The workflow contract for any agent that ingests, retrieves from, or maintains a claude-wiki-pages vault.
Create well-structured notes in Obsidian with intelligent tag suggestions. Use when the user asks to create a note, make a note, or save content to Obsidian.
Filter prefetched memory attachments against cumulative read state before mutating that state, so async surfacing does not dedupe itself away.
Render mathematical formulas in Obsidian using LaTeX/MathJax syntax. Use when writing equations, matrices, integrals, summations, or any mathematical notation in Obsidian notes.
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
Search shared memories from past sessions. Use when the user's question could benefit from historical context, past decisions, project knowledge, or team expertise.
Setup Mem9 persistent memory. Triggers: set up mem9, install mem9, configure memory, enable memory.
Save important information to shared memory. Use when the user asks you to remember, note down, or save something for future sessions.
Populate or refresh a persistent, high-level project snapshot in memoir. In a git repo this writes `codebase:onboard` (code-shape: modules, goals, rules, lessons) — use when: (1)…
After QA PASS, compare the Story's implementation footprint against relevant memory entries. Reports confirmed entries, contradictions, and new knowledge candidates.
Store, retrieve, search, and manage persistent memory across sessions. Triggers on: memory, store, remember, retrieve, forget, pattern, context.
Cross-reference and synthesise daily memory files into patterns, insights, and carry-forward items. Use when asked to review memory, generate weekly synthesis, find forgotten…
Validate and auto-inject the 11-key provenance frontmatter contract on memory files at write time. Use when authoring memory entries, running lint passes on memory directories, or…
Use ALWAYS. Управление базой знаний memory-compiler. Вызывай при ЛЮБОМ сообщении пользователя кроме приветствий.
Persistent project documentation system that maintains context across sessions. Creates structured Memory Bank files to preserve project knowledge, decisions, and progress.
Unified memory capture with routing - session compact or quick tips. Triggers on "memory capture", "compact session", "save session", "quick tip", "memory tips", "记录", "压缩会话".
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著.
Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.
Use when the user needs to run hoangsa-memory CLI commands — setup / index / query / watch / impact / context / changes / memory / skills / eval / uninstall.
Emergency single-pass memory compression when context window pressure is high mid-task. Activate when approaching token limits during active work.
Use when consolidating session signals into curated memory — four-phase loop ORIENT → GATHER → CONSOLIDATE → PRUNE.
Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session start - memory is core to agent reasoning, not optional.
Runtime memory-writing discipline for ginnie-agents. Three tiers — rules (always loaded), playbook (always loaded), episodes (lazy-loaded via grep).
Diagnose and fix Signet memory issues (daemon health, embeddings, search quality, and data integrity).
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode.
Ensure memory directories exist once and surface consistent guidance so agents skip redundant mkdir calls.
Use to store, recall, query, or audit durable project knowledge — atomic facts and compound documents alike — plus a working notepad that survives conversation compaction.
BOND'a doğrudan bağlı, Subagents hiyerarşisinin dışında çalışan sistem kalite ve hafıza ajanı. Konuşma akışını izler, sinyal biriktirir, DNA tutarlılığını doğrular.
Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still…
Keep MEMORY.md terse by capping entries, warning when caps hit, and pointing each memory to its own file.
Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.
Knowledge graph orchestration layer with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting.
Session-end memory garbage collector. Promotes valuable L2 session facts to L1 atomic memory, wipes L2, and rotates oversized audit logs.
Use when the user asks about hoangsa-memory itself — available MCP tools, CLI commands, resources, prompts, skill catalog, or how to drive the memory/graph workflow.
Manual memory tiering — classify Hot/Warm/Cold, review candidates, and migrate MEMORY.md index + memory files.
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code.
Validate discoverability invariants of memory `index.md` and `archive/superseded-decisions.archive.md`. Tool-agnostic L3 prompt + capability-dependent L4 script.
Detect and heal index.md drift — finds memory files on disk not registered in index.md and registers them.
The "Long-Term Knowledge" specialist that curates the persistent memory (KIs) of the project. — from general/knowledge-mgmt
在当前目录下初始化记忆系统，生成 CLAUDE.md（可选 AGENT.md 给 Cursor 用）、MEMORY.md 和 memory/ 目录。当用户说"初始化记忆"、"搭建记忆"、"memory init"、"/memory-init"时触发。
Persistent context management for Claude Code sessions. Save, load, update, share, and audit session memory via MEMORY.md. Prevents context loss on compaction or session restart.
Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks, or fixing leak reports.
Detect memory leaks in desktop applications through heap analysis and object tracking
Health-check any consumer's semantic memory by composing structural and domain-specific checks
Loads relevant entries from memory/ into the conversation context. Use at the start of any non-trivial conversation, and any time the topic might overlap with what is stored in…
Review PRs and diffs for unbounded memory loading, concurrency explosions, oversized payload materialization, and missing pagination or byte caps.
Unified memory management - CLAUDE.md updates and documentation generation with interactive routing. Triggers on "memory manage", "update claude", "update memory", "generate…
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like — from…
Use when installing or configuring memory_map, writing CLAUDE.md session-setup instructions, choosing what to save in memory vs history, managing cross-project memory, tuning…
Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` where scope is `global` (default), `user`, `workspace`, or `ws`.
C++ and Rust memory model skill for concurrent programming. Use when understanding memory ordering, writing lock-free data structures, using std::atomic or Rust atomics,…
Tune moflo's memory stack for speed, RAM, and index quality. Covers HNSW parameters (M, efConstruction, ef), vector quantization, batch operations, and common bottlenecks.
Use when deciding the lowest-cost context path for a mixed corpus, especially when choosing among direct reading, helper conversion, graph build, graph update, or graph query.
Analyze context management, memory systems, and state continuity in agent frameworks. Use when (1) understanding how prompts are assembled, (2) evaluating eviction policies for…
Persistent memory patterns for moflo agents — session memory, long-term knowledge, pattern learning, and cross-session context via moflo's sql.js + HNSW vector store.
Persistent role-scoped memory across sessions. The agent that worked on your codebase yesterday knows things today.
Use when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.
Read Cody's temporal Neo4j memory graph. Use when drafting, briefing, or answering questions about current or historical contact/deal state.
Scan all memory files, documentation (**/docs/**/*.md), and README files (**/README.md) for drift, contradictions, and stale references.
Periodic memory maintenance — archive session files, convert recurring knowledge into summaries, update the memory index.