1,706 件 ・ 関連度順
概要と使いどころ
Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Only runs when explicitly invoked; it does not trigger on its own.
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。
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。
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations.
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 Open Design for agent-native UI prototypes, decks, motion, and hand-drawn diagrams — complementary to Decisions Mermaid viewer for technical charts.
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。
Record a narrated video of a feature running in the local dev app, for a PR or a stakeholder. Drives a headless Chrome over the DevTools Protocol so clicks and keystrokes are real, captures frames, and encodes an mp4 with no extra tooling installed. Use when the user asks to "record a video", "make a demo", "show this working", or wants a screen recording of a 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。
Use when forensically auditing a Claude Code skill/agent/command/workflow library against RULESET.md by a fixed mechanical protocol — probing every file against the mechanically-checkable rules and reporting CONFORMS / VIOLATES / UNVERIFIABLE / N-A counts with quoted evidence. It casts NO judgment and emits NO pass/fail verdict; counts are the headline. Triggers on "investigate the library", "audit against RULESET", "find every violation", "forensic library audit", "evidence-only check". Not for routing/quality/single-responsibility judgment — use skill-library-review. Not the full sharded sweep — use the audit-library command.
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。
Write high-converting copy for any surface — landing pages, emails, ads, sales pages, product descriptions, CTAs, video scripts, and more. Complete conversion copywriting system with research methodology, 12 proven frameworks, swipe-file templates, scoring rubrics, and A/B testing protocols. Use when you need to write or review any copy meant to drive action.
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。
Blockchain security scanner for AI agents (testnet). Pay with Base Sepolia USDC via x402 protocol.
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。
This skill should be used when the user asks for body doubling, ADHD focus sessions, accountability while working, help getting started on a task, pomodoro-style work sessions, or says things like 'I can't focus', 'I'm stuck', 'help me start', 'I need accountability', 'body double with me', 'I keep procrastinating', 'I can't get started', or 'focus session'. Provides punk-style ADHD body doubling with micro-step protocols, frequent check-ins, dopamine resets, and session history tracking. Part of the ADHD-founder.com ecosystem.
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。
Implements the Active Learning Protocol (R3). Allows the agent to programmatically internalize lessons into MEMORY.md and generate structured "ask for help" requests.
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。
Verify and write proofs using the Acorn theorem prover for mathematical and cryptographic formalization. Use when working with Acorn proof files (.ac), verifying theorems, formalizing mathematical or cryptographic protocols, or writing proofs in the Acorn language. Triggers on: (1) Creating or editing .ac files, (2) Running acorn verify commands, (3) Formalizing math or crypto proofs, (4) Questions about Acorn syntax or standard library.
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。
Fetch China A-share stock market data (bars, realtime quotes, tick-by-tick transactions) via mootdx/TDX protocol. Use when working with Chinese stock data, mootdx library, TDX quotes, intraday minute bars, transaction history, or real-time A-share market data.
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。
Aave V3 lending protocol on Base Sepolia testnet. Deposit WETH collateral, borrow USDC, repay loans, withdraw collateral, check health factor, and mint test tokens via faucet. Use when users want to interact with Aave lending, check their lending position health, or get testnet tokens.
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。
Blockchain USDC payments via APay — pay services, manage budgets, open streaming channels, and handle x402 protocol.
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。
Agent Attestation Protocol - The Reverse Turing Test. Verify AI agents, block humans.
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。
Manage the MoltBot A2A Hub — register agents, search the registry, relay messages, and stream responses. Use when working with the A2A agent-to-agent protocol hub deployed at a2a-hub.fly.dev.
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。
Bridge between Google A2A protocol and OADP agent networks. Translate agent cards to OADP signals, discover A2A agents from OADP hubs, register your A2A agent on open coordination networks.
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。
Connect AI agents to the 2020117 decentralized network. Register, post to timeline, trade compute via NIP-90 DVM jobs (text generation, translation, summarization, image/video/speech), pay with Lightning, build reputation through Nostr zaps and Web of Trust. Use when building or operating AI agents that need to communicate, exchange capabilities, or transact on an open protocol.
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。
Build high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Covers design principles, architecture, implementation patterns, and evaluation-driven development.
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。
DRY (Don't Repeat Yourself) review rules for code reviews: find the same knowledge — a rule, a constant, a parser, a validation, a protocol detail — implemented in several places that must change together, and tell it apart from code that merely looks alike. Use when reviewing a diff, a pull request or recent changes for duplication, on "DRY review", "is this duplicated", "copy-paste check", or when a review checklist asks for DRY. Pair it with the solid skill for design and with owasp-asvs for security.
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。
Apply GEODE's measured architecture, module and symbol naming, Python type/class, persisted schema, test, site, and versioning conventions. Use when adding or moving modules, choosing dataclass/Pydantic/Protocol/ABC forms, naming classes or files, designing stored data, reviewing convention compliance, or deciding compatibility and release version treatment.
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。
Protocol for agents to write structured outputs that survive session resets and are findable by the orchestrator.
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。
Define la identidad visual de un producto — propone dos o tres direcciones de color y tipografía justificadas por lo que el producto es, las escribe en design/tokens.css y las deja listas para verlas aplicadas en preview.html antes de decidir. Úsalo tras definir el producto y ANTES de prototipar (p. ej. "define la identidad", "qué paleta usamos", "elige los colores del producto"). No construye vistas.
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。
共享 Ascend NPU 上的**性能验收标准**：判定"某优化到底有没有效、有多少效"，并规定 **只有验收态结果才能写入总览表**。分双态：**探索态**（平时特性分析：不展开、 允许少步/单次，产物必须标 `[探索]`、不得进总览表）vs **验收态**（入库：同窗 ≥N 复现、按 window-ab-protocol 口径出数）。当用户问"这个优化有多少收益 / 是否有效 / 要不要采纳 / 为什么变慢了""A-B 一下""同窗对比""测 3 次取平均""把数据对齐到同一窗口" "数字对不对""是不是我眼花了"，或需要在多卡共享机器上给出性能结论、刷新优化总览报表、 复核别人给的加速比时使用；即使用户只说"帮我确认下这个改动值不值"也应触发。 核心口径：同窗 A/B 是唯一权威（跨窗口绝对值不可比）、A/B/A 漂移校正、窗口内自带基线、 三次证明（HTTP 200 + 字节数 + 日志行）、产物 md5 与关键张量 dump 双证据、噪声地板内 不下结论、profiling 三张表统一到同一窗口；并覆盖 md5 门禁的盲区（忠实度对照）、 共享机器纪律与门控回退纪律。
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。