fast save-point: sync all session-context files and MEMORY.md with current progress. Zero questions, zero delay. Use whe...
Sync Claude Code AI tooling (skills, MCP servers, rules) across Warp, Cursor, and VSCode. Idempotent — safe to re-run. U...
/vibecorp:sync-check で検出された不整合を、各職種エージェントに委任して修正する。 各エージェントは自分の管轄ファイルのみ編集する。 「/vibecorp:sync-edit」「整合性を直して」と言った時に使用。
Sync files (skills, packages/core/patterns, agents, specs) from EN canonical repo to PT mirror, inserting "Tradução pend...
Synchronize shared rules into agent context files and headers.
Сделать сессии Claude Code на ЭТОМ компьютере видимыми под любым аккаунтом, как локальные треды Codex. Триггеры: /sync-s...
Promotes important observations from memory systems (Claude-mem, Serena) to SSOT (decisions.md, patterns.md). Use when u...
Build apps that USE synced-store for real-time multiplayer state. PROACTIVELY load when: designing a new Poe tile's stat...
Invoke SYNTHESIZER Deputy for operations, execution, and cross-domain coordination.
LLM-generated training data, augmentation strategies, distillation datasets, self-instruct and Evol-Instruct patterns, q...
Use AgentPMT external API to run the Synthetic Data Generator tool with wallet signatures, credits purchase, or credits...
You have access to a skills system that provides curated instruction files
Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination
System prompt assembly for blah.chat AI backend. Multi-layer prompt construction with priority ordering, parallel contex...
Design effective system prompts for custom agents. Use when creating agent system prompts, defining agent identity and r...
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured im...
Autonomously correct project rules when negative feedback occurs. Use PROACTIVELY when user says 'no', 'wrong', 'wait',...
World T Skill
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking...
Use when working as the primary coding agent in a T4-team repo (T4 Labs / Slow-Inc) and you need durable memory across s...
Use LightGBM DART boosting (dropout on trees) with aggressive feature and bagging fractions to reduce overfitting on hig...
Generates out-of-fold predictions from auxiliary models and uses them as input features for the final model.
Augments training data with high-confidence test predictions as pseudo labels, retrains the model, and keeps the result...
Two-stage stacking where Ridge regression on OHE+scaled features produces OOF predictions fed as an extra feature to XGB...
Enforce consistent tagging across the Obsidian wiki using a controlled vocabulary. Use this skill when the user says "fi...
Use when working through Takopi (Telegram bridge) to route Codex tasks by project, branch worktree, or topic; covers dir...
塔勒布(Nassim Nicholas Taleb)的思维框架与表达方式。基于40+个来源的深度调研， 提炼6个核心心智模型、9条决策启发式和完整的表达DNA。 用途：作为思维顾问，用塔勒布的视角分析问题、审视决策、质疑主流叙事。 当用户提...
Talent Sourcing Engine. Professional enterprise agent for Talent Sourcing Engine within the Operations & HR sector.
Turns a script into an animated talking-character video ad: one or more characters rendered in an animated style talk to...
Generate natural, ElevenLabs-ready talk tracks for physician course lectures using Ralph-style iterative architecture wi...
Operate Tandem as a multi-agent, multi-device MCP orchestrator. Use it when an MCP-capable caller needs to start, inspec...
唐家三少网文创作思维——日更自律、魂环体系、院线流模板、爽文进度条、IP全产业链、六波推动模式。 触发词：「唐家三少视角」「像唐家三少那样写」「斗罗大陆」「升级流」「院线流」「六波推动」。 擅长：升级流体系设计、院线流模板、爽文节奏管控、I...
TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama. Use for chat...
LLM-generated TypeScript execution in sandboxed environments: createCodeModeTool() with isolate drivers (createNodeIsola...
Server-side AG-UI streaming protocol implementation: StreamChunk event types (RUN_STARTED, TEXT_MESSAGE_START/CONTENT/EN...
Chat lifecycle middleware hooks: onConfig, onStart, onChunk, onBeforeToolCall, onAfterToolCall, onUsage, onFinish, onAbo...
Use when wiring honcho() from @tanstack/ai-memory/honcho — a hosted memory adapter where recall is a dialectic answer ov...
Use when wiring inMemory() from @tanstack/ai-memory/in-memory — explains setup, options (embedder, extract, topK/minScor...
