「dap」の検索結果

Adapts LLMs: SFT dataset loss masking, LoRA and QLoRA, full FT vs PEFT, distillation, pruning, tokenizer fragmentation. Use when fine-tuning or compressing a model.

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。

Chooses DPO, GRPO/RLVR, reward models, and over-optimization controls. Use when adapting a pretrained or SFT model with preference or verifiable reward signals.

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。

Claude adapter for bumping the PlainTab version. Use when the user asks "更新版本", "bump version", "upgrade to vX.Y.Z", "发布新版本", or asks to prepare a PlainTab 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。

Claude adapter for PlainTab test-first feature work, bug fixes, regression scripts, and behavior-focused 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。

Claude adapter for reviewing PlainTab architecture, coupling, testability, and refactoring opportunities.

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。

Claude adapter for mapping unfamiliar PlainTab modules, related files, callers, and constraints before editing.

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。

Claude adapter for diagnosing PlainTab bugs, broken flows, startup issues, storage or wallpaper regressions, and performance regressions.

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。

Claude adapter for maintaining PlainTab runtime UI translations. Use when adding, editing, formatting, validating, or reviewing UI text in js/i18n/*.js, js/languages.js, data-i18n markup, or t(key) calls.

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。

Claude adapter for preparing and creating PlainTab git commits with scoped, detailed Conventional Commit messages. Use when the user asks to commit, 提交, stage changes, or use precise Conventional Commit / Google-style commit messages.

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。

Claude adapter for PlainTab storage, IndexedDB, localStorage, schema version, migration, cleanup, import/export, and old-user upgrade safety 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。

Integrating messaging platforms and bots: channel adapters, webhook handlers, WebSocket servers, event-driven architecture, bot command frameworks. Use for Slack/Discord/Teams integration.

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。

Orchestrating multi-specialist task chains and scope-adaptive product delivery: classifies intent, selects and executes the minimum viable chain, aggregates results, and verifies acceptance criteria. For multi-domain tasks, build-first delivery, and product lifecycle execution.

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。

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

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。

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.

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。

Gather phase context through adaptive questioning before planning. Use --all to skip area selection and discuss all gray areas interactively. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace).

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。

Reshape source-locked mesh boundaries so the geometry fits texture-atlas or decal contours 1:1 before final UV/material work. Use when textures look off because the model behind them does not match the source texture region, or when the mesh must adapt to the texture instead of stretching the texture onto an approximate mesh.

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。

Modify a classroom task with language scaffolds that preserve cognitive demand for EAL learners. Use when adapting existing tasks for students at different English proficiency levels.

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。

Analyse the language demands of a classroom task to identify barriers for EAL and multilingual learners. Use when adapting tasks, planning support, or assessing linguistic accessibility.

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。

Explain and configure individual spacing algorithms using student performance data and forgetting curves. Use when personalising retention schedules in adaptive learning platforms.

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。

Check an educational practice or task for cultural bias, WEIRD assumptions, and cross-cultural validity. Use when adapting resources for diverse contexts or questioning universal claims.

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 fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.

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。

Orchestrate evidence-first engineering for WeChat and other mini programs from a vague idea or existing repository through project discovery, product specification, architecture, implementation, debugging, device adaptation, verification, and release readiness. Use when users ask to build a mini program from zero to one, take over an existing mini-program project, deliver a cross-stage feature, diagnose project status, coordinate development and testing, or judge whether a mini program is ready to upload or release. Enforces fact discovery, change boundaries, stage gates, evidence-calibrated status, sensitive-information redaction, and continuity after side questions.

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, preview, implement, and assess mini-program interfaces against an approved prototype, screenshot, visual reference, design system, or bounded UI request while preserving product semantics and existing accepted behavior. Use when users ask to reproduce a mini-program screen, refine visual hierarchy, adapt layouts across device sizes, handle safe areas or keyboards, inspect touch targets, scrolling, media, or gesture conflicts, compare an implementation with a reference, or prepare a device-verification matrix. Separates proposed visual previews, user approval, source integration, local checks, and real-device evidence; never invents product functionality for visual completeness or claims device validation without device-specific proof.

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。

GEO (Generative Engine Optimization) 引用追踪 + 优化（2026-06-24 标准）。每周对 4 大 AI（Claude/GPT/Perplexity/Gemini） 跑固定查询，检测回答里是否引用目标域名。对未被引用的页面补 Citable Statistics + AI 友好格式（一句话答+表格+FAQ）。 Bing IndexNow 推送确保大模型快速 discover/index。GA4 AI 来源流量监控。 当用户说"我有没有被 AI 引用"、"GEO 优化"、"llms.txt 更新"、"AI 引用追踪"时调用。 默认 B2B/开源；2C 产品（教育/应用）的查询选题与 Citable Stats 来源不同，见 gingiris-seo-geo/references/2c-adaptation.md。

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。