7,446 件 ・ 人気順
概要と使いどころ
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.
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。
Diagnoses macOS system-level slowness, heat and fleet-wide timeouts: high load average, leaked per-session child processes (MCP servers, helpers), fork storms, busy loops. Use when the Mac feels slow or hot, fans spin up, or everything times out at once (电脑发烫/卡顿/负载高/全部超时). Not for single-app bugs, network slowness (use tunnel-doctor), launchd watchdog design (use macos-watchdog), or disk-full (use macos-cleaner).
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。
Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before implementation. Use for multiple UI versions, interaction alternatives, progressive-disclosure options, or when styling is fine but hierarchy/workflow/interaction feels off. Not for static visual-style calibration (use design-style-picker) or a settled CSS tweak.
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。
Batch-generate and compare visual design directions so a user can choose the style they actually want. Use when the user says they cannot describe an abstract visual style, asks for many style options, wants to choose from generated UI/design-system images, rejects outputs as too colorful/too dead/too generic, or needs an existing UI/design system evolved without discarding current assets.
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 design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.
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。
Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF. Use whenever the user wants a meme, 梗图, 表情包, or reaction GIF from footage; to cover faces in a video; or asks to 把 logo/头像贴到视频里跟着动. Not for transcript-driven editing, programmatic scene generation, or subtitle work.
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 a specific, non-generic cover letter that connects your evidence to the role. Use when asked to write a cover letter, an application letter, or a note to accompany a resume. Produces a tight 3–4 paragraph letter — a real hook, two evidence paragraphs mapping your proof to the job's needs, and a confident close — tailored to the company, ready to export as a designed PDF.
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 a content style guide / voice & tone guide so everyone writes consistently. Use when asked to write a content style guide, a voice and tone guide, editorial guidelines, or UX-writing standards. Produces a usable guide — voice principles with do/don't examples, tone-by-context, mechanics (grammar, capitalisation, formatting), terminology/word list, and accessibility/inclusivity rules — that a team can actually apply.
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 a consulting proposal that wins the engagement — outcomes over hours. Use when asked to write a consulting proposal, a project proposal, a pitch for a client engagement, or to respond to an RFP. Produces a proposal — the client's problem in their words, your approach & deliverables, outcomes/value, timeline & phases, investment with options, and why-you — framed around results, not a task list. Ready to export as a designed PDF.
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。
Plan a session's context window like the budget it is — what loads up front, what gets linked instead, what stays fetch-on-demand, and how to keep the stable prefix cache-friendly so repeated turns cost cents instead of dollars. Use when asked my agent keeps blowing its context, plan what to load into the session, why is every turn so expensive, or design the context for this workflow. Produces the load/link/fetch allocation, the cache-aware prefix layout, the per-turn cost shape, and the eviction rules for when the window fills anyway.
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 asked 帮我准备大厂技术面试, 八股文怎么背, 模拟一面二面, 系统设计面试题, 项目深挖怎么答, 手撕算法, or run a mock technical interview for a Chinese internet company. Produces a preparation plan for the interview rounds Chinese tech companies run (笔试, 技术一面二面, 交叉面, HR 面), a 八股 question bank by stack with answer points, a system design walkthrough, a project deep-dive script, and a mock round asked one question at a time with follow-ups (追问) and scores.
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。
Prepare for and run a product requirements review (需求评审 / PRD 评审会) the way Chinese internet teams do it: a pre-read the engineers, testers and designers can challenge, the questions each role will ask, the meeting run sheet and a written conclusion (通过 / 有条件通过 / 不通过). Use when asked 帮我准备需求评审, PRD 评审会怎么开, 评审前检查一下我的 PRD, 研发会问什么问题, or prepare my requirements review in Chinese. Produces a readiness check of the PRD, a role-by-role question bank with answer points, a 60-minute run sheet, and the review minutes template with the conclusion and follow-ups.
