2,308 件 ・ 関連度順
概要と使いどころ
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast 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。
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
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。
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
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。
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
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。
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
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 building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR, JWT authentication, AOT compilation.
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。
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
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。
Takes a structured list of changes from changelog-scan and produces a clean, categorized, user-facing release notes draft. Follows project voice and conventions. Never publishes — only proposes a draft file or section.
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。
Scan recent merges to main for tech debt, TODOs, debug code, and small cleanup opportunities. Produces a prioritized fix list.
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。
Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.
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。
Turn raw notes or a transcript into a clean summary with decisions and action items.
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。
Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.
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。
Archive accumulated phase directories from completed milestones
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 clean PR branch by filtering out .planning/ commits — ready for 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。
End-of-semester case handoff memos — the mirror of /ramp. Produces per-case transition memos and a cohort summary so the departing cohort hands work to the incoming cohort cleanly. Reads deadlines, client-comms, and case history. Use when the professor or departing students need to wrap up the semester, build transition memos, or offboard a graduating/withdrawing student.
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。
Resolve unresolved PR review comments across an entire Graphite (gt) stack of many PRs, bottom-up, in one working directory. Use when asked to "go through this stack and resolve comments", "clean up review comments across the whole stack", or given a list/range of PR numbers that form (or partially form) a gt stack. Distinct from the single-PR resolve-pr-comments skill, which this one uses as its per-branch inner loop.
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。
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of /tmp helper scripts.
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。
Unified guide for authoring dashboard panel components in vanilla TypeScript — covers the authoritative Panel base class (grid-span persistence, dual resize handles, radar loading animation, exponential-backoff error countdown, data/new badge helpers, full destroy() cleanup), localStorage state via loadMap/saveMap, exponential-backoff retry, and CircuitBreaker integration. Shows how to wrap any existing fetchX() service call with CircuitBreaker.execute() as a one-liner and clarifies when each resilience layer is appropriate.
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。
Build cross-game mashups and total conversions, the "Minecraft inside Elden Ring" or "skateboarding in MW2" kind. Covers passthrough mods (two games running at once and exchanging state, rendering and collision), porting one game's content or mechanics into another, embedding a decompiled game as a library, and clean reimplementations that read the user's own game files. Use when the user wants to combine two games, bring an enemy, mechanic or world from one game into another, or rebuild a game's runtime, or reimplement the guest's rules headless inside a real host.
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。
Launch, see and drive a real game so an agent can test its own mods. Covers launching via Steam or the exe, windowed mode at a fixed size, screenshots of the game window (GPU-safe capture), clicking and typing into menus, holding keys, relative mouse, crash-reporter cleanup, killing by PID, reading logs, scripted test scenes, and an in-game JSON bridge that lets an agent observe and act. Windows-first (also from WSL), with notes for Linux and macOS. Use when a mod must be verified in game, when navigating menus automatically, or when building a repeatable test or demo scene.
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。
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。
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。
Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. Use when the user asks to create, write, rewrite, improve, compress, clean up, or prepare a goal prompt, goal condition, /goal command, goal-mode objective, or copy-ready long-running task objective.
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。
Scans TON (The Open Network) smart contracts for 3 critical vulnerabilities including integer-as-boolean misuse, fake Jetton contracts, and forward TON without gas checks. Use when auditing FunC contracts.
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。