7,665 件 ・ 関連度順
概要と使いどころ
End-to-end system for creating supervised fine-tuning datasets from books and training style-transfer models. Covers text extraction, intelligent segmentation, synthetic instruction generation, Tinker-compatible output, LoRA training, and 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。
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
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。
Refine an existing implementation plan with a second iteration. Re-analyzes the codebase for gaps, missing tasks, and wrong dependencies. Use after /aif-plan or to improve an /aif-fix plan. Optional +check flag validates refinements via a fresh-context subagent.
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。
Self-improve AI Factory skills based on project context, accumulated patches, and codebase patterns. Analyzes what went wrong, what works, and enhances skills to prevent future issues. Use when you want to make AI smarter for your project.
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。
Refine an existing implementation plan with a second iteration. Re-analyzes the codebase for gaps, missing tasks, and wrong dependencies. Use after $aif-plan or to improve an $aif-fix plan. Optional +check flag validates refinements via a fresh-context subagent.
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。
Perform code review on staged changes or a pull request. Checks for bugs, security issues, performance problems, and best practices. Use when user says "review code", "check my code", "review PR", or "is this code okay". Optional +check flag validates findings via a fresh-context subagent.
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。
Facilitate design discussion — research context, clarify requirements, draft RFC/ADR
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 running Plans.md tasks on a scheduled cadence (fresh context per wake-up, sprint-contract flow, plateau detection, flock guard). Do NOT load for: single-task work (harness-work), planning, review, release.
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。
Troubleshoot and resolve common issues with the ClickHouse Node.js client (@clickhouse/client). Use this skill whenever a user reports errors, unexpected behavior, or configuration questions involving the Node.js client specifically - including socket hang-up errors, Keep-Alive problems, stream handling issues, data type mismatches, read-only user restrictions, proxy/TLS setup problems, or long-running query timeouts. Trigger even when the user hasn't precisely named the issue; vague symptoms like "my inserts keep failing" or "connection drops randomly" in a Node.js context are strong signals to use this skill. Do NOT use for browser/Web client issues.
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 the transcript of a YouTube video as text or JSON.
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。
Extract text from a PDF or a scanned document, with or without OCR.
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。
Render text or an image as ASCII art for terminal-friendly output.
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。
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
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。
Detect and fix AI-generated writing patterns (slop). Comprehensive detection with 50+ patterns across 3 severity tiers, structure weighted above lexical tells, scoring system, and editor mode that directly fixes problems. Use when scanning any content for AI tells, auditing drafts before publishing, checking if writing "sounds like AI", humanizing AI-generated text, or verifying content authenticity. Trigger on "check for slop", "does this sound like AI", "humanize this", "AI audit", "slop check", "clean up AI writing", or any request to detect/remove artificial-sounding patterns. Also use proactively before publishing any AI-assisted content.
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。
Secure environment variable management with Varlock. Use when handling secrets, API keys, credentials, or any sensitive configuration. Ensures secrets are never exposed in terminals, logs, traces, or Claude's context. Trigger phrases include "environment variables", "secrets", ".env", "API key", "credentials", "sensitive", "Varlock".
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 only for user-provided academic text, explicit scholarly claims, existing citations, or known bibliographies needing citations added, verified, replaced, extracted, or formatted. Supports claim-to-source matching, citation-support checks, replacements, and common academic citation formats. Do not use for general fact-checking, legal/journalistic citation work, open-ended 'find literature about X', topic-level exhaustive discovery, systematic-review corpus construction, PRISMA searches, or creating new research claims. Chinese: 为已有段落补参考文献、核验已有引用、替换错误引用、提取需引文论断、GB/T 7714 格式化.
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。
Launch a guided durable update for the active gc-branch.
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。
为 msModelSlim 创建基础 Transformers 模型适配器（Model Adapter）。 包含创建适配器、实现必需接口与注册安装流程。 适用：Decoder-only LLM、理解类 VLM（仅 LLM/text 部分）。 多模态生成（DiT/扩散，含双/多专家）见下方「多模态生成扩展」节，按需加载。 不适用：Encoder-only、非 Transformers 架构。
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。
Ascend cluster comparison tool. Invoke when user asks to compare two cluster datasets (DB or TEXT), or to generate cluster_analysis_output from raw profiling data via msprof-analyze and then compare.
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 native UI with the @expo/ui package: real SwiftUI on iOS and Jetpack Compose on Android rendered from React in an Expo or React Native app. Covers universal cross-platform components (Host, Column, Row, Button, Text, List, and more imported from @expo/ui), drop-in replacements for popular React Native community libraries (BottomSheet, DateTimePicker, Slider, Menu, etc.), and platform-specific SwiftUI (@expo/ui/swift-ui, iOS only) and Jetpack Compose (@expo/ui/jetpack-compose, Android only) trees and modifiers. Use when adding or reviewing @expo/ui Host/RNHostView trees, building native-feeling UI where standard React Native components fall short (grouped settings forms with toggles, sections, menus, sheets, pickers, sliders), choosing between universal and platform-specific components, or replacing an RN community UI library with a native @expo/ui equivalent. Not for custom native modules, Expo Router navigation, Reanimated, or data fetching.
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。
Research companies, competitors, funding, news, leadership, and market context with Exa Agent and advanced search. Use when researching companies, competitor analysis, market research, or building company lists. Writes findings the caller can fold into brand/competitors.md or brand/landscape.md. Prefer this over ad-hoc web search for company deep dives. Distinct from competitive-intel (full brand competitive file methodology) - this skill is the Exa research engine those foundation skills should call.
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。
Call Exa Search (POST /search) for semantic web retrieval with ranked results, filters, freshness, highlights/text, structured output, or streaming. Use when the agent needs open-ended web search, competitor discovery, news, people, or research papers and does not already have URLs. Prefer Exa MCP web_search_exa / web_search_advanced_exa when available; otherwise raw HTTP with EXA_API_KEY. NOT for known-URL extraction (use exa-contents or firecrawl) or multi-step list-building (use company-research / lead-generation / Agent API).
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。
Call Exa Contents (POST /contents) for LLM-ready extraction from known URLs: text, highlights, summaries, links, image links, subpages, freshness-controlled crawl. Use when the agent already has URLs. Prefer Exa MCP web_fetch_exa when available; otherwise raw HTTP with EXA_API_KEY. NOT for open-ended discovery (use exa-search) or auth-walled X/Twitter (use mktg-x). For full-site crawl of a known domain, firecrawl may be better.
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 to generate an image or video via Higgsfield AI. Covers 30+ models: Soul V2, Seedance 2.0, Kling 3.0, Veo 3.1, GPT Image 2, Nano Banana 2. Also covers Marketing Studio — branded ad video/image with avatars and products. Use whenever: "generate an image", "make a video", "animate this photo", "image-to-video", "img2vid", "edit this image with AI", "produce a clip", "create an ad", "make a UGC video", "marketing video", "brand video", "TV spot", "import product from URL", "create avatar for ad", "Seedance", "Kling", "Veo", "Soul gen", "Nano Banana", "Marketing Studio". Chain with higgsfield-soul-id when user wants a reusable face identity. Owns AI-generated "marketing video" / "brand video" / ad creative. NOT for: training a Soul Character (use higgsfield-soul-id), product photoshoots with mode-specific enhancer (use higgsfield-product-photoshoot), text/TTS, screen-recorded product demos (use marketing-demo), slides-to-MP4 assembly (use video-content), Remotion code (use remotion-best-practices). Requires Higgsfield CLI installed and authed.
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。