Research and synthesize from a local Verifiable Memory Bank with source-backed evidence, reproducible selectors, chronology, attribution, and explicit uncertainty. Use when a request asks Codex to recall banked material, investigate a topic, verify a claim, build a dossier or timeline, distinguish quoted facts from…
Maintainer view of the agentic-memory system. Use when onboarding to the codebase, planning a refactor that crosses module boundaries, or answering "what calls what / what depends on what". Don't use for end-user MCP tool questions — that's the user-facing agentic-memory skill.
Use OpenViking long-term memory and context database via the openviking MCP tools. Trigger when the user mentions memory, recall, remember, viking:// URIs, OpenViking, past preferences, or stored project knowledge.
Search and manage durable personal or project knowledge through the Foundation MCP atom tools. Use when prior preferences, decisions, constraints, facts, people, procedures, or project context could materially improve the answer. Do not use for transient chatter or secrets.
Deep exploration of Memoo knowledge graphs via Memoo MCP. Use when investigating connections, tracing decisions, or understanding architectural evolution in a Memoo namespace.
Guide an incremental, evidence-aware discussion that turns an AI, product, model-strategy, competition, or implementation topic into durable personal cognition. Use when the user wants to discuss, learn, explore, compare, challenge, or deeply understand such a topic, including a recommended daily topic. Ask one…
A Chinese-language search tool for finding content in a user's local collection, including documents, code, images with text, saved web pages, and video transcripts. It can also index files, find similar content, show time-based patterns, and map relationships between named things.
Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands, (3) check schema-pack consistency against the brain's actual shape, (4) file enriched brain pages, (5) audit the…
A standard operating guide for maintaining LeafMem, a memory engine for an AI system. It covers checking memory health, combining duplicates and fragments, updating profiles, and adjusting the importance of older memories.
Process new Raveil Frontispice handoffs at Codex session start/resume, classify them, delegate relevant verification to specialist agents, integrate validated conclusions into repository knowledge, and acknowledge only completed handoffs.
Answer questions about this project, its history, past conversations, and prior team decisions from source-backed evidence with verified citations. Use whenever the user asks what something is, why it was decided, what happened before, or what the team already knows.
Incrementally integrate a user-provided batch of recent learning, project progress, debugging, practice, and observations into an existing Obsidian knowledge base. Use for requests to organize or synchronize a heterogeneous recent batch. Preserve confirmed evidence attribution, but do not initiate method attribution…
Persistent semantic memory across sessions, stored in a local HNSW vector index with local embeddings and no external API calls. Use when the user asks you to remember something for later, refers to something decided or discussed in an earlier session, asks what you already know about a topic or project, or when you…
Anchor this session to a named Chat Across environment and auto-sync a compacted context brief both ways. Use when the user says "chat-across " or asks to connect/anchor to a Chat Across environment.
Use this skill whenever working on a project that has a Continuity MCP server connected (tools named memoryinit, memoryread, memoryupdate, memorylog, memorycompact, memorylist, memorystatus). This applies any time the user references "the project," resumes prior work, or the conversation involves multi-step or…
Generates, maintains, and visualizes a structured Markdown knowledge base (.lithium-kb/{architecture,debug,tasks,features}) with an interactive Neural Network graph, auto-watch mode, custom agent directives (.agentrules), and MCP server integration for Pi, Claude, Codex, Cursor, and other coding agents. Triggers…
A long-term memory workflow for coding work. It searches stored decisions and project knowledge before an answer, then saves useful new context afterward when the required memory tools are available.
An MCP connection to AIWorkers, a service for managing automated workers, chats, memory, tasks, surveys, Telegram commands, and account or group balances. It includes a login flow that keeps tokens out of URLs and chat.
Open, search, read, and analyze an Obsidian-compatible Markdown vault through COMET. When invoked directly without another request, open the interactive COMET explorer. Use for note discovery, wikilinks, backlinks, tags, graph traversal, orphan detection, and vault-based synthesis. Do not use for unrelated source-code…
Wire Memvara into an agent or editor, pick the right surface (hosted MCP, Python library, REST), and use memory without forging history. Use when the user wants persistent memory, says remember this, that's wrong, you forgot, what do you know about me, delete that, why did you say that, migrate from mem0, connect MCP…
Search the auto-knowledge-sync MCP knowledge base before non-trivial technical research, architecture or design decisions, dependency or version choices, and troubleshooting. Use it to reuse prior technical knowledge without treating it as current authority, and to capture only durable, complete, privacy-safe…
★not rated 0 2mo agoA65 tokens
originalApache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: