Direct Gemini-native integration of OpenWiki for autonomous, high-agency documentation management and release notes maintenance.
Establish operational memory bank structure for production systems. Choose between separate, integrated, or hybrid operational knowledge structure based on team dynamics, access…
Profile, audit, and optimize frontend page performance with emphasis on animation work, memory-leak risks, long-session slowdowns, CSS animations, canvas/WebGL…
Implements Zero Allocation patterns using Span, ArrayPool, and ObjectPool for memory efficiency in .NET.
Provides essential Zero Allocation patterns using Span and ArrayPool. Use when quickly referencing core memory optimization techniques without detailed explanations.
知识库 OrbitOS Obsidian Vault 共享配置。Vault 结构、格式规则、排版规范。被 orbit-* 系列 skill 自动引用；也可在知识库相关操作中直接调用以获取上下文。
Use quando o usuário pedir para organizar, arrumar, mover, limpar ou sincronizar arquivos no Google Drive, especialmente da pasta 'Documentos Obsidian'.
Organizational strategy and management theory for business decision-making. Covers objectives-based management, the knowledge-worker firm, decentralization, the five management…
Initialize orra in the current repo. Runs orra_setup, installs all stock directives, and adds vault-bridge when memento-vault is available.
Trigger with "remember this", "update memory", "what should we record from this session", "capture learnings", "write a session log", or when closing a session.
Outline is a fast, collaborative knowledge base for teams built with React and Node.js. It provides real-time editing, Markdown support, and a rich API for integration with Slack,…
Use when inspecting Obsidian callout types, malformed callouts, nested callouts, or callout taxonomy.
Use when writing or reviewing pandas code. Covers idiomatic, vectorized, memory-efficient patterns; avoiding SettingWithCopyWarning, chained indexing, and slow apply loops.
Store passwords with a slow, salted, memory-hard hash and a plan to raise the cost over time. Use when building signup or login, migrating off a weak hash, or reviewing how a…
PDF를 vault 잉게스트 가능한 MD로 변환해 Clippings/에 투입한다. 페이지별 텍스트 밀도를 측정해 변환 전략(S2 pymupdf4llm / S6 로컬 OCR / S4 Claude 비전 전사)을 제안하고 사용자 확인 후 실행한다. wiki화는 하지 않는다 — 기존 vault-ingest가 이어받는다.
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM f — from…
Session-after-session product perfection loop for Vibeman. The strongest available model (Fable) directs — it walks the repo's context map context-by-context, proposes 5…
Analyze volatile memory dumps using Volatility 3 to extract running processes, network connections, loaded modules,
Bridges session memory to persistent storage across conversations. Use for: remember this, persistent memory, save to memory, recall later.
面向 AI Agent 的无限分层持久记忆系统，在内置记忆之上构建并行、可扩展、可检索的结构化本地存储. 直击跨会话遗忘、检索不准、记忆膨胀、新旧冲突四大痛点。核心能力涵盖无限分层结构化存储、 三层索引体系、混合检索策略、记忆生命周期管理、冲突检测与版本化、分类自动分裂、回收站恢复机制.
|-. 适合需要persistent memory engine相关能力的开发场景,提供完整工作流程和配置指南. 该工具经过差异化增强,结合实际使用痛点进行了优化。Use。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。适用于独立开发者、企业团队和自动化工作流场景。
面向 AI Agent 的基础持久记忆系统，在内置记忆之上构建并行的结构化本地存储. 基础能力涵盖分层结构化存储、三层索引体系、混合检索策略. 完全位于 ~/memory/，与内置 Agent 记忆并行运作，永不修改内置 MEMORY.md. 适用于项目记忆、人脉管理、知识库构建等基础场景.
Five-layer Willow memory model — flat-file boot, intake, KB, SOIL, handoff — with write rules and promotion paths.
PKM systems comparison covering PARA, Zettelkasten, GTD, and Building a Second Brain methodologies with capture workflows, processing routines, retrieval strategies, tool…
Sync ~/.personal/tracker.json to/from an Obsidian markdown vault at ~/.personal/vault/. Bidirectional, idempotent, runs on demand or via 15-min launchd cron.
Créer des statblocks (blocs de statistiques) pour les différents éléments de Pathfinder 2e, tels que les PJ, PNJ, monstres, feats (dons), sorts (spells), actions, activités, etc.
구현 결과 → Obsidian 설계 동기화. Git diff 분석, 참조 체이닝 업데이트, 회고 기록, Linear 정리.
Unified memory bus for the Proactive Intelligence Layer with 4-tier hierarchy, namespace management, TTL-typed storage, and vector search.
Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates,…
Decide where to place a new rule, skill, hook, KB entry, agent, CLAUDE.md rule, memory, or context artifact.
How to work in a Plain Notes project (the `plain-notes` starter pack): a flat notes/ folder plus a daily/ journal. The 'I just want to write' layout.
PLAUD NotePin 녹음을 Plaud Web에서 자동 수집하고 로컬 faster-whisper로 음성 인식해 Obsidian Vault의 날짜별 Markdown에 저장하는 파이프라인. 사용자가 "plaud 가져와", "오늘 녹음 정리해줘", "녹음 처리해", "/plaud-daily" 같은 요청을 하면 발동.
Evaluate a local pre-trade checklist before manual order entry, blocking planless, oversized, revenge-risk, market-regime-blocked, or circuit-breaker-blocked entries while…
Use Rowboat to build local work memory from email, calendar, notes, and web context, then generate meeting briefs, follow-ups, docs, and decks.
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like — from…
Coordinate projects using Zettelkasten method in Obsidian Markdown files. Organize current status, project state, and team into linked atomic notes with beautiful formatting.
Use when extracting durable project knowledge from code, docs, issues, incidents, reports, screenshots, or conversations into reusable context such as skills, ADRs, glossaries,…
Maintain a project-level knowledge base for coding agents using AGENTS.md, knowledge files, bug memory, decisions, and changelog records.
A governed project management OS for OpenClaw that applies to user requests involving planning, coordination, memory, or potential conflicts, supports optional project creation…
Menganalisis sesi terakhir untuk mencatat progress, mengambil pelajaran, dan menyimpannya ke instruksi memory proyek.
Persist and retrieve durable project knowledge artifacts across orchestration stages.
Store project-specific insights and context into file-based memory. Use after completing tasks that reveal important details about THIS codebase.
프로젝트별 Claude Code 세션 시간을 집계하여 리포트 생성. 일별/주별/월별 시간 분포를 Obsidian 테이블로 시각화. "시간 추적", "프로젝트 시간", "time tracking" 등의 요청 시 자동 적용.
Instrui o Claude a usar o servidor MCP advwiki como memória arquitetural persistente de projetos de software — especialmente arquiteturas de microsserviços.
E-signering är idag inbäddat i quotes + contracts (SES-nivå, eIDAS-giltig). Planerad extraktion till en horisontell modul à la Odoo Sign när 3:e entity behöver signering.
Publish a completed static HTML page or slide deck into the erain/knowledge-pages hosting repository, supporting public and unlisted visibility, updating artifact metadata,…
Publish a structured specification or document to a Confluence page using the Atlassian MCP server.
Push a planning artifact to Confluence as a formatted page. Use when the user says 'push to Confluence', 'publish this doc', or 'sync to Confluence'.
Consulta e envia conhecimento à base PW2C (LightRAG). Use ao planejar, antes de codar, ao resolver bugs/tarefas complexas ou quando o usuário pedir para consultar/indexar a base.
Run a QLoRA (4-bit LoRA) fine-tune of an open-weight model from a prepared dataset — set up the config, train memory-efficiently (e.g.
Fast, read-only, index-first queries over an llm-wiki with bounded file reads, exact citations, and honest evidence gaps.
Expert in building Datalog queries for Logseq DB graphs. Auto-invokes when users need help writing Logseq queries, understanding Datalog syntax, optimizing query performance, or…
Save a quick memo to Obsidian for future recall. Use when the user says 'メモ', 'note', '覚えて', '記録', or wants to jot down a quick thought, tip, or reminder.
Suppress trailer sections (teaching-provenance and knowledge-diff) from the immediately following agent response without disabling Learning Mode writes or any other agent…
Sync buffered memories to Cognee. Use when agent-memory reconnects or to force sync pending entries.
Inspect public GitHub repositories by orienting with README/docs/manifests and DeepWiki-style summaries first, then reading the real source files that answer the user’s question.
Jog the agent's memory on a topic, person, or project that lives somewhere in the user's Obsidian vault (second brain). Works from any directory on the machine.
Expert in reading data from Logseq DB graphs via HTTP API or CLI. Auto-invokes when users want to fetch pages, blocks, or properties from Logseq, execute Datalog queries against…
Verify a session's working assumptions are still true before building on them — referenced PRs/issues/branches still in the state a handoff or plan claims, base-branch drift,…
Safely apply chunking configurations to Zarr datasets with validation, progress reporting, memory-bounded execution, and rollback safety. Supports local and cloud storage backends.