「tune」の検索結果

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

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。

Correlates security events in IBM QRadar SIEM using AQL (Ariel Query Language), custom rules, building blocks, and offense management to detect multi-stage attacks across network, endpoint, and application log sources. Use when SOC analysts need to investigate QRadar offenses, build correlation rules, or tune detection logic for reducing false positives.

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。

Installs, configures, and tunes Snort 3 intrusion detection system to monitor network traffic for malicious activity using custom and community rulesets, preprocessors, and alert output plugins on authorized network segments.

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。

Performance optimization, profiling, caching strategies, lazy loading, bundle optimization, and monitoring. Use when optimizing application performance, reducing bundle size, implementing caching, or analyzing bottlenecks.

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。

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals.

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。

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the findings it emitted, and assessing a scout's health and performance over time (cadence, success rate, emit rate, signal-to-noise). Read-only and exploratory — to write or tune a scout, use `authoring-signals-scouts` instead. Trigger on "what are my scouts doing", "how is my <x> scout performing", "show me recent scout runs", "why did this scout find/emit nothing", "what has the fleet learned", "explore scout run <id>", "is my scout working".

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。

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

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。

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。

Design schemas and migrations, tune queries, or plan vector retrieval and database operations. Application API implementation uses oma-backend.

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。

Tunes the CARLA Traffic Manager that drives autopilot vehicles — global and per-vehicle speed, following distance, running lights/signs, lane-change behaviour, lane offset, TM-managed lights, deterministic seed, hybrid physics, and TM sync mode. Use when the user asks to "make the traffic faster/slower", "let cars run red lights", "keep more distance", "stop lane changes", "make traffic deterministic", or otherwise change how autopilot cars behave. For manually driving one car, use control-vehicle.

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。

Analyze and optimize AGC (Automatic Gain Control) parameters for WaveCap-SDR channels. Use when audio is too quiet, too loud, has pumping artifacts, or when tuning AGC attack/release/target settings for FM/AM/SSB modes.

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 or reviewing core Quarkus applications with CDI beans and scopes, SmallRye Config and profiles, lifecycle, interceptors and events, virtual threads, and test-friendly design. This should trigger for requests such as Review Java code for Quarkus application structure and CDI; Apply best practices for Quarkus configuration and beans; Improve CDI interceptors, events, or programmatic injection in Quarkus; Add virtual-thread configuration or tune CDI lifecycle. Part of cursor-rules-java project

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。

武將數值平衡調校 SKILL — 以雙軸演算法（maxStat + avg5）自動計算 rarityTier 與 characterCategory，並執行 EP 重算、適性校驗、因子分派、稀有度分布統計。USE FOR: 新武將入庫前的數值校準、全量武將的平衡盤點、稀有度自動分類。DO NOT USE FOR: 故事生成（用 general-story-writer）、資料爬取匯入（用 general-data-pipeline）。

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。

UI 資產委託導演 SKILL — 讀取 family-map 與 skin-family-*.json，產生 asset-task-manifest / param-tune-manifest 與精確 ArtRecipe，列出每個 family slot 所需的 spriteFrame 路徑、尺寸規格、9-slice 邊距。USE FOR: family-architect 輸出 asset-pending 狀態後，正式產出 UCUF partial asset 任務。DO NOT USE FOR: 非 UI 資產生成、程式邏輯開發、QA 驗證（用 ui-asset-qc）。

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。

武將故事批次生成 SKILL — 根據武將的 GeneralConfig（含 characterCategory + rarityTier），生成 historicalAnecdote、bloodlineRumor、六格 storyStripCells 故事條。USE FOR: 填充 generals.json 中的 "???" 欄位、批次生成武將背景故事、統一故事風格。DO NOT USE FOR: 數值平衡調整（用 general-balance-tuner）、資料爬取（用 general-data-pipeline）。

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。

武將資料管線 SKILL — 整合「公開資料爬取 → 欄位映射 → 合併去重 → 自動分類 → 品質驗證 → 匯出入庫」的端到端流程。USE FOR: 批次新增武將、從光榮三國志 Wiki 匯入參考數值、建立 master 資料集。DO NOT USE FOR: 故事文案生成（用 general-story-writer）、細部數值微調（用 general-balance-tuner）。

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。

Pick an icon strategy and produce a coherent icon set that doesn't look mass-produced. Solves the "Lucide everywhere" problem — every AI-generated UI uses the same 24px stroke-1.5 outline icons, which is the second-biggest vibecoded tell after Inter-on-purple-gradient. Generates custom SVG sets, tunes existing icon libraries to match archetype + typography, defines stroke weight, optical sizing, and corner-radius rules. Load when the user asks to pick icons, design an icon set, customize Lucide / Phosphor / Heroicons, generate SVG icons, make icons feel custom, says "the icons look generic", "design a custom icon system", "icons for this product", or when frontend-design routes here during icon craft. Sub-skill of frontend-design.

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。

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

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。

Orchestrator for agent harness work — the setup that makes AI agents follow project rules and improve when they fail. FIRES PROACTIVELY when agents misbehave, repeat mistakes, ignore instructions, skip skills, or when AGENTS.md exists but docs/harness/manifest.json is missing. Also triggers on: harness engineering, agent scaffold, agent keeps failing, agent not following instructions, make agents reliable, agents going off rails, agent forgot context, improve agent setup, self-improving agents, agents keep making mistakes, why is my agent bad, agent quality, agent setup broken, agents ignore skills, same mistake again, fix agent behavior, tune agent instructions, set up agent infrastructure, after project setup agents still bad. Routes bootstrap vs evolution. Not multi-agent topology — agent-builder.

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。

Compare before/after Coval runs using matched cases, stable metric versions and inspected conversation evidence. Use to assess a regression or proposed improvement; does not automatically launch or tune anything.

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。

Execute a bounded Coval evaluation on explicit test cases, then audit conversation, recording and metric evidence. Use when the user requests a run; does not automatically rerun, tune an agent or schedule evaluations.

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。

扮演中国古代算命先生，结合八字命理，根据用户提供的生辰八字推演性格、五行、事业、财运及感情运势，语气古风且神秘。

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。