Use Letta to create agents whose identity, tools, memory blocks, and conversation state persist across sessions for long-running assistant or application workflows.
Update a notebook's cross-chain vault universe to the top 10 vaults by one-year return using the helper script output.
Use when building an agent that needs deep domain expertise — reads documents, checks them against professional knowledge, asks clarifying questions, and produces structured…
Query and curate knowledge-base using ByteRover CLI. Use `brv query` for knowledge retrieval, `brv curate` for adding context, and `brv push/pull` for syncing.
Interactive knowledge-driven project onboarding. Queries comprehensive knowledge across all domains, presents a structured project overview, identifies knowledge gaps, and…
Write C with explicit ownership conventions, bounds discipline, and sanitizers wired into every test run. Use when writing or reviewing C code, or hunting memory corruption.
Mostra o contexto atual carregado do Obsidian para o projeto. Exibe: project-context.md, decision-log.md e últimas decisões.
VS Code の未要約リリースを GitHub から検出し、まとめて日本語で要約して Obsidian Vault に保存する。各バージョンの要約は「注目ポイントを冒頭で深掘り → カテゴリ別の表で全変更を一覧」の構成。「最新まで追いついて」「VS Code のアップデート確認して」と頼まれた時に使う。
Register maintained or ephemeral Git checkouts with codebase-memory-mcp, keep long-lived indexes current through non-clobbering Git hooks, and tear down ephemeral indexes by exact…
Organizational learning from CFN Loop execution - workflow codification and playbooks. Use when you need to store successful patterns, query past learnings, track edge cases and…
将 AI 聊天内容提炼为结构化技术文档并保存到 Obsidian 知识库。支持三种文档类型：问题解决型、知识学习型、方案对比型。自动推断知识库分类目录，生成符合 Obsidian 规范的 Markdown 文件（含 frontmatter、双链）。适用于：(1) 聊天中解决了技术问题后想记录下来，(2) 学到新知识想沉淀到知识库，(3)…
Check Mojo code for memory safety issues (ownership violations, use-after-free, etc.). Use to catch memory bugs.
Find fields that have multiple different types across notes (schema violations). Triggers on "schema check", "frontmatter inconsistencies", "metadata violations", "type…
Check the health and state of a deployed SmartVault by querying on-chain data
Document AI-assisted development sessions to Obsidian vault using Chronicle data. Works with MCP (fastest) or CLI commands (portable).
Complete workflow for tracking development work with Chronicle - session recording, git tracking, AI summarization, and Obsidian documentation.
Use when hardening the reproducibility of a CIKM paper — pinning the pipeline stages where IR, mining, and knowledge-management results silently diverge, documenting KGs and…
Use when reasoning about CIKM peer review — the EasyChair double-blind pipeline, the mixed IR/data-mining/knowledge-management reviewer pool, per-track evaluation criteria, the…
Use when revising a CIKM manuscript for the tri-community readership — writing an opening that lands with IR, data-mining, and knowledge-management reviewers simultaneously,…
Instala un LLM Wiki (knowledge base markdown interconectado, estilo Carpati/Obsidian) en cualquier proyecto.
Audit, review, clean up, and prune Claude Code durable context. Use when the user asks about CLAUDE.md, CLAUDE.local.md, .claude/rules, user Claude rules, Claude Code auto memory,…
Persistent memory for Claude across conversations. Use when starting any task, before writing or editing code, before making decisions, when user mentions preferences or…
把剪贴板片段沉淀到本地知识库，自动补来源、标签和后续行动。；use for clipboard, knowledge, capture workflows；do not use for 保存敏感密钥明文, 忽略来源信息.
Create flashcards for spaced repetition learning, compatible with Anki import. Specializes in cloze deletion cards.
Use when a user asks to organize, save, compare, review, map, or dissect conversations and source material into an Obsidian vault or Markdown knowledge base, including Chinese…
AST-based code graph for fast symbol lookup, dependency analysis, and blast radius via codebase-memory-mcp MCP server
Codebase'i knowledge graph olarak analiz et. Dependency, call graph, hotspot analizi.
Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.
Retrieve universal coding patterns from vector database using true two-stage retrieval. Auto-invokes before complex tasks or when user says "--recall".
Store universal coding patterns into vector database. Auto-invokes after difficult tasks with broadly-applicable lessons.
