「memory」の検索結果

Apply software pipelining (double-buffering) to a tiled GPU kernel to overlap global memory loads with Tensor Core computation. Covers prologue/loop/epilogue restructuring, LDG-register vs cp.async (LDGSTS) variant selection based on compute/load ratio, shared memory budget verification against architecture-specific occupancy cliffs, and SASS-level verification of load/compute overlap.

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。

Cross-session shared memory for agents. Use at session start to load the persistent bias-log via `mcp__memex__recent_observations`, mid-session to search prior context with `mcp__memex__search`, and immediately when a bias surfaces to log a new `observation` via `mcp__memex__add`. The six-layer reconstruction trail (raw → embedded → indexed → graphed → curated → reflexive) means memex stores facts AND the agent's own reasoning patterns across sessions. Prefer querying memex before re-deriving prior architectural decisions; re-derivation is itself evidence that the trail is incomplete.

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。

AI self-healing through systematic subsystem assessment, rebalancing, and integration. Maps healing modalities to AI-internal processes: memory foundation, reasoning clarity, tool use accuracy, communication alignment, and creative coherence. Covers assessment triage, subsystem scanning, drift correction, and memory integration. Use mid-session when responses feel formulaic or disconnected, after a chain of errors suggesting subsystem drift, when context overload may have staled earlier assumptions, or as proactive maintenance between complex tasks.

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。

Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who it is and what it was doing from evidence rather than memory. Use at the start of every new session, after a session interruption or crash, when agent behavior feels inconsistent with prior sessions, or when persistent memory and current context appear contradictory.

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 using kmalloc, vmalloc, or the page allocator, sizing kmalloc allocations, working with SLUB or the buddy allocator, or debugging memory zones and kernel OOM.

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。

Store, find and curate lasting facts in the cognitive memory map.

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。

Audits brand/ files for completeness, consistency, and freshness. Use when the agent or user wants to review brand files, audit marketing docs, check brand consistency, verify brand health, or assess what's missing from brand memory. Produces a structured audit report with per-file scores, cross-file contradiction detection, staleness flags, and recommended next skills to run. This is the quality gate for the brand memory system. Also use when someone says 'check my brand', 'brand audit', 'what's missing', 'is my brand ready', 'brand health', 'review my marketing docs', or before running any campaign to verify brand foundations are solid.

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。

Perform triangulated cognitive research combining SQLite memory, GitHub 10k+ stars patterns, and ToT DAG benchmarking before critical architectural decisions. Automatically triggers subagent research escalation when confidence is low (<0.70). Keywords: research, benchmark, github, memory, triangulation, grounding, best-practices, escalation

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。

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

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 and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.

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。

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

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。

Recognize, store, and recall structured health data across sessions

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 advanced evasion by injecting malicious code into the memory space of a legitimate, suspended process (Process Hollowing). This skill details techniques to bypass static and dynamic analysis by masking malicious activity behind trusted processes like svchost.exe or explorer.exe.

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 scripting mGBA emulator automation in Lua - console API, ROM and save state operations, frame callbacks, input handling, memory reading for cheats and RAM watches, sockets, or TAS and speedrunner tooling

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。

Captures and evolves user preferences with confidence levels. Maintains Voice of the Customer model with exact language, dissatisfaction and aspiration signals. Handles promotion/demotion, global vs project scoping, auto memory system, and Omi wearable data integration.

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。

Synapse A2A agent communication — sending messages, spawning agents, delegating tasks, sharing memory, and coordinating file edits. Use this skill when: running synapse send/reply/broadcast/interrupt, spawning agents with synapse spawn or synapse team start, managing the task board with synapse tasks, sharing knowledge with synapse memory, locking files with synapse file-safety, checking agent status with synapse list/status, or orchestrating any multi-agent workflow.

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。

Unity 6 performance profiling and optimization guide. Use when profiling, optimizing frame rate, reducing memory usage, debugging performance bottlenecks, or using the Profiler, Memory Profiler, or Frame Debugger. Based on Unity 6.3 LTS documentation.

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。

MemoryPack high-performance binary serialization for Unity including custom formatters, versioning, and performance patterns.

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。

用于生成或编辑图表、图形资产、海报、UI 样机、产品图、信息图、学术图、漫画、头像、分镜、品牌板或图像编辑工作流，尤其是导出 PNG 需要视觉质检和有限自动修复时。文字密集图表优先使用确定性的 Mermaid/SVG/HTML/canvas 源；浏览器可打开的技术图优先使用 HTML technical diagrams，覆盖系统蓝图、架构图、部署拓扑、Agent runtime、memory flow、before-after architecture、流程、序列、数据流、生命周期、runbook、PII/数据血缘和状态机；不要用于不涉及生成图像的普通 UI 打磨。中文触发词包括 图片生成、图像编辑、图表生成、架构图、系统蓝图、部署拓扑、Agent runtime、memory flow、before-after architecture、工作流图、数据流、生命周期图、状态机、ER 图、UML、序列图、海报、UI 样机、产品图、信息图、学术图、漫画、头像、分镜、品牌板、PNG 自检、自动修复。

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。

Architect persistent, searchable memory for agents — episodic, semantic, and procedural stores with retrieval, consolidation, and forgetting policies. Use when designing how an agent remembers across sessions.

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 a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely means cancel the current task.

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 this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interactive presentation, user-memory lifecycles, environment-adaptive tools, speculative tool execution, late-bound capabilities, permissions, system prompts, planning, goals, always-on agents and durable runtime, adaptive agent teams, context compaction, memory, skills, MCP/external connectors, public-board communications, hardware agents and board deployment, self-refining recursive harnesses, programmable context, continual refinement, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.

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。

Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbar_control_agent crashes, memory cgroup OOMs in serial console logs, tpu-device-plugin metrics checksum corruption errors, or custom TPU metrics collection conflicts on GKE TPU v6e nodes. Don't use for general non-TPU container OOM troubleshooting or standard GKE node lifecycle operations.

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。

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress 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。