3,015 件 ・ 関連度順
概要と使いどころ
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
日本語の概要は準備中です。原文の説明を表示しています。
Nexscope Ozon product detail query: fetches the complete detail of a single Ozon product by SKU, returning title, price (RUB), rating, review count, QA count, total and daily average sales within the stats window, revenue, stock, category ranking, daily sales trend, brand, seller, fulfillment method (FBO/FBS/OZON), weight, and listing time/days/months. Use for single product deep analysis, competitor product teardown, Ozon product selection assessment, listing diagnosis, sales trend and category ranking tracking. Trigger when the user mentions Ozon product detail, Ozon single product analysis, Ozon SKU query, competitor product data, Ozon sales trend, Ozon category ranking, Ozon stock, Ozon listing time, Nexscope Ozon product search, Ozon product detail, Ozon SKU lookup, single product analysis, competitor product teardown, Ozon sales trend, category rank. Also trigger when the intent is to view detailed data of an Ozon product, even without explicitly mentioning Nexscope.
日本語の概要は準備中です。原文の説明を表示しています。
Nexscope Ozon category product search: fetches the product list for a given Ozon category ID, returning category-level aggregates (total sales, total revenue, average price, average rating, seasonality) and per-product sales, price, rating, review count, brand, seller, and fulfillment method. Use for category selection analysis, category bestseller mining, category capacity and price band analysis, seasonality assessment. Trigger when the user mentions Ozon category products, Ozon category analysis, Ozon category selection, Ozon category bestsellers, Ozon category total sales, Ozon category average price, Ozon category search, Ozon category products, category best-sellers, category analysis. Also trigger when the intent is to view products and category-level summary data within an Ozon category, even without explicitly mentioning Nexscope.
日本語の概要は準備中です。原文の説明を表示しています。
Nexscope Ozon shop product search: fetches the product list of an Ozon shop (seller) by shop ID, returning each product's 30-day sales, price, rating, weight, fulfillment method (FBO/FBS), seller type (local/cross-border), return/cancellation rate, and the shop's total 30-day sales. Use for competitor shop product analysis, shop bestseller mining, seller product structure analysis. Trigger when the user mentions Ozon shop products, Ozon seller product list, competitor shop analysis, Ozon shop bestsellers, Ozon seller analysis, Nexscope Ozon shop search, Ozon shop search, Ozon seller products, competitor shop analysis, Ozon store products. Also trigger when the intent is to view an Ozon shop/seller's products and sales data, even without explicitly mentioning Nexscope.
日本語の概要は準備中です。原文の説明を表示しています。
Advanced Amazon product search and filtering powered by Nexscope data, supporting multi-dimensional criteria including category, price, monthly sales, keywords, BSR rank, review count, rating, package dimensions, weight, fulfillment type, and more. Trigger when users mention Nexscope product selection, Amazon product search, advanced product selection, BSR filtering, sales rank filtering, keyword-based product discovery, category search, competitor screening, niche product discovery, historical rank filtering, or similar terms. Even if the user does not explicitly mention "Nexscope," trigger this skill whenever the request involves multi-criteria Amazon product search, sales-metric-based filtering, or advanced product selection beyond simple keyword search.
日本語の概要は準備中です。原文の説明を表示しています。
Use Nexscope data to search and filter Amazon products, supporting multi-dimensional criteria including price, monthly sales, BSR ranking, gross margin, ratings, fulfillment method, badges, seller origin, and more across multiple Amazon marketplaces. Trigger when the user mentions Amazon product selection research, product filtering, sales filtering, product discovery, BSR analysis, niche product discovery, competitor analysis, market opportunity assessment, product-level market size estimation, gross margin screening, Nexscope product selection, Amazon product selection, sales filtering, BSR analysis, profit screening, market analysis, product selection tool. Even if the user does not explicitly mention "Nexscope", if their need involves filtering and analyzing Amazon product-level data for product selection, this skill should also be triggered.
日本語の概要は準備中です。原文の説明を表示しています。
Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.
日本語の概要は準備中です。原文の説明を表示しています。
Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.
日本語の概要は準備中です。原文の説明を表示しています。
Designing and auditing repository structure for humans and LLM agents: layouts, monorepos, docs/tests/scripts, progressive disclosure, prompt-cache topology, and safe migrations.
日本語の概要は準備中です。原文の説明を表示しています。
Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.
日本語の概要は準備中です。原文の説明を表示しています。
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team
日本語の概要は準備中です。原文の説明を表示しています。
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
日本語の概要は準備中です。原文の説明を表示しています。
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
日本語の概要は準備中です。原文の説明を表示しています。
LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".
日本語の概要は準備中です。原文の説明を表示しています。
每日 SEO/GEO 巡逻（2026-06-24 标准）。覆盖：SERP 关键词排名追踪（DataForSEO / volume 300-1000 / KD 5-35）、 Google 索引数统计、llms.txt 可达性、GA4 tag 部署检测及 AI 来源 channel 配置、 PH canonical 合并修复、社媒关键词雪崩救援（title 含 best/free/top/guide+年份、内链注入 ≤2-3/段、 主动 cite 竞品外链）。当用户说"跑 SEO 日报"、"检查排名"、"某关键词掉了"、"修 canonical"、"加内链"时调用。
日本語の概要は準備中です。原文の説明を表示しています。
GEO (Generative Engine Optimization) 引用追踪 + 优化（2026-06-24 标准）。每周对 4 大 AI（Claude/GPT/Perplexity/Gemini） 跑固定查询，检测回答里是否引用目标域名。对未被引用的页面补 Citable Statistics + AI 友好格式（一句话答+表格+FAQ）。 Bing IndexNow 推送确保大模型快速 discover/index。GA4 AI 来源流量监控。 当用户说"我有没有被 AI 引用"、"GEO 优化"、"llms.txt 更新"、"AI 引用追踪"时调用。 默认 B2B/开源；2C 产品（教育/应用）的查询选题与 Citable Stats 来源不同，见 gingiris-seo-geo/references/2c-adaptation.md。
日本語の概要は準備中です。原文の説明を表示しています。
표준 거래내역에 계정과목을 매핑하는 스킬. 룰 기반 분류 우선(80%+), 실패 건만 LLM fallback(마스킹 뷰), 사용자 확인 루프. 한국 거래처 100개 시드 룰 포함, 내부 계정 ↔ 국세청 표준계정 이중 구조.
日本語の概要は準備中です。原文の説明を表示しています。
Core technical documentation writing principles for voice, tone, structure, and LLM-friendly patterns. Use when writing or reviewing any documentation.
日本語の概要は準備中です。原文の説明を表示しています。
Use when comparing two or more code implementations against a spec or requirements doc. Triggers on "which repo is better", "compare these implementations", "evaluate both solutions", "rank these codebases", or "judge which approach wins". Also covers choosing between competing PRs or vendor submissions solving the same problem. Does NOT review a single codebase for quality — use code review skills instead. Does NOT evaluate strategy docs — use strategy-review. Requires a spec file and 2+ repo paths.
日本語の概要は準備中です。原文の説明を表示しています。
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: "research X for me", "do web research on", "look up sources for", "find citations for", "gather evidence on", "what does the web say about X". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), local file search, LLM-as-judge evaluation, or paywalled/auth-gated scraping. Produces a written plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.
日本語の概要は準備中です。原文の説明を表示しています。
Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.
日本語の概要は準備中です。原文の説明を表示しています。
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
日本語の概要は準備中です。原文の説明を表示しています。
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
日本語の概要は準備中です。原文の説明を表示しています。