Claude Skills by majiayu000

Extract reusable patterns from the current session and save them as skills. Use after solving a non-trivial problem to capture the solution for future sessions. Saves to .claude/skills/learned/.

Persistent memory system for storing and recalling learnings across sessions. AUTO-INVOKE THIS SKILL when you: - Fix a non-obvious bug (store as "bug") - Discover a useful code pattern (store as "pattern") - Encounter a gotcha or edge case (store as "gotcha") - Find a useful tool/library feature (store as "tool") - Make a performance optimization (store as "perf") - Discover configuration that solved a problem (store as "config") - Make an architecture decision with rationale (store as "arch...

[Utilities] Teach Claude lessons that persist across sessions. Triggers on 'remember this', 'always do', 'never do', 'learn this', 'from now on'. Smart routing to the most relevant reference doc.

When the user asks to learn, remember, or save a preference — or after a conversation where the user gave corrections or guidance worth preserving — review the conversation to identify learnings and propose memory updates (CLAUDE.md, rules, skills, agents, docs). Can create new files or reorganize existing ones. Always requires user approval before changes.

Capture lessons after fixing a bug or receiving a correction — ecto, liveview, oban, iron law mistakes. Use when the user corrects your approach or teaches a pattern.

When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented it. The skill library should grow from real failures, not hypothetical improvements. Every painful debugging session is a skill waiting to be written.

Record mistakes. Check before similar builds. Avoid repeating silently.

Detect recurring patterns in user's project. Apply automatically next time.

Learn user's preferences over time. Code style, naming, structure. Save to global prefs.

Scan project code to detect patterns, dependencies, and conventions. Propose domain rules based on what the code actually does.

Extract lessons from conversation and persist to project configuration

Extract learnings from current conversation and add to project's CLAUDE.md.

Log a learning, discovery, or decision to the vault with full context from the current conversation.

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

Extracts reusable patterns from sessions. Use at session end to capture debugging insights and project-specific knowledge.

Add a learned pattern (lesson) that Ralph will remember for future stories.

libmemory - Memory management for LLM context windows. WindowBuilder constructs token-limited context from conversation history and tools. createWindow factory simplifies window creation. MemoryIndex stores conversation identifiers. Use for managing chat history, building LLM prompts, and context window optimization.

libutil - General utilities. countTokens and estimateTokens for GPT-style token counting. generateHash creates SHA256 hashes. generateUuid creates unique IDs findProjectRoot locates repository root. updateEnvFile modifies environment files. exec runs child processes. createBundler downloads code bundles. Use for token counting, hashing, and project utilities.

Use when recalling conversations from Limitless Pendant, finding what was discussed in meetings, searching lifelogs, or answering 'what did I say about' questions

Fetch a URL, summarize it, and save it to memory for later retrieval. Use when the user drops a link and wants it remembered, or asks to "save this link".

Auto-load relevant memories at session start from both mem0 and graph. Use when you need session context restored or preloaded.

バグ修正・エラー解消・技術的知見を自動記録するスキル。デバッグで発見したインサイト、実装上のハマりポイント、設定の回避策などをExocortexに保存し、将来の同様の問題解決を効率化する。プロジェクト固有でなくても、汎用的な技術知見も記録対象。

コンテキストサイズを監視し、作業中に自動 compact が走らないよう事前にコンテキストを圧縮する。「コンテキストを圧縮して」「compact して」「メモリを整理」「会話を整理」「履歴を圧縮」「コンテキストが大きい」「動作が重い」などで起動。操作がない時やタスクの区切りでコンテキストが一定ラインを超えていたら自動的に /compact を実行。

This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, saving user/assistant messages, fetching history for agent input, and handling async database queries.

This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, saving user/assistant messages, fetching history for agent input, and handling async database queries.

This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, saving user/assistant messages, fetching history for agent input, and handling async database queries.

This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, saving user/assistant messages, fetching history for agent input, and handling async database queries.

This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, saving user/assistant messages, fetching history for agent input, and handling async database queries.

Local memory storage patterns, file coordination, and cleanup

Local memory storage patterns, file coordination, and cleanup

Memory layer operations for persistent session storage

Helps manage context window efficiently by summarizing, focusing, and pruning context to stay within token limits.

Optimize MCP tool context loading through progressive disclosure and hierarchical indexing. Use when working with large MCP tool sets (e.g., Miyabi's 172 tools) to prevent context window bloat. Triggers include "find tool", "search mcp", "tool lookup", "which tool", "context optimization", or when dealing with many MCP tools.

- Overview

- Overview

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.

Auto-sync session context, decisions, and patterns to Mem0 for cross-session continuity

This skill should be used when the user asks to "search the KB", "find documentation", "add to knowledge base", "document this pattern", "check organizational docs", or when an agent discovers reusable knowledge worth preserving.

Search, filter, and retrieve Claude/Codex history indexed by the memex CLI. Use when the user wants to index history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-friendly JSON output for RAG.

双层结构化长效记忆专家 (Kontext-Aware)

SQLite 기반 메모 저장, 조회, 삭제 (사용자 선호도, 중요 정보 기억)

Esta skill gerencia a memória persistente por usuário, permitindo que

Update agent memory (Sessions, Lessons, Preferences, Checkpoint, Context) and Brief.md

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.

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 tasks, detect decision patterns, or audit what was carried forward vs dropped. Also triggers on "what did I decide about X", "what's still pending", "weekly review", "memory synthesis", "what patterns do you see".

Route memory operations to appropriate backends (Graphiti for knowledge, AgentDB for coordination).

Manage development logs in .aimemory/ with chronological date ordering.

Establishes a persistent "Long-Term Memory" file to prevent context amnesia across sessions.

Cross-session continuity through pattern compression. Use when need to bridge sessions, accumulate wisdom, or evolve without calcifying.