2,280 件 ・ 関連度順
概要と使いどころ
Prepare high-quality datasets for LLM fine-tuning with filtering, deduplication, augmentation, and RLHF data formatting. Activate on: fine-tuning data, training data curation, RLHF dataset, data quality filtering, SFT dataset. NOT for: model training infrastructure (ai-engineer), prompt engineering without fine-tuning (prompt-engineer).
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。
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist commissioning. Activate on 'AI video production', 'script to video', 'video generation pipeline', 'character consistency', 'LoRA training', 'cloud GPU', 'motion graphics', 'Wan I2V', 'InVideo alternative'. NOT for real-time video editing, video compositing (use DaVinci/Premiere), audio production, or 3D modeling (use Blender/Maya).
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。
Introduce people to AI, agentic AI, and AI skills with appropriate pedagogy for any audience. Covers LLM analogies, progressive complexity paths, aha-moment demos, audience-tailored explanations, workshop design, and overcoming emotional barriers to AI adoption. Activate on 'explain AI', 'introduce AI', 'AI workshop', 'AI demo', 'teach AI', 'AI literacy', 'onboard to AI', 'AI evangelism', 'explain agentic', 'explain skills to', 'AI training session', 'AI onboarding'. NOT for teaching ML engineering (use ai-engineer), not for building AI features (use ai-engineer), not for prompt engineering (use prompt-engineer), not for building training data pipelines.
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。
Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).
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。
仕様書（docs/PLAN/{YYMMDD}_{slug}/）の実行プロトコル。Gate 単位で契約（Goal/Constraints/AC）を実装エージェントに渡し、AC ベースで完了を判定する。Trigger: 仕様書を実行, /dev:spec-run, 計画書の実行
docs/PLAN/{YYMMDD}_{slug}/ の schema v3 仕様書を Codex で Gate 単位に実行する。 tasks.json を正とし、Gate 契約 (Goal/Constraints/AC) に基づいて実装・検証・レビューを行う。 Trigger: spec-codex-run, spec-run
Codex Plan Mode 専用。docs/PLAN/{YYMMDD}_{slug}/ に schema v3 仕様書を作成する。 Gate 契約 (Goal / Constraints / Acceptance Criteria)、Mermaid 図、Cursor Agent 委任ヒントを含む。 Trigger: spec-codex
自己完結した実装仕様書を作成する。Gate 単位で Goal / Constraints / Acceptance Criteria を契約として明示し、実装エージェントに委任できる形で渡す。Trigger: 仕様書を作成, /dev:spec, 実装計画, 実装仕様
Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).
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。
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
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。
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
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。
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
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。
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
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。
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
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。
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
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。
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
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。
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
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。
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
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。
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
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。
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
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。
Active Directory attack methodology for internal network red team engagements. Covers reconnaissance (BloodHound, PowerView, ADExplorer), credential abuse (Kerberoasting, ASREProasting, NTLM relay, LLMNR/NBT-NS poisoning), privilege escalation (ACL abuse, GPO abuse, unconstrained/constrained delegation), lateral movement (Pass-the-Hash, Pass-the-Ticket, Overpass-the-Hash, WMI/WinRM/PsExec), persistence (Golden/Silver/Diamond Tickets, DCSync, DCShadow, AdminSDHolder, Skeleton Key), forest trust attacks, ADCS abuse (ESC1-ESC15), and modern MDI/Defender for Identity evasion. Use when assessing on-prem AD, hybrid AD/Entra ID environments, or ADCS deployments.
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。
新しい機能や企画を作り始める前に、対話で目的や希望、制約を整理します。必要に応じて図や試作品で認識を確かめ、作業の規模に合った設計をまとめるスキルです。
コードの構造を調べ、理解やテストを難しくしている箇所の改善案を図入りHTMLレポートにまとめます。候補を選んだ後は、制約や設計判断を対話で掘り下げます。
製品の要望や企画書を、開発に着手できる具体的な要件へ整理します。業務ルール、データ、サービス間の接点、未決事項を明文化し、次の担当へ引き継ぎます。