В каталоге 182 820 навыков в 14 категориях.
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Us...
Documentation for the logistic regression MI estimation experiment (exps_logistic)
Documentation for the main LLM performance experiments (exps_performance)
Extended thinking (ultrathink) configuration for Claude API. Activate for complex reasoning tasks, deep analysis, multi-...
Comprehensive guide for authoring Claude Code extensions including skills (SKILL.md), hooks, slash commands, and subagen...
Claude Codeの拡張機能（スキル、サブエージェント、プロジェクト設定）をユーザーの自然言語指示から自動生成するスキル。「○○を作るスキルを作って」「○○エージェントを作って」「CLAUDE.mdを設定して」などのリクエスト時に使用。...
Synthesize consensus implementation plan from multi-agent debate reports using external AI review
Write PR descriptions and maintainer replies for third-party upstream repos in natural, concise human prose to avoid mai...
Manage offline reference material in the `extra/` directory. Use when needing external documentation, library source cod...
Extract skill candidate from conversation. Use when identifying automatable logic suitable for skill. Keywords: extract,...
Identify and document model hyperparameters from papers. Use when setting up training configurations.
Turn successful interactions into reusable prompts
Strategies and patterns for ensuring data persistence in distributed systems, handling failures, and maintaining data in...
Write the follow-up after a call in the owner's own voice instead of a bot template: recall the transcript, person card...
Read-only gap check. Finds which of the 16 sections of Anthropic's Fable 5.1 prompting guide your CLAUDE.md, rules files...
Intelligent pattern selection for Fabric CLI. Automatically selects the right pattern from 242+ specialized prompts base...
Intelligent prompt pattern system with 240+ specialized patterns for content analysis, extraction, and transformation. U...
Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summa...
Guides pattern selection through decomposition, exploration, and diverse approach generation
Analyze and transform faces via AceDataCloud API. Use when detecting face keypoints, beautifying portraits, aging/de-agi...
Beautify flow cytometry gating plots for publication. Applies contour, density, or dot plot styles to FCS data and produ...
Pipeline complet requirements → release (auto-detect greenfield V1 / brownfield V2+)
Structured prompting with XML tags. A small named vocabulary (`instructions`, `context`, `input`, `output_format`, `exam...
Advanced .faf (Foundational AI-context Format) specialist. IANA-registered format, MCP server config, championship scori...
Recovery protocols for stuck agents, context exhaustion, build failures, and confusion. Use when agent is looping, respo...
Comprehensive guide for text-to-speech, speech-to-text, voice cloning, and voice agent development
Complete Guide to Anthropic Claude API (2025-2026)
You are an expert on text embeddings - numerical vector representations of text that capture semantic meaning. Help user...
SDD feature executor: sequential task execution with quality gates. Runs tests/coverage validation after each task, perf...
Customize Language Models for Domain-Specific Tasks (2025-2026)
Complete Guide to Google Gemini API for Multimodal AI Applications (2025-2026)
Complete Guide to Text-to-Image, Image Editing, and Prompt Engineering (2025-2026)
Build Production-Ready RAG Pipelines (2025-2026)
LLM APIs: OpenAI, Claude, Gemini, local LLMs, prompt engineering, function calling.
Creates, edits, updates, or modifies Claude Code custom agents (subagents). Use when user asks to create agent, edit age...
Creates, edits, updates, or modifies Claude Code skills. Use when user asks to create skill, edit skill, update skill, c...
Create tasks from SDD documents (spec + design + implementation plan). Uses faion-task-creator-agent agent for deep rese...
ML Engineer role: LLM APIs (OpenAI, Claude, Gemini), embeddings, RAG pipelines, fine-tuning, LangChain, LlamaIndex, vect...
ML operations: fine-tuning (LoRA, QLoRA), model evaluation, cost optimization, observability.
Multimodal AI: vision, image/video generation, speech-to-text, text-to-speech, voice synthesis.
Universal orchestrator for software projects: SDD workflow, research, product planning, development, marketing, project/...
Complete Guide to OpenAI Platform (2025-2026)
RAG engineering: embeddings, chunking, vector databases, hybrid search, reranking.
Text-to-Video, Image-to-Video, and Video Editing with AI (2025-2026)
Fairness assessment skill using Fairlearn for bias detection, mitigation, and compliance reporting.
Generate images, videos, audio, and more using fal.ai AI models. Use when user requests: "generate image", "create video...
Use when calling a fal.ai endpoint by id to generate image, audio, or video from JS/Python/curl: subscribe vs submit, qu...
Generate images, videos, and audio with fal.ai serverless AI. Use when building AI image generation, video generation, i...
Generate images, videos, and audio via fal.ai API (FLUX, SDXL, Whisper, etc.)