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。
Design a budget-vs-actuals tracker that stays alive past February — the category grain that matches real statements, the variance view that answers 'are we okay', the update ritual small enough to survive, and the honest handling of irregular expenses. Use when asked build me a budget spreadsheet, track team spend against budget, why do we always blow the budget invisibly, or design a household/project budget tracker. Produces the tracker structure, the variance logic, the irregulars ledger, and the monthly fifteen-minute ritual.
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。
Plan an e-commerce category / collection page that ranks and merchandises well. Use when asked to design a category page, a PLP (product listing page), a collection page, or to improve category SEO and merchandising. Produces a brief — search intent & keywords, intro copy, merchandising/sort logic, filters & facets, internal links, and SEO/technical notes — so the page converts browsers and earns organic traffic.
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 a brand's visual and verbal identity into an applicable guideline kit — tokens, voice rules, and do/don't pairs — then apply it consistently to any artifact. Use when asked to apply brand guidelines to a document/deck/page, to extract a brand kit from existing materials or a website, to keep AI-produced artifacts on-brand, or to write lightweight brand guidelines for a startup. Produces a compact brand kit (visual tokens + voice rules + application examples) and/or an artifact restyled to it. For a creator's personal voice use creator-brand-kit; for building new UI systems use frontend-design.
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 a board pre-read that's sent before the meeting so the meeting is about decisions, not status. Use when asked to prepare a board pre-read, a board update/package, or pre-meeting materials for a board. Produces a board pre-read — a TL;DR, the metrics dashboard vs. plan, what's working / what's not, the decisions and asks for the board, and risks — designed to be read in advance.
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。
Take a board game idea from 'wouldn't it be cool if' to a playtestable prototype — core loop, tension source, components you can make tonight, balance starting-points, and a real playtest protocol with kill criteria. Use when someone says 'I have a board game idea', 'design a game about X', 'my game drags in the midgame', or 'how do I playtest this'. Produces a design one-pager, a print-and-play prototype spec, and a 3-session playtest plan.
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。
Decide which of your recurring rituals to put on autopilot — and which to keep manual. Use when asked what to automate, how to set up recurring AI runs, which reports or briefings could run on a schedule, or to design an automation charter for a team. Produces a ritual inventory with automate/assist/keep-manual calls, guardrails per ritual, and a rollout order.
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。
Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are eroding seat counts, when asked to migrate to usage- or outcome-based pricing, to price an agent/API tier, or to defend revenue as customers automate their own usage. Produces a pricing migration plan: the new value metric, fences, agent-tier design, cannibalisation math, and a phased migration for existing customers. For general pricing and packaging strategy use pricing-strategy.
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。
Design an AI-assisted workflow for a recurring task — which steps to hand to AI, which to keep human, and how they connect — so you get leverage without losing quality or control. Use when asked how do I use AI for [process], automate this with AI, design an AI workflow, or where does AI fit in my process. Produces a map of the task's steps split into AI-does / human-does / human-checks, the right tool/prompt for each AI step, the hand-offs and review points, the failure modes to guard against, and a start-small rollout — turning a manual process into a reliable AI-assisted one that keeps you in control.
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。
Evaluate performance fairly when output is AI-assisted — what still measures the human, what now measures the tooling, and how to run the review conversation. Use when reviewing someone whose work is heavily AI-assisted, when output volume stopped meaning anything, when calibrating a team with uneven AI adoption, or when writing review criteria for the AI era. Produces review guidance: a what-measures-whom analysis, rewritten criteria, calibration rules for mixed-adoption teams, and conversation scripts. For the general review document use performance-review; for redesigning the role itself use role-redesign-for-ai.
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。
Specify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's tools and guardrails, scope what an agent is allowed to do, or write an agent spec/PRD. Produces an agent spec — goal & scope, tools with permissions, the control loop, guardrails & approval gates, memory, escalation/handoff, evaluation, and failure handling.
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。
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.
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 a short, punchy announcement designed to be shared as an image or social card. Use when asked to announce a launch, milestone, feature, hire, funding, or win — something to post on LinkedIn/X/Slack. Produces a tight, visually-structured announcement (headline, one-liner, 2-3 proof points, CTA) that looks great exported as a PNG card from the playground.
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。