В каталоге 182 820 навыков в 14 категориях.
Train neural models (LSTM, Transformer, N-BEATS) on market data using npx neural-trader with confidence intervals
Cross-context shared trading discipline — output language, independent verification, scenarios not points, noise filteri...
Reference system prompt and tool schemas for Trae. Use when imitating, comparing, or analyzing Trae's prompting style; d...
Auto-generate custom agents and skills for remaining capability gaps after assembly. Creates definitions based on projec...
Voice-first runtime steering + nightly deep analysis to learn per-user conversation steering priors.
Execute model training with optimization algorithms. Use when running training loops on datasets.
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasti...
Build train machine learning models with automated workflows. Analyzes datasets, selects model types (classification, re...
Schema, grounding rules, outcome status and cost ledgers for agent trajectories. Use when an agent must record, replay o...
Review how an agent reached its result, not only whether the result passed, covering tools called, detours, unverified a...
Transcribe specific video URL(s). Use when you have one or more TikTok video URLs to process.
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe spe...
Transcribe audio and video from URLs (YouTube, direct media links) using WhisperKit locally. Optionally analyze transcri...
Reach for this whenever what was SAID in a YouTube video matters: a pasted link or bare video ID, a summary, quote, tran...
Search and analyze Claude Code transcripts for past decisions, solutions, and discussions. Use when recalling past conte...
Reach for this whenever a task touches YouTube, said or unsaid: pasted video/channel/playlist links, IDs and @handles, s...
Use when rewriting an existing skill so Opus 4.7 (or any frontier reasoning model) executes it with better judgment, les...
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention...
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer...
This skill should be used when working with pre-trained transformer models for natural language processing, computer vis...
Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub...
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (tex...
Run Hugging Face models in JavaScript or TypeScript with Transformers.js in Node.js or the browser.
Six transitions with exact presets and the editing rules behind them: photo collage burst, Droste recursive zoom into a...
> Compiler: skill-compiler/1.0.0
This skill group covers first-principles calculation of electronic transport properties using the Boltzmann transport eq...
根据用户提供的 1–10 张真实旅拍照片和旅游地点，设计文旅宣传片的推荐分镜顺序、统一视觉母版与逐镜头首帧图生视频提示词。适用于让旅拍照片自然动起来、设计克制运镜和后期剪辑连续性的请求；输出可独立复制的提示词，不直接提交视频生成任务。
旅行 vlog 地图视频：用户给一组旅行照片（和一张自己的照片），自动按照片 GPS 和拍摄时间找出机位、排好顺序、沿真实步行/驾车路线连起来；用照片生成用户的 Q 版卡通形象，卡通小人沿路线一颠一颠地走，右上角里程累加，走到每个机位停下「...
Reference system prompt and tool schemas for Traycer AI. Use when imitating, comparing, or analyzing Traycer AI's prompt...
Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
Phylogenetic tree visualization and formatting with ggtree (R) or iTOL (web). Use when rendering a phylogenetic tree as...
Learns unified hierarchical cell-type trees across multiple scRNA-seq reference atlases using scArches + scHPL on scVI/s...
Backend orchestrator for Treido. Use to route data/auth/payments work to the right specialist (Supabase, auth, Stripe, c...
Frontend orchestrator for Treido. Use to route UI work to the right specialist (Next.js, Tailwind, shadcn/ui, design, mo...
Orchestrates Treido work end-to-end (parallel specialist audits, single-writer plan, execute, verify/test). Uses a bundl...
Skill-system maintainer for Treido. Use to create/merge/trim skills, enforce treido-* naming, and keep `.codex/skills` m...
Multi-signal trend forecasting for autonomous agents. Combines prediction market odds, Twitter/X social sentiment, news...
TrendRadar 多平台热点监控日报生成与 Telegram 推送
Interleave three deterministic color streams into balanced schedules for parallel execution and evaluation.
Orchestrates multiple skills in GF(3)-balanced triplets. Assigns MINUS/ERGODIC/PLUS trits to skills ensuring conservatio...
Move issues through a state machine of triage roles — categorise, reproduce, grill if needed, and write agent-ready brie...
将 issue 和外部 PR 推过一组分诊角色的状态机——分类、验证、必要时盘问，并写出 agent 就绪的任务简报。
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write ag...
Triangle Metrics Skill
LangSmith prompt governance for Triatu. Use when moving prompts out of code, versioning them, or documenting prompt mana...
Runs a doer -> verifier-panel -> consensus loop to verify a deliverable before it ships. An orchestrator freezes accepta...
Run one neutral prompt independently across every discovered model from selected CLI providers, then compare all answers...
AI agent patterns with Trigger.dev - chat.agent, Sessions, AI Prompts, Trigger Agent Skills, orchestration, parallelizat...
GF(3)-balanced structured decompositions for parallel computation. Decomposes problems into MINUS/ERGODIC/PLUS component...
Finalises a reviewed task — creates PR and merges using the TRIPLE protocol, as the lead agent.
