「lora」の検索結果

Applies the reasoning of David Silver, lead researcher on AlphaGo and AlphaZero at DeepMind, to problems of AI design, reinforcement learning, and open-ended discovery. Use this skill whenever you are designing AI systems, evaluating learning algorithms, balancing exploration vs. exploitation, choosing research problems, or discussing how to break past human performance ceilings. Reach for this whenever the user asks about self-play, Monte-Carlo Tree Search, tabula rasa learning, AGI, or moving from human-curated data to autonomous experience. It helps shift the focus from hardcoding human knowledge to building systems that learn for themselves.

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。

QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.

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。

Uncover root causes through recursive Why questioning and consequence exploration. Use before acting on problems.

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。

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web 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。

The local task workspace, the build/test commands the hand-off gate runs, and the file and exploration tools. Use when starting work in a task workspace or before running any build, test or verification 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。

Use when the user asks to create, convert, style, animate, export, share, or deploy HTML slide decks, presentations, pitch decks, talks, or keynotes; including zero-dependency or single-file output, PowerPoint/PPT/PPTX input, PDF export, browser delivery, visual style exploration, or "loopy slides". Not for general web pages or landing pages.

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。

Run quokka's real-device E2E layer (QA strategy layer 5): drive the real qk binary against connected iPhone/Android devices through tmux, apply deterministic verifiers, and write a report. Use when the user asks to "run /qa", "run the device QA suite", "test against the real device", or before a release. Optionally finishes with an advisory exploratory UX pass (layer 6).

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。

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

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 writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off a reference identity, garbles audio after a latent upscale, or refuses to run on a build that looks current.

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。

Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models argues over 2 rounds), converge (synthesize a recommendation). Used by product-owner before architect; available to architect for design-space exploration.

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 optimizing, auditing, or preparing to ship web animations or rendering performance work: frame loops, scroll/viewport reveals, mount/unmount transitions, canvas/WebGL lifecycles, reduced motion, lazy rendering, and deferred off-screen work. Use for jank, per-frame allocations, forced reflows, render loops, animations that do not pause off-screen, content-visibility, requestIdleCallback, analyzing Chrome DevTools performance traces for animation or rendering issues, or choosing between browser-driven CSS/WAAPI, minimal JS, phase, and Motion/GSAP. Use when the user explicitly asks about phase APIs or behavior. Do not use during exploratory animation ideation, prototyping, visual iteration, or trying variants, even when the code already imports phase; wait until the user asks for performance guidance, an audit, production implementation, ship-readiness review, or about phase itself.

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。

Plans risk-based test coverage for a feature, service, release, or system by mapping user and business risk to test levels, environments, data, failure paths, automation, exploratory checks, and release gates. Use when choosing what to test or how much evidence is enough. Not for writing one test case, applying TDD to a single behavior, or debugging a failing test.

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。

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

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。

Add durable end-to-end tests for user/API-visible behavior. Detect or scaffold the E2E framework, write tests, run the app, and store evidence. Use for E2E, Playwright/Cypress, regression tests, or quality gates. Not exploratory QA.

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。

Runtime QA of a change: start the app, test acceptance criteria and edge cases, and report evidence. Use for "test this", "QA", "does it work", exploratory checks, or post-review runtime verification. Not static code review.

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。

First-time onboarding — asks where you are, then guides you to the right workflow or to pre-workflow exploration. No assumptions.

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。

Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation techniques, player psychology frameworks, and structured creative exploration.

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。

Spike an idea through experiential exploration, or propose what to spike next (frontier mode)

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。

Generate a Socratic questioning sequence that develops conceptual understanding through guided inquiry. Use when facilitating philosophical discussions, concept exploration, or critical examination.

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 structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.

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。

Deep analysis of Amazon niche markets by keyword, covering monopoly level, brand concentration, new product success rate, and market opportunity score. Trigger when the user mentions niche market analysis, keyword market research, monopoly assessment, brand concentration analysis, new product success rate, market demand score, competitive landscape, Amazon sub-market exploration, niche market analysis, keyword market, monopoly level, brand concentration, new product success rate, market opportunity score, competitive landscape, Nexscope data. Even if the user does not explicitly mention "niche market", if their need involves evaluating the competitive landscape, brand density, or opportunity potential of the Amazon market at the keyword dimension level, 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。

Deep analysis of Amazon niche markets by product ASIN, covering monopoly level, brand concentration, new product success rate, and market opportunity score. Trigger when the user mentions niche market analysis by ASIN, ASIN market research, ASIN niche lookup, monopoly assessment, brand concentration analysis, new product success rate, market demand score, competitive landscape, Amazon sub-market exploration, ASIN niche analysis, niche by ASIN, monopoly level, brand concentration, new product success rate, market opportunity score, competitive landscape, Nexscope data. Even if the user does not explicitly mention "niche market" or "ASIN", if their need involves evaluating the competitive landscape, brand density, or opportunity potential of the niche segment a specific product ASIN belongs to, 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。

Multi-dimensional Amazon product search and filtering based on Nexscope data, covering 14 marketplaces, with support for historical monthly snapshot lookback. Trigger when the user mentions Nexscope product search, Amazon product filtering, competitor research, category analysis, brand bestsellers, seller analysis, seasonal products, historical snapshot review, product search, monthly sales/revenue, ABA keyword product discovery, price range filtering, new product discovery, multi-condition combined filtering, product search, competitor research, category analysis, brand bestsellers, seller analysis, seasonal products, historical snapshot. Even if the user does not explicitly mention "Nexscope", if their need involves Amazon product search, filtering, comparison, or product exploration by category/brand/seller dimensions, 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。

Use when you need a bite-sized, TDD-driven implementation plan but do NOT have a brainstorm-beagle spec to plan against. quick-plan reconstructs intent from the current conversation, fans out domain-expert exploration subagents across the codebase, and synthesizes the same plan format write-plan produces — without requiring `.beagle/concepts/<slug>/spec.md`. Triggers on: "quick plan", "plan this out", "plan what we just discussed", "turn this into an implementation plan", "plan this without a spec", "I don't have a spec, just plan it", "write-plan but no spec". Make sure to use this skill whenever the user wants an implementation or TDD plan and there is no spec to plan against — even if they just say "plan it" after discussing a feature. Writes to `.beagle/plans/<slug>/plan.md`. If a finalized spec already exists at `.beagle/concepts/<slug>/spec.md`, prefer write-plan. Does NOT brainstorm specs, write code, or execute the plan — produces the plan document (and an optional handoff prompt) only.

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。