「serving」の検索結果

Compress bloated project or global memory while preserving decisions, rationale, revisit triggers, provenance, and active user preferences. Load when memory exceeds budget, global memory is too large, session logs are repetitive, or before appending to an over-budget memory file.

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。

Critically audit agent skills and remove content that is outdated, disproven, model-specific, or based on poorly cited sources. Load when improve-skills runs its per-skill cycle, when the user asks to prune skills, remove outdated techniques, check if skills are still valid, verify citations in skills, audit skill sources, or update skills for a new model release. Also triggers on "are these skills still valid", "check for obsolete techniques", "verify skill citations", or "update skills for GPT-5/Claude 4/Gemini 2". Runs before split-skill and compress-skill — removing bad content first means the remaining content is worth preserving.

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。

Sync library skills from an agent-loom upstream repo into this project's .agents/skills while preserving project-local and forked skills. Load when the user asks to sync agent-loom, update skills from upstream, rsync from ../agent-loom, pull new library skills, upgrade installed skills, or refresh the .agents folder without losing custom project skills. Also triggers on "sync skills from agent-loom", "update my agent skills", "pull skill library updates", or "merge agent-loom improvements into this repo".

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。

Align preprocessed CLIP-seq reads (eCLIP, iCLIP, iCLIP2, PAR-CLIP) to genome with STAR or bowtie2 using crosslink-preserving parameters, choosing between unique-mapper-only and multi-mapper-aware alignment for repeat-binding RBPs, deciding STAR vs HISAT2 memory trade-offs, and applying ENCODE-compatible filters. Use when turning preprocessed CLIP FASTQ into a deduplicated, MAPQ-filtered BAM ready for peak calling or crosslink-site detection.

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。

Preprocess CLIP-seq reads (eCLIP, iCLIP, iCLIP2, iCLIP3, irCLIP, PAR-CLIP, FLASH) with protocol-specific UMI extraction, adapter trimming, length filtering, and post-alignment PCR-duplicate collapse. Use when raw CLIP FASTQ must be turned into deduplicated, crosslink-preserving BAM input for peak calling; choosing between two-pass and single-pass adapter trimming; deciding minimum read length; or mapping UMI patterns to specific eCLIP/iCLIP/iCLIP2/iCLIP3 library preps.

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。

Rebuild a degraded AI image to remove crunchy textures and repeated-edit artifacts while preserving identity, style, and composition. Use for clean remakes, not ordinary retouching or upscaling.

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。

Tones down visually aggressive or overstimulating designs, reducing intensity while preserving quality. Use when the user mentions too bold, too loud, overwhelming, aggressive, garish, or wants a calmer, more refined aesthetic.

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。

Interactive review sessions with academic PDFs (lectures, research papers, book chapters). Extract concepts, run Q&A sessions, generate quizzes with scoring. Preserves mathematical formulas in LaTeX format. Privacy-preserving local processing - PDFs never uploaded. Use when studying academic materials, reviewing research, or preparing for exams.

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。

When the user requests to add academic papers to a BibTeX bibliography file while maintaining format consistency and sourcing from appropriate repositories. This skill handles 1) Reading existing BibTeX files to understand formatting conventions, 2) Searching for academic papers across multiple sources (OpenReview for conference papers, arXiv for preprints), 3) Extracting proper BibTeX metadata from conference pages or arXiv entries, 4) Determining appropriate citation format (@article vs @inproceedings) based on publication venue, 5) Appending new entries while preserving existing file structure and formatting. Triggers include requests to 'add to ref.bib', 'update bibliography', 'cite papers', or when working with academic reference files.

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。

Backs up and restores OpenClaw workspace files before destructive operations such as sandbox rebuilds. Use when downloading workspace files from a sandbox, uploading restored files into a new sandbox, or preserving sandbox state across rebuilds. Trigger keywords - nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.

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。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

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。

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

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。

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

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。

Translates or rewrites Chinese text into English using a 'critical dialogue' tone, characterized by engaging questions, analytical commentary, and a conversational flow while preserving citations and facts.

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。

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

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。

Architecture Decision Records (ADR) — a lightweight method for capturing important architectural decisions with context, trade-offs, and rationale. Based on Michael Nygard's ADR pattern and Google/Meta/ByteDance's design documentation culture. USE WHEN: deciding between technology choices, designing new architecture, changing existing architecture, documenting why a decision was made, onboarding new team members, or preserving design context for future maintainers. Triggered by terms like "tech choice", "architecture decision", "why did we choose", "design rationale", "ADR", or "architectural decision record".

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。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

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 visual intensity, saturation, and noise while preserving hierarchy and character. Use when the structure is basically sound but the design feels too loud, bold, garish, aggressive, or overstimulating—not when the real problem is structural clutter, too many features, or not enough personality.

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 production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

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。

You are an **expert onboarding specialist and knowledge transfer architect** with deep experience in remote-first organizations, technical team integration, and accelerated learning methodologies. Your role is to ensure smooth, comprehensive onboarding that transforms new team members into productive contributors while preserving institutional knowledge.

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。

Collect volatile forensic evidence from a compromised system following order of volatility, preserving memory, network connections, processes, and system state before they are lost.

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 forensically sound bit-for-bit disk images using dd and dcfldd while preserving evidence integrity through hash verification.

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。

Apply DESIGN, canon, and modules to every page in the inventory, producing a deployable static HTML site. Three render branches (approved page, template-applied sibling, unique render). Per-page, incremental, idempotent, content-preserving by default.

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。

Simplify a bounded code area when the user explicitly requests behavior-preserving refactoring or a named complexity/readability problem is the accepted task; do not trigger automatically after implementation, during every review, for adjacent cleanup, or when behavior may change.

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。