1,309 件 ・ 関連度順
概要と使いどころ
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
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。
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
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。
Translate one, multiple, or all explicitly requested FastGPT i18next namespace JSON files from the completed Simplified Chinese source into every supported target locale, with product-language research and structural validation. Use only when the user explicitly invokes `$i18n-translate` and identifies namespace names, files under `packages/web/i18n/zh-CN/`, or all namespaces; never trigger implicitly for ordinary i18n, copywriting, or documentation 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。
将 FastGPT 文档从中文翻译为面向北美用户的英文。当用户提到翻译文档、i18n、国际化、translate docs、新增/修改了中文文档需要同步英文版时，使用此 skill。也适用于用户要求检查文档翻译缺失、批量翻译、或对比中英文文档差异的场景。
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。
FastGPT CI workflow 双轨同步。当用户修改或新增 .github/workflows/ 下的 GitHub Actions workflow 时必须触发：同步更新 .forgejo/workflows/ 对应文件保持功能一致，或判断是否需要新建 Forgejo 版本。涉及 CI、GitHub Actions、Forgejo Actions、镜像构建、container registry、artifact、workflow yaml 改动、build-* workflow、test-* workflow 时也使用此技能。即使用户只提到"改一下 CI"或"加个 workflow"也应触发。
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。
为 FastGPT 新增、修改或审查自动系统升级脚本及其注册信息。涉及系统迁移、升级任务、启动迁移、migration registry、checkpoint、全量重跑、阻塞升级、进度或失败数据时使用；普通业务更新和未接入自动升级框架的一次性手工清洗不使用。
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。
当用户需要弃用一个工作流节点（保留向后兼容、隐藏出模板面板）时触发该 skill。FastGPT 工作流节点的弃用流程标准化封装，覆盖模板、Dispatcher、UI 引用等所有需要改动的位置。
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。
为 FastGPT 新资源接入权限管理。当用户需要为新资源（如 AgentSkill、Plugin 等）添加权限支持时触发。
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。
FastGPT API 开发规范。重点强调使用 zod schema 定义入参和出参,在 API 文档中声明路由信息,编写对应的 OpenAPI 文档,以及在 API 路由中使用 schema.parse 进行验证。
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。
手动触发的 FastGPT PR 或本地分支变更梳理技能。仅当用户显式调用 $pr-change-analysis 时使用；用于 reviewer 分析一个 GitHub PR 或当前本地分支相对 upstream/main 的需求变更、影响范围、代码质量与代码风格，不用于自动审查触发。
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 nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.
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。
Fullstack development toolkit with project scaffolding for Next.js, FastAPI, MERN, and Django stacks, code quality analysis with security and complexity scoring, and stack selection guidance. Use when the user asks to "scaffold a new project", "create a Next.js app", "set up FastAPI with React", "analyze code quality", "audit my codebase", "what stack should I use", "generate project boilerplate", or mentions fullstack development, project setup, or tech stack comparison.
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。
Show the architecture of a public GitHub repository with GitDiagram (gitdiagram.com) - a written explanation, its main components and source paths, how they connect, and a Mermaid diagram. Use when the user wants to understand, map, visualize or get an overview of a GitHub repository or open-source project's architecture, structure or data flow, or asks for an architecture diagram of a repo, e.g. "/gitdiagram fastapi/fastapi" or "how is vercel/next.js structured?".
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。
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
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。
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
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。
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
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。
Sets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-clang-fast or afl-gcc-fast. Covers instrumentation modes, parallel main and secondary campaigns, persistent mode, corpus minimization, and crash triage. Use when scaling fuzzing across cores, fuzzing a mature C/C++ codebase, reading the afl-fuzz status screen, or moving on after libFuzzer has plateaued.
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。
Writes, reviews, and debugs property-based tests — Hypothesis, fast-check, proptest, jqwik, rapid, and Echidna or Medusa for Solidity invariants. Use whenever tests should cover a whole input domain instead of a hand-picked list of examples: encode/decode and serialize/deserialize pairs, parsers, canonicalizers and normalizers, validators, numeric and Decimal types, comparators and sort order, data structures, and smart-contract state invariants. Also use when adding cases to an existing @given, fast-check, or proptest suite, when judging whether existing property tests assert anything real, and when a generator has shrunk a counterexample and you need to tell a wrong property from a genuine bug. Not for coverage-guided binary fuzzing (libFuzzer, AFL), mutation-testing campaigns, static analysis, benchmarking, or end-to-end UI tests.
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。
Validate Illumina BCL run folders and sample sheets, plan demultiplexing, review index/UMI/lane choices, run BCL-to-FASTQ conversion, and interpret demux metrics while surfacing license/download boundaries.
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。
Submit compact UniProt REST API requests for UniProtKB, UniRef, UniParc, and FASTA stream endpoints. Use when a user wants concise UniProt summaries; save raw JSON or FASTA only on request.
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。
Submit compact RCSB PDB requests for core metadata, Search API queries, and FASTA downloads. Use when a user wants concise RCSB summaries; save raw JSON or FASTA only on request.
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。
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release: masked-LM logits, hidden states, mutation scoring, contact prediction, and the SAE interpretability head. MIT-licensed weights on HuggingFace org `biohub`. Use this skill when: (1) Predicting complex structures with single-sequence input, (2) Validating designed binders with ESMFold2-Fast, (3) Running ESMFold2 with MSA input, (4) Getting ESMC embeddings or per-residue mutation scores, (5) Choosing kernel backend and sampling-step settings for paper-faithful throughput.
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 codebase search via WarpGrep (20x faster than grep)
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。