444 件 ・ 関連度順
概要と使いどころ
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers 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。
Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on the Autonomys Network. Rebuild your full history from a single CID, even after total state loss.
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。
Maxim e-commerce direct-response video — engineered for PURCHASE. The primary sales style. Uses AIDA + JTBD + Loss Aversion + Scarcity + Anchoring stacked for maximum conversion. Every second is behavioral leverage.
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。
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (GLOSSARY.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
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。
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers 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。
Stress-test a plan against existing domain language, code behavior, and durable decisions. Use when the user wants DDD/domain-model grilling, glossary refinement, terminology challenges, context documentation, ADR candidates, or plan validation against a repo's language.
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。
Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses. Use PROACTIVELY for risk assessment, trade tracking, or portfolio protection.
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。
Detects insider data exfiltration by analyzing DLP policy violations, file access patterns, upload volume anomalies, and off-hours activity in endpoint and cloud logs. Uses pandas for behavioral analytics and statistical baselines. Use when investigating insider threats or building user behavior analytics for data loss prevention.
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。
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
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。
Complete competitive intelligence system — market mapping, product teardowns, pricing intel, win/loss analysis, battlecards, and strategic monitoring. Goes far beyond SEO to cover the full business landscape.
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。
Handle images with ImageMagick (magick) — read metadata, resize, crop, rotate, convert format, combine images (side-by-side or grids with montage), overlay logos/watermarks, and losslessly compress with oxipng before sending. Use when the user sends an image to process, when you produce an image to deliver, or before attaching any image to a message or upload — compressing first keeps transfers fast and tokens low. Core discipline - always compress before delivering, never expose local file paths to the user, and fail open (if a tool is missing or a step errors, pass the original through unchanged; never block the task).
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。
Monthly strategic review playbook. Chains pipeline-review + campaign-analyzer + win-loss-analyzer + gtm-analyzer. Outputs executive summary with KPIs, channel ROI, competitive shifts, and strategic recommendations.
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。