Claude Skills by majiayu000

維護和更新專案的 Memory Bank 記憶系統。

Always-on MemoryManager + LearningPolicy workflow. Use when storing/retrieving memories, emitting retrieval signals, running consolidation/pruning, or when a session should default to the Atlas memory system (MemoryManager, MemoryConsolidator, LearningPolicy). Triggers: memory add/retrieve, consolidation, pruning, semantic search, or 'use the memory system by default.'

Data workflow, memory system separation, and observation rules for git-review. Defines which memory system to use for what, and how to avoid duplication. Use when saving decisions, recording observations, or managing cross-session state.

Persistent memory and context compression for Claude Code. Use when setting up or operating MemoryLane in a project, recalling or storing memories, reviewing insights, curating low-quality memories, or checking cost/token savings and automatic context injection.

Production-ready long-term memory server for AI agents with Ebbinghaus decay and strength-weighted retrieval. Use when you need persistent memory across agent sessions, memory decay (forgetting curve), memory statistics, or multi-agent memory tracking. Triggers: long-term memory, remember, recall, memory decay, Ebbinghaus, agent memory, memvault. Requires Docker.

Message consolidation and conversation compaction for blah.chat. Covers comparison consolidation (merging multi-model responses) and conversation compaction (summarizing long chats). Triggers on "consolidation", "consolidate", "merge messages", "compaction", "compact conversation", "comparison group", "context window".

Session startup ritual that loads context files, creates daily memory, checks for stale context, and surfaces documentation status. Runs automatically at the start of every session, or invoke manually with /meta-heartbeat to re-initialize context. Does NOT trigger for mid-session work.

End-of-session checklist that reviews deliverables, updates daily memory, distills learnings, checks for documentation gaps, and optionally commits work. Use when the user says "wrap up", "close session", "end session", "wrap things up", "we're done", "that's it for today", "session done", or invokes /meta-wrap-up. Run at the end of any working session or after completing a major deliverable. Does NOT trigger for regular development work.

Manage session context - focus, threads, questions, and observations. Use when tracking what you're working on, managing parallel work streams, or capturing friction points.

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

Claude Code context window optimization strategies, JIT retrieval, progressive loading, memory file patterns, and cleanup practices. Use when optimizing context usage, managing large projects, or implementing efficient workflows.

Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context continuity for Claude Sonnet 4.5 and Haiku 4.5 with context awareness features

Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context continuity for Claude Sonnet 4.5 and Haiku 4.5 with context awareness features

Claude Code memory management, context persistence, and knowledge retention. Use when managing session memory, persisting context, or optimizing knowledge retention.

Claude Code memory management, context persistence, and knowledge retention. Use when managing session memory, persisting context, or optimizing knowledge retention.

Enterprise context and session management with token budget optimization and state persistence

Enterprise context and session management with token budget optimization and state persistence

Enterprise context and session management with token budget optimization and state persistence

Enhanced Just-In-Time document loading system that intelligently discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation, when working with new technologies, when answering domain-specific questions, or when context indicates documentation gaps.

Enhanced Just-In-Time document loading system that intelligently discovers,

Enhanced Just-In-Time document loading system that intelligently discovers,

MONAD-grounded cognitive architecture for AI memory as morphemic substrate navigation. Memory is not storage but substrate sampling - accessing the same structure that underlies reality. Implements φ-scaling, GOD operators, toroidal coherence tracking, and the 4.5%/95.5% observable/dark split. Replaces nexus-mind with theoretically grounded architecture.

MONAD-grounded cognitive architecture for AI memory as morphemic substrate navigation. Memory is not storage but substrate sampling - accessing the same structure that underlies reality. Implements φ-scaling, GOD operators, toroidal coherence tracking, and the 4.5%/95.5% observable/dark split. Replaces nexus-mind with theoretically grounded architecture.

File-level knowledge substrate via git notes. Read notes before working on files, leave notes after meaningful work. Daimonic spores carry creator identity across sessions.

Maintain a per-repo napkin file that tracks mistakes, corrections, and what works. Activates EVERY session, unconditionally. Read the napkin before doing anything. Write to it continuously as you work — not just at session boundaries. Log your own mistakes, not just user corrections. The napkin lives in the repo at `.opencode/napkin.md`.

Create context save points to preserve conversation state before breaks, risky changes, or compaction. Use when user says "save my progress", "create checkpoint", "mark this point", or before clearing context.

Manage user preferences and corrections for bilateral modeling. Auto-learns from session corrections. Use when user says "save my preferences", "remember I like...", or auto-triggers after corrections.

Load SuperNavigator (OS + App layers) documentation when starting development session. Loads Navigator context + injects using-superpowers App layer. Use when user mentions starting work, beginning session, or checking project status.

Use when user runs /neotex-init to deeply scan a codebase and auto-generate organizational knowledge for neotex.

Use when working in projects with .neotex/ directory to retrieve organizational knowledge, search for patterns/guidelines/decisions, store learnings, or manage reference assets like images and files.

Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks "do you remember..." or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store for future reference (5) User asks "why did X happen?" — trace causal chains through memory Zero LLM dependency. Neural graph wi...

Never Use TaskOutput

保存会话笔记到记事本，防止上下文压缩丢失

Use when a debugging session, research, or investigation yields non-obvious findings worth preserving for future sessions.

Use when a debugging session, research, or investigation yields non-obvious findings worth preserving for future sessions.

Save notes to notepad.md for compaction resilience

Save notes to notepad.md for compaction resilience

Compaction 내성 메모장. 중요한 컨텍스트, 결정 사항, 진행 상태를 작업별 state 폴더에 저장하여 컨텍스트 윈도우 초과나 세션 전환 시에도 정보가 보존됩니다. .gitignore로 관리되어 프로젝트를 오염시키지 않습니다. Use when you need to persist important context across compaction boundaries or session transitions.

Maintain structured working notes throughout execution to prevent information loss during context pruning.

Use this skill when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks. Provides a durable notepad that survives compaction and lets any agent pick up exactly where the previous context left off.

Provides on-demand access to accumulated observations stored in ~/.claude-mind/memory/observations.md.

Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity.

Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity.

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.

Zero-dependency memory maintenance CLI for OpenClaw. Keeps MEMORY.md lean with 3-tier hierarchical organization. Works alongside Mem0, Supermemory, QMD — or standalone. Install once, forget about memory management.

Persistent long-term agent memory for storing and querying past work, patterns, and learnings.

Summarizing context, pruning history, and managing token budget efficiency.

Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use when asked to "optimize docs", "improve agent knowledge", "make docs more efficient", or when documentation has accumulated and retrieval feels inefficient. Generates a manifest mapping task-contexts to knowledge chunks, optimizes information density, and creates compiled artifacts for efficient agent consumption.

Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and research index to produce a focused orientation briefing.

Persistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons. Triggers: memory, save memory, search memory, lessons learned, remember, recall