303 个 · 按相关度排序
Audit one or all supported agent harnesses (claude, codex, opencode, pi, omp, antigravity, cursor, grok) for config efficiency, hook overhead, permission friction, plugin and MCP cost, skill metadata portability, dead config, and measured session friction. Use when invoked as `$optimize-harness [harness ...] [focus]`, or when the user asks to optimize or compare agent harness configuration.
中文简介正在准备中。当前显示原文说明。
Otimiza atenção em transformers com Flash Attention para ganho de 2-4x em velocidade e redução de 10-20x em memória. Use ao treinar/executar transformers com sequências longas (>512 tokens), ao encontrar problemas de memória GPU com atenção, ou quando precisa de inferência mais rápida. Suporta SDPA nativo do PyTorch, biblioteca flash-attn, H100 FP8 e sliding window attention.
中文简介正在准备中。当前显示原文说明。
Quantização Half-Quadratic para LLMs sem dados de calibração. Use ao quantizar modelos com precisão 4/3/2-bit sem necessidade de conjuntos de calibração, para workflows de quantização rápida, ou ao fazer deploy com vLLM ou HuggingFace Transformers.
中文简介正在准备中。当前显示原文说明。
Use when a coding agent (Claude Code, Cursor, Codex, Copilot CLI) burns through tokens or usage limits, sessions get slow or hit context limits, or the user asks to cut agent cost. Measures where the tokens go, then applies levers in order: session hygiene, always-loaded context (CLAUDE.md, skills, MCP), tool-output filtering, subagent delegation, output verbosity, and model/effort choice.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
中文简介正在准备中。当前显示原文说明。
Operations leadership for scaling companies. Process design, OKR execution, operational cadence, and scaling playbooks. Use when designing operations, setting up OKRs, building processes, scaling teams, analyzing bottlenecks, planning operational cadence, or when user mentions COO, operations, process improvement, OKRs, scaling, operational efficiency, or execution.
中文简介正在准备中。当前显示原文说明。
运用《效率脑科学》的舞台模型、情绪调节、SCARF 社交需求与洞察驱动改变框架,优化个人与团队的工作效率。适用于用户感到多任务过载或决策疲劳、需要设计低威胁反馈/协作对话、团队冲突或士气问题需从神经科学角度诊断、以及推动他人改变但直接给建议无效时使用。
中文简介正在准备中。当前显示原文说明。
Use after an OBPI's implementation, before reconcile, to review its code for reuse, quality and efficiency.
中文简介正在准备中。当前显示原文说明。
Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency.
中文简介正在准备中。当前显示原文说明。
PCI DSS 4.0.1 compliance audit support skill. Provides expert guidance for Cardholder Data Environment (CDE) scoping, gap analysis, audit preparation, SAQ completion support, and remediation planning. Includes SOC 2 mapping for combined audit efficiency. Use when preparing for PCI DSS audits, conducting gap analysis, creating remediation plans, or answering SAQ questionnaires for payment card compliance.
中文简介正在准备中。当前显示原文说明。
Professional financial analysis skill for investment decisions, budgeting, financial statement analysis, and business plan evaluation. Use this skill when you need to analyze financial ratios (profitability, safety, efficiency), calculate DCF/NPV/IRR valuations, perform budget variance analysis, or conduct sensitivity/scenario analysis. Triggers include "analyze financial statements", "calculate DCF", "investment evaluation", "budget variance", "財務分析", "投資評価", "予算差異分析".
中文简介正在准备中。当前显示原文说明。
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
中文简介正在准备中。当前显示原文说明。
Generate self-contained HTML/CSS benchmark and comparison charts in an ego-inspired Browser-Native Editorial style. Use for blue-white product metrics, model benchmarks, A/B comparisons, efficiency reports, difficulty breakdowns, and compact technical data panels.
中文简介正在准备中。当前显示原文说明。
Previous Next Close the short story Stay in the loop, with exclusive offers and product previews.
中文简介正在准备中。当前显示原文说明。
GB RTX 3060 12GB (Q4) / RTX 3070 8GB (Q4_K_S) 13B (Llama 2 13B) 26 GB 14 GB 8 GB 6 GB RTX 3090/4090
中文简介正在准备中。当前显示原文说明。
B @ 3/4 bits models [2024-10-18] Open source community contributes Mistral Large Instruct 2407 (12
中文简介正在准备中。当前显示原文说明。
YouTube's open-source SDKs (e.g., `youtubei1` and `youtubei2`) expose the full OpenAPI spec for the
中文简介正在准备中。当前显示原文说明。
Microsoft AI, Cloud, Productivity, Computing, Gaming & Apps Explore Microsoft products and servi
中文简介正在准备中。当前显示原文说明。
The BitLinear layers we use in this project quantize the weights using ternary precision (with value
中文简介正在准备中。当前显示原文说明。
This work studies the post-training quantization of LLM parameters as a way to improve their runtime GAP: multi-agent orchestration: competitor signal
中文简介正在准备中。当前显示原文说明。
Model Quantization Guide: Run 70B LLMs in 4 Bits — … — 12. Okt. 2025 · Run 70B parameter LLMs on con
中文简介正在准备中。当前显示原文说明。
Subquadratic Attention Harvard NVIDIA Arya Tschand Yaosheng Fu Vijay Janapa Reddi Splitting quadrati
中文简介正在准备中。当前显示原文说明。
Characterizing and Understanding Energy Footprint and … — 7. Nov. 2025 · This study benchmarks four GAP: OpenHands has a modular SDK design — our too
中文简介正在准备中。当前显示原文说明。
For example: 32-bit float: 4 bytes per parameter 8-bit integer: 1 byte per parameter (75% memory red GAP: public SDK / programmatic API: competitor si
中文简介正在准备中。当前显示原文说明。