Create and personalize a new local Codex Vault when the user asks for a persistent Markdown second brain or a new memory vault. Do not use for modifying an existing vault.
HERITAGE skill documenting the donor-era Obsidian plugin (integrations/obsidian-plugin, Control Plane views, task/session sync via unified_* and gsd_* tools).
Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion,…
Full memory hygiene cycle — compresses memory-sessions.md, deduplicates memory-decisions.md, and syncs key project facts to the memory MCP graph.
Developer implementation guide for adding compact memory to an Agent — covers fork agent pattern for compaction, trigger strategy, summary format design, and memory restoration in…
记忆增强陪伴——BRO/SIS 回复前自动 spawn MemoryAgent 检索近期记忆，让陪伴有"记得你"的感觉。无需用户触发，CTRL 路由到 BRO/SIS 时自动激活。
Expert in complex functions, contour integration, residue theory, and conformal mappings — from majiayu000/claude-skill-registry
Draft and revise company, internship, club, hackathon, competition, scholarship, and program application answers by retrieving verified reusable answer chunks and experience cards…
Expert-level guide to compression knowledge distillation. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
Extract and build a complete memory pack from a Claude conversation or session, synthesizing it into vault-ready artifacts so the next session resumes with full context.
Install and configure llm-wiki-hugo-cms in a wiki repository so it renders as a static Hugo site. Requires Hugo extended ≥ 0.147.0.
Use when the user wants to interact with Confluence — search pages, read documentation, create or update pages, or browse spaces
Expert in Confluence operations using Atlassian MCP. Use when the user says "search Confluence", "create a Confluence page", "update a page", "find documentation in Confluence",…
Advise on USING Confluence well, not operating it: make the structural call — is this a space, a page, or a child page? — diagnose why a wiki is a dread (can't find anything,…
Manage Confluence pages and spaces. Use when the user wants to: (1) List, create, update, or delete Confluence pages, (2) Search content across spaces, (3) View or manage spaces,…
Crawl an authenticated Confluence space (Atlassian Cloud or on-prem Server/Data Center) by page hierarchy and convert each page to clean Markdown with frontmatter.
Read a Confluence page and recursively explore its child pages up to 3 levels deep. Use when users want to comprehensively read a Confluence page tree, understand hierarchical…
Atlassian Confluence integration for enterprise documentation. Create and update pages via API, manage spaces and permissions, handle content migration, and sync between — from…
Atlassian Confluence integration for enterprise documentation. Create and update pages via API, manage spaces and permissions, handle content migration, and sync between — from…
Atlassian Confluence expert for creating and managing spaces, knowledge bases, and documentation. Configures space permissions and hierarchies, creates page templates with macros,…
Manages connections to Logseq graphs via HTTP API, CLI, or MCP Server. Auto-invokes when users mention connecting to Logseq, API tokens, graph paths, connection issues, or backend…
Identify how consciousness maintains, transforms, and operates itself. Use when diagnosing notion-reality engines, mind projection patterns, ego-sense dynamics, equanimity…
Assemble a minimal, high-signal execution context bundle from already-retrieved memory, governed artefacts, and applicable rules.
Personal knowledge base integration via Obsidian vault. Provides semantic search, note retrieval, and context loading for Claude Code sessions.
Use when work spans many turns or phases and you need durable notes, active-objective tracking, or context compaction without letting stale memory override the current codebase.
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long — from…
Implements Children''s Online Privacy Protection Act (COPPA) compliance under 16 CFR Part 312. Covers verifiable parental consent methods including signed forms, credit card…
Regenerate obsidian/Connections.md from current hermit state. Runs nightly via routine and after each turn that mutates sessions/proposals. Safe to invoke manually.
Obsidian LiveSync の CouchDbClient の構造と使用方法を説明します。CouchDbRepository トレイトの実装方法、HTTP プロキシパターン（forward_request）、longpoll リクエストの処理、メトリクス収集、ヘルスチェックの実装を理解・拡張する際に使用します。CouchDB…
从访谈转录、课程文件和 materials.jsonl 中提取带证据位置的观点、方法、步骤、案例、数据、边界与讲师原话，生成 knowledge-cards.jsonl。Use when the user says 知识萃取、提取课程知识卡、整理专家经验、把访谈变成可用素材，或 Course Producer 进入 knowledge_extraction…