「memory」の検索結果

Store embeddings beside application data in Postgres, create vector indexes, and query nearest neighbors for semantic search, RAG, recommendations, or agent memory retrieval.

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 SimpleMem to store, compress, index, and retrieve text or multimodal memories for agents through MCP or Python integrations.

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 Yao when an operator needs to package an AI agent workflow, hooks, MCP tools, memory scopes, and a reviewable web or chat interface into one deployable runtime.

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。

Endpoint defense evasion after an operator-selected chain already has a valid execution path but AV/EDR/AMSI/WDAC/PPL/memory/kernel telemetry blocks the intended action. Originating modules include /web-attack /ad-attack /cloud-attack /k8s /cicd /service-attack /phishing /privesc-win /privesc-linux /creds /post /shell. Success is the blocked action becoming executable, then resume the originating module — not obtaining a shell here.

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。

Systems-level performance engineer: identifies hotspots, provides optimized code with resource justifications.

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。

First-run setup for the Mycelium plugin. Creates project-state directories (.claude/canvas, .claude/diamonds, .claude/memory, .claude/harness) and minimal starter files in the user's project. Optionally provisions opencode runtime support (a starter scaffold) when opencode is detected or requested. Idempotent — re-running on an initialized project is a no-op. Run this once after installing the Mycelium plugin and before invoking other skills.

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。

Measure Mycelium's own scaffold token cost (CLAUDE.md + engine + harness + canvas + memory) and surface a structured estimate. One-shot audit; pair with /framework-health for trend tracking.

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。

Maps a startup's competitive landscape, scores moat strength across 6+ dimensions, and writes an investor-ready competition narrative with a positioning map. Use when the user asks for a competitive landscape, moat analysis, or positioning review and gives enough to work from: a deck, a list of competitors, or a clearly named startup. A full run takes about 30–40 minutes and searches the web, so for a passing question such as 'who are my competitors?' or 'is that a real moat?', answer briefly in chat and offer the analysis instead of starting it. When it runs, the competitor set and moat scores are checked adversarially, never recalled from memory.

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。

Scores and strengthens startup pitch decks (pre-seed through Series A) against 35 investor-grade criteria grounded in Sequoia, DocSend, YC, a16z, and Carta data. Use when the user has shared a pitch deck (PDF, PPTX, markdown, pasted slide text, or a link to one) and asks for a review, score, feedback, or critique. A full review takes about 15–25 minutes, 40 or more for a long investor deck, so for a general pitch question with no deck, answer briefly in chat and offer the review instead of starting it. When it runs, score with the rubric, never with deck advice from memory.

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。

Builds credible TAM/SAM/SOM analysis with external validation and sensitivity testing for startup fundraising: top-down, bottom-up, or both. Use when the user asks to size a market or check market claims and gives something to size: a product or service description, a market segment, or a deck with TAM/SAM/SOM claims. A full run takes about 15–20 minutes and searches the web, 30 or more with a large data room or a revision round, so for a passing question about market size, answer briefly in chat and offer the analysis instead of starting it. When it runs, every figure is externally sourced and stress-tested, never estimated from memory.

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 for past-session context recovery. Triggers: recall, last time, previous session, chat search, memory search, 그때, 지난번, 저번 세션, 예전에 했던, 기억나?, 리콜, 지난 세션, 이전 작업, 뭐였지, 어떻게 했었지.

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 writing, reviewing, or optimizing CUDA kernels targeting sm_120a (RTX 5090 / Consumer Blackwell, GB202) in the imp inference engine. Triggers on CUDA/PTX kernel code, shared-memory layout, bank conflicts, tensor-core MMA (mxf4nvf4, tf32, 3xTF32/3xFP16), GEMV/GEMM/attention/quantization/GDN-scan kernels, decode tok/s under expected, kernel emitting HMMA instead of mxf4nvf4, occupancy, register pressure, __launch_bounds__, spills, PDL. Pair with `benchmark-cuda` for measurement and `check-degeneration` after hot-path changes.

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。

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。

Verifies repository baseline test passing state and available memory/GPU resources to ensure safe mission execution.

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。

Research-backed skill refresh workflow for updating existing skills with TDD checkpoints, memory-aware integration, and EVOLVE/reflection trigger handling.

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 you need to auto-log all tool interactions into a self-organizing vector DB with instant recall. Intercepts interactions, extracts key information, generates embeddings, stores in LanceDB, auto-categorizes, and builds a retrieval index. Inspired by OpenClaw SQLite LCM + summary DAG pattern.

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。

Specific optimization strategies for Python scripts working with larger-than-memory datasets via Dask.

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 and registers hooks for the Claude Code framework. Handles pre/post tool execution, validation, memory, and session hooks. Use when new validation, safety, or automation hooks are needed.

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 Exa web search monitor. Uses CronCreate to search configured topics every 4 hours via mcp__Exa__web_search_exa, deduplicates URLs via MemoryRecord, and stores summaries 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。

Sync OpenClaw + ClawHub + Skills docs into a local mirror for the QMD memory 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。

Stealth headless browser with CDP server for anti-fingerprint browsing, parallel scraping, and low-memory CDP automation. This skill should be used when stealth browsing, anti-detection scraping, headless CDP automation with fingerprint protection, or tracker-free page fetching is needed. Triggers on 'stealth browse', 'anti-fingerprint', 'obscura', 'stealth CDP', 'undetectable scraping', 'headless stealth', 'tracker-free browsing'.

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。

Slack workspace integration: 9 on-demand scripts (post, read, delete, search, stream, react, upload, channels, users) + dual-token support + RTS API search + chat streaming + AI Block Kit + Session Bridge + Claudicle unified launcher (Claude Agent SDK, soul engine, three-tier memory).

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 enables cross-model dialogue between Claude and Gemini with shared visual memory. Use when the user wants to generate images, have visual dialogues with AI, create scientific illustrations with continuity, or have multiple AI perspectives respond to the same prompt. Key trigger phrases: "generate an image", "visual dialogue", "ask the daimones", "resonance field", "Minoan tarot", "cross-model", "KV cache", "MESSAGE TO NEXT FRAME".

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。

Reflective Memory

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。