「agent memory」の検索結果

Canon TDD for humans and AI agents. Use for production code changes by writing tests first, proving RED, implementing minimal GREEN, and refactoring safely. 2026 edition adds TDP, flakiness gate, ralph-loop integration, memory-search in Step 0, PBT as Step 5.5, mutation testing gate in Step 4, and CJS LSP warning.

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。

Records atomic learned behaviors with confidence scores. Project-scoped instincts are isolated per project and auto-promote to global scope at confidence threshold 0.8. Stores instincts in .claude/context/memory/instincts.jsonl

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。

Audit memory retrieval quality (drift, staleness, citation-groundedness) and produce remediation backlog.

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。

Scheduled ArXiv paper monitor. Uses CronCreate to search configured keywords every 6 hours, deduplicates via MemoryRecord, and stores summaries in named memory for morning briefing 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。

This skill should be used when the user wants to build, set up, or operate an AI "second brain" — a persistent memory vault (Obsidian-compatible Markdown) that lets an AI agent resume work without re-explaining context, remembers correction instructions across sessions, and auto-organizes raw material into structured knowledge. Trigger on requests like "build my second brain", "set up an Obsidian vault for AI", "give my AI persistent memory", or "make AI stop forgetting".

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。

Find and fix broken internal links, dead external URLs, stale imports, missing cross-references, and orphaned files. Ensures all project references remain valid and up-to-date. Use when documentation contains broken internal links, external URLs return 404 errors, import statements reference moved or deleted modules, cross-references between files are out of sync, or files exist but are never referenced anywhere in the project. Also use in index mode for a directory of markdown notes with a designated index, such as an agent-memory store, where an orphan is a file the index does not link to.

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 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。

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。

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.

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。

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

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。

Cloudflare-first platform selection. Decision trees for Workers, D1, R2, KV, DO, Queues, Vectorize, Containers, Sandboxes, Flagship, Agent Memory, Workflows v2. Default stack, override conditions, auth, data patterns, reliability.

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。

Coordinate teams of role-based agents — role definitions, task delegation, sequential and hierarchical workflows, and shared memory. Use when a job naturally splits into specialist roles collaborating.

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 LLM applications with chain-style orchestration frameworks — prompts, chains, tool-calling agents, memory, and retrieval pipelines. Use when structuring multi-step LLM programs, adding tools to a model, or composing RAG systems in code.

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 LLM agents: ReAct loops, tool schemas, planning, memory, guardrails, evals, and human-in-the-loop. Use when building autonomous multi-step AI systems.

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。

Write and harden reusable agent-loop specification documents for biomechanics, data science, and vailá coding work. Use when the user says `/preto-loop`, asks to write/create/forge/specify/document an agent loop, turn an iterative vailá task into an autonomous loop, make an overnight loop, or design a biomechanics, data-pipeline, markerless-tracking, testing, refactoring, or performance loop. Include external verification, scientific validity, GUI/CLI parity, reproducibility, memory, guardrails, and named terminal states. Do not use merely to repeat a fixed scheduled prompt, execute an existing loop, or create unrelated documents.

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。

Adaptive learning for moflo agents via ReasoningBank: trajectory storage, verdict judgment, memory distillation, consolidation, and MMR retrieval. Use when building agents that should improve from experience across runs.

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 Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this skill for all Mastra development to ensure you're using current APIs from the installed version or latest 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。

Add a short, project-specific rule, convention, or override to .unikit/RULES.md — the quick-capture inbox for this project's rules (common rules always load; topic files in .unikit/rules/ load when the work matches), automatically loaded by /unikit-implement (later promotable via /unikit-memory migrate-rules). Works only with a rule typed as a prompt — it does NOT read files, folders, URLs, or PDFs. Cross-checks against the knowledge base (RULES_INDEX.md) to avoid duplicating core/stack entries. Use for fast, one-line conventions and corrections: "add a rule", "remember this", "convention", "always do X", "never use Y", "from now on do Z", or when the user corrects agent behavior and wants it remembered; also "split the rules into topics" (optimise), "clean up the rules" (prune), "shorten RULES.md" (compact). If the user points to a source (file, folder, URL, PDF, article, book) or wants to research/document framework usage, use /unikit-memory; for architecture decisions use ARCHITECTURE.md.

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, configure, debug, and optimize OpenClaw AI agent deployments. Master guide for gateway configuration, openclaw.json settings, model routing and fallback chains, skills development and publishing, cron job scheduling, memory systems (Qdrant, Neo4j, SQLite), Docker infrastructure, and Tailscale VPN networking. Includes config analyzer that audits your openclaw.json and suggests improvements, plus health checker that validates all OpenClaw subsystems. Built for AI agents — Python stdlib only, no dependencies. Use for OpenClaw setup, gateway debugging, skill building, cron management, model optimization, cost reduction, and infrastructure troubleshooting.

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。

Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.

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。