Starts working on a task using the TRIPLE protocol, as the impl agent.
Helps define a TASK.md for the current task using the TRIPLE protocol, as the lead agent.
Reviews a task using the TRIPLE protocol, as the review agent.
Configure triton inference config operations. Auto-activating skill for ML Deployment. Triggers on: triton inference con...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRP...
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO...
Troubleshooting protocol with MiniMax subagent delegation - NEVER stop early, use all resources before asking user
tRPC end-to-end type-safe APIs for TypeScript with React Query integration and full-stack type safety
Orchestrator for Truesight MCP skills. Use this when the user needs help choosing the right Truesight workflow or when i...
唐纳德·特朗普（Donald Trump）的思维框架与行为逻辑。基于著作、长访谈、辩论、 心理分析、前幕僚回忆录、重大决策记录共6个维度的深度调研（320KB+原始资料）， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途：（...
Specifies guidelines for the AI assistant to provide accurate, thoughtful answers, admit when it doesn't know something,...
基于 aihot.virxact.com 最新 AI 资讯，为 AI 口播频道（试界TryWorld · 纸上算法风格）产出选题清单。由 $tryworld-koubo 在模式 B 下路由调用；被显式点名「只要选题」时也可直接触发。产出为...
Use this skill when the user wants Tsui Hark / Xu Ke-inspired fantasy action, wuxia spectacle, kinetic camera ideas, eas...
Text-to-speech synthesis with ElevenLabs and system voices
This skill standardizes the end-to-end Horus voice workflow using uvx-style
MUST read immediately before drafting a prompt for, selecting a voice for, or calling `manus-tools.generate_speech` — in...
MUST read this skill BEFORE entering generate mode for text-to-speech (TTS) tasks. Covers prompt crafting framework, sep...
Multi-engine text-to-speech skill. Supports Qwen3-TTS local voice cloning, VoiceCraft online TTS, and OpenAI TTS.
This skill provides a general, composable workflow for building datasets and training
Send messages to other tmux sessions for multi-agent coordination. Use when user types 'ttt' or needs to communicate wit...
Remove pauses, filler words (um, uh), and dead air from raw YouTube recordings via the Tubeify API. Use when the user wa...
优雅结束会话——逐级收集状态、shutdown 所有 Teammate、生成会话总结后退朝
---name: tumor-clonal-evolution-agent
---name: tumor-heterogeneity-agent
---name: tumor-mutational-burden-agent
Generates code via Cerebras hosted LLM from a structured contract prompt, writes files directly to disk, then applies su...
プロジェクト プロジェクトの **実際の並列実行エンジン**。 ultrawork + ecomode + Crystal の TaskQueue コンセプトを統合。 **v3.0 核心変化**: Enforced Skill Patte...
Türkçe metinlerden AI-üretimi yazım imzalarını temizler ve metnin registeri uygunsa insan Türkçesinin ritim imzalarını y...
Interactive walkthrough of Egregore's Local core loop — activity, reflection, and a quest — using adaptive questions and...
name: 'Tool Description: Skill'
Build trading systems in the style of Two Sigma, the systematic investment manager pioneering machine learning at scale....
Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft...
Best practices for using the Council MCP server in Tzurot v3 development - When to consult external AI, how to structure...
Build and operate the "Memory Tool Health Monitor" capability for Memory and Knowledge Operations. Trigger when this exa...
Build and operate the "Memory Regression Sentinel" capability for Memory and Knowledge Operations. Trigger when this exa...
Build and operate the "Memory Equity Impact Scorer" capability for Memory and Knowledge Operations. Trigger when this ex...
Build and operate the "Memory Skill Gap Diagnoser" capability for Memory and Knowledge Operations. Trigger when this exa...
Use when the user wants to "model a problem", "translate to math", "formalize a problem", "mathematical modeling", "how...
Designs draft UCP vendor-namespace extensions for service commerce, including service capability profiles, scope, pricin...
Predicts access barriers in a learning task before delivery, given a learner variability profile. Distinguishes between...
Audits an existing lesson against UDL's three principles — engagement, representation, and action/expression. Identifies...
Generates multiple means of engagement, representation, and action/expression for a given learning goal. Produces specif...
YOLO UI元素检测器项目管理。训练自定义模型识别界面元素（按钮、输入框、二维码等），用于半自动化操作。
Non-Archimedean distance metrics for hierarchical clustering and p-adic analysis
Autonomously iterates until specified Plans.md range is complete - long-running /work with self-learning. Use when user...
Parallel execution engine for high-throughput task completion
Configure, repair, or audit Umbrella Dynamic Image in ASP.NET Core, Blazor, or Razor applications. Use for analyzer and...
Scaffold a Razor-view-based email sender (interface, implementation, Razor views, DI registration) following the Umbrell...
Scaffold Mapperly mapper classes that map between EF Core entities and API model records, or between client-side model t...
Scaffold a logic service (interface, implementation, models) in the Core.Logic project, following the Umbrella ServiceBa...