990 个 · 按相关度排序
Sync high-value dev knowledge (skills, decisions, lessons) into Google NotebookLM for cloud recall, podcasts, and flashcards. Pairs with Dockit/deep-search. Use for NotebookLM, nlm, knowledge base, skill sync, or cross-machine AI memory.
中文简介正在准备中。当前显示原文说明。
Optional power-up — detects oversized codebases/docs and suggests tobi/qmd for local semantic search. Bridges cm-continuity (working memory) with long-term document retrieval. Zero-config detection, non-intrusive suggestion.
中文简介正在准备中。当前显示原文说明。
Working memory protocol — maintains context across sessions via CONTINUITY.md. Inspired by Loki Mode. Read at turn start, update at turn end. Captures mistakes and learnings to prevent repeating errors.
中文简介正在准备中。当前显示原文说明。
Log a bias-log / vipassana observation to the memex store the moment a reasoning pattern surfaces, mid-session or at close. Use when you catch a bias in your own reasoning (anchoring, confirmation, trust-the-summary), when a pace tell or verification gap appears, or when meditate/observe produces a reflection worth persisting across sessions. Primary path pipes the body to `memex add` over stdin (`--title` required) then runs the `meditate-vipassana` extractor to make it queryable; secondary path appends a numbered bullet to `docs/OBSERVATIONS.md`.
中文简介正在准备中。当前显示原文说明。
Build and analyze discrete or continuous Markov chains including transition matrix construction, state classification, stationary distribution computation, and mean first passage times. Use when modeling a memoryless system with observed transition counts or rates, computing long-run steady-state probabilities, determining expected hitting times or absorption probabilities, classifying states as transient or recurrent, or building a foundation for hidden Markov models or reinforcement learning MDPs.
中文简介正在准备中。当前显示原文说明。
Forecast infrastructure and application metrics using Prophet or statsmodels for capacity planning, cost optimization, and proactive scaling. Visualize predictions in Grafana and set up alerts for projected resource exhaustion. Use when forecasting infrastructure capacity needs for CPU, memory, or disk, planning hardware procurement for next quarter, predicting cost trends to optimize cloud spending, or setting up proactive scaling policies based on predicted load.
中文简介正在准备中。当前显示原文说明。
AI internal coordination using stigmergic signals — managing information freshness in context and memory, decay rates for assumption staleness, and emergent coherent behavior from simple local protocols. Use during complex tasks where multiple sub-tasks must coordinate, when context has grown long and information freshness is uncertain, after context compression when information may have been lost, or when sub-task outputs need to feed into each other cleanly without degradation.
中文简介正在准备中。当前显示原文说明。
Extract maximum value from existing code — performance optimization, API surface refinement, and dead weight elimination. The art of turning base code into gold through systematic identification and amplification of value-bearing patterns. Use when optimizing a working but sluggish codebase, refining an API surface that has accumulated cruft, reducing bundle size or memory footprint, or preparing code for open-source release — when code works correctly but doesn't shine and needs polish rather than a full rewrite.
中文简介正在准备中。当前显示原文说明。
Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy calculations, compute/load ratio per tile, and SASS instruction inspection. Produces a decision matrix for optimization strategy selection (cp.async, warp interleaving, tiling, double-buffering, or CuAssembler hand-tuning).
中文简介正在准备中。当前显示原文说明。
Verifies repository baseline test passing state and available memory/GPU resources to ensure safe mission execution.
中文简介正在准备中。当前显示原文说明。
Research-backed skill refresh workflow for updating existing skills with TDD checkpoints, memory-aware integration, and EVOLVE/reflection trigger handling.
中文简介正在准备中。当前显示原文说明。
Specific optimization strategies for Python scripts working with larger-than-memory datasets via Dask.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Use when project vocabulary is fuzzy, overloaded, disputed, or needed before naming docs, schemas, commands, skills, code, plans, or memory.
中文简介正在准备中。当前显示原文说明。
Use when deciding what project context should be remembered, retrieved, updated, or deliberately forgotten.
中文简介正在准备中。当前显示原文说明。
Use when repeated wins or failures should become durable memory, wiki, or skill updates.
中文简介正在准备中。当前显示原文说明。
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).
中文简介正在准备中。当前显示原文说明。
Use this skill when tool outputs exceed 2000 tokens, tasks span multiple conversation turns, sub-agents need to share state, context window is bloating, plans need to persist across summarization, terminal/log output needs selective querying, or when user mentions "offload context", "dynamic context discovery", "filesystem memory", "scratch pad", "reduce context bloat", or "just-in-time context loading".
中文简介正在准备中。当前显示原文说明。
Use when the user and agent may hold different pictures of current state after a gap, sync request, or exposed stale claim. Not for persistence: use memory-update.
中文简介正在准备中。当前显示原文说明。
对 msMemScope 显存数据做全链路处理：根据用户的显存问题诉求（OOM、显存泄漏、显存占比拆解、Step 间对比等），指导并帮助用户以最合适的 msMemScope 采集配置完成显存数据采集（支持命令行、Python 接口、mstx 打点三种采集方式，覆盖训练、推理 vLLM-Ascend、FSDP、强化学习 verl 等场景）；对已采集的 memscope_dump_*.csv/db 数据做系统性解读与问题诊断（整体显存曲线趋势分析、显存使用大头按模块/组件拆解分析、显存峰值点各模块与流程占比分析，以及对显存泄漏、OOM 等典型问题的根因定位与原因分析）。
中文简介正在准备中。当前显示原文说明。
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
中文简介正在准备中。当前显示原文说明。
Use when the user wants an agent to track, inspect, or operate Research Pilot project memory through natural chat.
中文简介正在准备中。当前显示原文说明。