Use when wiring mem0() from @tanstack/ai-memory/mem0 — a hosted memory adapter that talks to a mem0 server over plain HT...
Use when wiring redis() from @tanstack/ai-memory/redis in production — covers client setup (ioredis or node-redis via fr...
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evalua...
Predict miRNA target genes using sequence-based algorithms and database lookups. Use when identifying potential mRNA tar...
Execute complex tasks with planning, parallel subagents, atomic commits, and documentation updates. Use when the user as...
Autonomous batch task execution with PRD parsing, task decomposition, and continuous execution until all tasks complete....
Patterns for using TaskCreate, TaskUpdate, TaskList, and TaskGet to coordinate multi-step work. Use when the user has a...
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and wor...
Project-agnostic skill for delegating execution work to subagents with skill activation, parallel execution, and quality...
Task delegation patterns for multi-agent systems - hierarchical, parallel, and reactive delegation.
Delegate tasks to specialized agents and coordinate multi-agent workflows for parallel test generation
AI reasoning skill for detecting user intents from natural language, mapping to MCP tools, handling multi-step workflows...
Parse memory.yaml and consolidate recurring patterns into skills. Use when memory.yaml grows large, when patterns recur...
思源任务笔记管理插件 MCP 工具总览技能。
Orchestrate the complete development workflow for implementing sub-tasks from a task list. Use for end-to-end feature im...
Documentation-first task execution with quality checks and progress tracking. Use when working with task lists, implemen...
Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing hear...
Parse natural language task input and extract structured data (title, due date, priority, category) using Google Gemini...
Automatically analyze tasks and route to optimal agent(s). Use when receiving complex requests to determine which agents...
Autonomous task management with execution loop. Creates tasks, executes them, spawns subtasks when blocked, and NEVER st...
A creative-direction (taste) layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop visu...
Use when scaffolding a new Tauri 2 project, setting up initial project structure, or generating boilerplate code. Preven...
Archived skill guidance for tavily.
Tavily web search, content extraction, and research tools.
使用Tavily API进行网络搜索，获取实时信息、回答问题或研究主题
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
Use Tavily Search API for optimized, real-time web search results for RAG. A pre-configured, cost-effective search tool.
Web search, online search, real-time search, internet search, Google alternative, Bing alternative, DuckDuckGo alternati...
Executes Tavily AI search, extraction, crawling, mapping, and deep research via Python CLI. Use when web search, URL con...
Web search, content extraction, crawling, and research capabilities using Tavily API
Extract Federated Taxonomy tags from text. LLM extracts candidates, deterministic validation filters to known vocabulary...
购物决策 + 家居避坑。给明确答案，不给「看个人需求」的废话——口碑、对比、比价、线下导购四类服务。 When to use / 适用场景: 购物、买什么、值得买、数码、3C、家居、家电、装修、买房、A 和 B 选哪个、哪里买最便宜、怎么砍...
---name: tcr-pmhc-prediction-agent
---name: tcr-repertoire-analysis-agent
Scout ONE external surface of the TouchDesigner community for what's HYPED in 2025-2026 that could become a tdmcp tool....
TDD workflow for migrations - orchestrate agents, zero main context growth
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehens...
Teach the user a new skill or concept, within this workspace.
Teach a concept, walk through a session, or conduct an explicitly requested ongoing course.
The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic quest...
并行团队执行，N 个协调 Worker 协作
Use when executing large plans with mixed dependencies, shared-file conflicts, or TDD ordering that requires lead coordi...
Quickly assemble a temporary AI Agent team for a task. Automatically selects the best members from .claude/agents/.
Multi-agent meta-orchestrator. Use when task spans 5+ files or 3+ modules, or when user says 'parallel', 'split this up'...
Unified team skill for architecture optimization. Uses team-worker agent architecture with role directories for domain l...
首次创建 Teammate 的引导流程——太子首次协作或尚书首次派发六部时加载，完成 Team 创建与分层启动
Unified team skill for brainstorming team. Uses team-worker agent architecture with role directories for domain logic. C...
Preset-driven team building — spawn coordinated multi-agent teams from battle-tested presets for full-stack, review, tes...
Design and generate team command .md files following established patterns (8 infrastructure patterns + 10 collaboration...
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown pr...
Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this...
Autonomous mission-control skill with two parameterized modes for the two team branches:
Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files...
Multi-person projects - shared state, todo claiming, handoffs