2,447 件 ・ 関連度順
概要と使いどころ
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
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 a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.
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。
Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.
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 phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.
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。
Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.
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。
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
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。
Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on the Autonomys Network. Rebuild your full history from a single CID, even after total state loss.
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。
Systematic performance profiling and optimization methodology. Covers CPU profiling, memory profiling, heap analysis, goroutine/thread analysis, FlameGraph generation, latency profiling, database query profiling, network I/O profiling, and continuous performance regression detection. USE WHEN: investigating performance issues, optimizing slow code, reducing memory usage, diagnosing GC/CPU bottlenecks, finding N+1 queries, analyzing pprof/flamegraph output, or establishing a performance baseline. Triggers on "profiling", "performance analysis", "slow code", "flame graph", "pprof", "heap dump", "memory leak", "CPU spike", "bottleneck".
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。
Systematic debugging methodology covering root cause analysis, log-based debugging, production debugging, memory leak diagnosis, deadlock detection, performance anomaly investigation, and reproducible bug reproduction. Distilled from real experience at Google, DeepMind, ByteDance, and Huawei. USE WHEN: investigating production incidents, debugging hard-to-reproduce bugs, analyzing crash dumps, finding race conditions, diagnosing memory leaks, debugging performance regressions, or any situation requiring systematic root cause analysis. Triggers on "debugging", "root cause", "bug", "crash", "segfault", "deadlock", "race condition", "memory leak".
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 memory — store, recall and query project knowledge across sessions. Detects whatever persistent memory is available (MemPalace, claude-mem, or file-only fallback) and uses the best one present.
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。
Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` where scope is `global` (default), `user`, `workspace`, or `ws`.
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 transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
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。
Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.
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 GC and memory. GC modes, LOH/POH, Gen0/1/2, Span/Memory deep patterns, ArrayPool.
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。
Detects and analyzes fileless malware that operates entirely in memory using PowerShell, WMI, .NET reflection, registry-resident payloads, and living-off-the-land binaries (LOLBins) without writing traditional executable files to disk. Activates for requests involving fileless threat detection, in-memory malware investigation, LOLBin abuse analysis, or WMI persistence examination.
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。
Detects and analyzes process injection techniques used by malware including classic DLL injection, process hollowing, APC injection, thread hijacking, and reflective loading. Uses memory forensics, API monitoring, and behavioral analysis to identify injection artifacts. Activates for requests involving process injection detection, code injection analysis, hollowed process investigation, or in-memory threat 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。
Detects fileless malware and in-memory attacks that execute entirely in RAM without writing persistent files to disk, evading traditional antivirus. Use when building detections for PowerShell-based attacks, reflective DLL injection, WMI persistence, and registry-resident malware. Activates for requests involving fileless malware detection, in-memory attacks, PowerShell exploitation, or living-off-the-land techniques.
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 and systems design for agents that retain bounded state across sessions. Covers durable event history, owned state, derived memory, retrieval indexes, framework evaluation, recovery, deletion, and rebuild behavior. Uses constructed implementation examples and workload calibration rather than universal vendor, latency, similarity, retention, or cost claims. Activate on: "always-on agent", "persistent agent architecture", "episodic memory system", "agent memory design", "long-running agent", "stateful agent", "agent that remembers", "MemGPT architecture", "Letta deployment", "/always-on-agent-architecture". NOT for: choosing what data to feed the agent (use always-on-agent-inputs), brainstorming applications (use always-on-agent-applications), safety and privacy concerns (use always-on-agent-safety), general agentic patterns (use agentic-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。
Swiftのactorで共有データへのアクセスを管理し、メモリ内キャッシュとJSONファイル保存を組み合わせて、同時アクセス時のデータ競合を避ける保存処理を設計するスキル。
PyTorchのモデルや学習コードを作成・点検し、データ読み込み、実験の再現性、学習状態の保存、GPUメモリや処理速度の改善を支援するスキル。
Pythonコードの作成・レビューで、PEP 8や型ヒント、例外処理、パッケージ構成を整え、読みやすさと保守性、メモリ効率を考えた改善を支援するスキル。
投資家向けの説明資料や財務モデル、資金使途表、応募書類を作成・更新し、事業実績や収益の前提、調達額、チーム情報の食い違いを複数の資料で確認するスキル。
C++のテスト作成・修正から、GoogleTestとCTestの設定、失敗原因の調査まで支援します。実行結果が不安定なテストの改善やカバレッジ測定にも対応します。
AIエージェントの不調を、指示・記憶・ツール実行・画面表示など12の層から調べるスキル。コードやログを根拠に原因を整理し、重要度順の指摘と修正案をまとめます。