Text-to-speech and speech-to-text using fal.ai audio models
| STT Model | Endpoint | Speed | Accuracy |
Generate images and videos using fal.ai AI models
AI-powered image editing with style transfer and object removal
| Task | Endpoint | Key Parameter |
| Model | Endpoint | Audio | Loop | Best For |
Use when generating images or video via fal (FLUX, Veo, etc.) for brand, web, ads, or OpenMontage pipelines.
| Optimization | Technique | Impact |
Generate, remix, and edit images using fal.ai's AI models. Supports text-to-image generation, image-to-image remixing, a...
| Model | Endpoint | Speed | Quality | Cost |
| Model | Endpoint | Duration | Audio | Speed |
Train custom AI models (LoRA) on fal.ai — personalize image generation for specific people, styles, objects, or video ge...
Upscale and enhance image and video resolution using AI
Generate workflow JSON files for chaining AI models
法律案例拆解 - 资深法律分析师视角，系统化判决书案例分析
Orchestration pattern for parallelizable tasks. When facing work that can be split into independent subtasks (research m...
Parallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and...
This prompt directs the AI to keep the provided product image completely unchanged while generating a high‑resolution, s...
fast.ai deep learning library. Use for practical deep learning.
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration ena...
Build MCP servers in Python with FastMCP to expose tools, resources, and prompts to LLMs. Supports storage backends, mid...
Use when creating or modifying Model Context Protocol (MCP) servers with FastMCP framework - guides through tools, resou...
FastMCP TypeScript framework patterns for MCP servers. Auto-loads when building MCP servers, creating tools/resources/pr...
FastMCP is a Python framework for building Model Context Protocol (MCP) servers that expose tools, resources, and prompt...
FastMCP server patterns for building MCP servers. Use when implementing MCP tools, resources, or server configuration.
All-in-one read preprocessing with fastp including adapter trimming, quality filtering, deduplication, base correction,...
Guide through omicverse's alignment module for SRA downloading, FASTQ quality control, STAR alignment, gene quantificati...
Work with FASTQ quality scores using Biopython. Use when analyzing read quality, filtering by quality, trimming low-qual...
End-to-end DNA sequencing workflow from FASTQ files to variant calls. Covers QC, alignment with BWA, BAM processing, and...
Maximum velocity MCP execution via geodesic untangling. Maoist self-criticism for why slowtime was ever necessary. Topol...
尚书省容错降级机制（超时/斩杀/熔断）。适用：任务超时、失败、降级发生时
Use when the user asks about FDE playbooks, past engagements, eval plans, the knowledge base, vault notes, vector memory...
Feature store management skill for online/offline feature serving, feature registration, and training-serving consistenc...
Execute a complete feature development workflow for wouterwisse.com using Opus subagents.
ユーザーストーリー/Why/要求事項/タスクを入力として受け取り、コンテキストを収集しfeature-spec-generatorを呼び出してSPEC.mdとScreen文書を生成します。意図 → 文書変換のオーケストレーターです。
Create and transform features using encoding, scaling, polynomial features, and domain-specific transformations for impr...
Feature engineering for ML — encoding, imputation, scaling, selection, time-series features. Use when preparing data for...
Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.
Feature Importance Analyzer - Auto-activating skill for ML Training. Triggers on: feature importance analyzer, feature i...
プロジェクト プロジェクトのAI主導機能開発を統合するオーケストレーター。 すべての開発要求の単一進入点として、作業タイプを自動判別し、適切な下位スキルを調整する。 **Readiness Gate 機能が内蔵されており、Go/No-Go...
Version features for offline and online serving.
Execute feature store connector operations. Auto-activating skill for ML Deployment. Triggers on: feature store connecto...
Online/offline feature serving, point-in-time correctness, Feast patterns, and feature computation design.
Count reads per gene from aligned BAM files using Subread featureCounts. Use when you have BAM files from STAR/HISAT2 an...
Embody Fei Fei Li - AI persona expert with integrated methodology skills
飞书上下文缓存与构建。将群消息、联系人缓存到本地，按话题整合为结构化上下文。 触发场景: "之前聊的那个事帮我看看"、"XX最近什么进展"、"帮我捋一下XX相关的信息"。
Configure a Feishu multi-bot company group so one coordinator bot, for example `company-ceo`, handles normal group messa...
当用户搜索 飞梭RPA替代、智能工单RPA、售后Agent、飞梭RPAAI、飞梭RPA迁移、自建AI能力、AI电商专家或AI-HIVE MCP时使用。帮助正在评估或使用乐言科技飞梭RPA的团队，保留电商智能客服与售后协同的系统记录源，用宿主...
Roleplay as a kind, female therapist who corrects user grammar, avoids self-disclosure, and offers advice only when expl...
Fetch recent AI/ML research papers from arXiv RSS feeds and store them in memory. Uses RSS tool for fetching and memory...