An AI that predicts the market is everywhere. This is the opposite: a guard that remembers YOUR past trading mistakes and warns you before you repeat one. Keep a small Markdown pattern journal (FOMO chases, thesis-less averaging down, "bubble" misses); before any trade decision the agent scans it and shows your own words back — how it ended last time, and the rules you set for yourself. Runs 100% locally, no API keys, Korean & English. Self-review tool only — not investment advice.
This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.
LLMエージェントがセッションをまたいで記憶を保持するための永続メモリ層。抽象基底クラス MemoryStore ＋ LocalJSONStore 実装で、保存・取得・検索を再利用可能に。Karpathy の「LLM OS（記憶＝ディスク層）」着想。バックエンド差し替え可・Python標準ライブラリのみ・LLM呼び出しゼロ・ユニットテスト同梱。
Your agent forgets why it decided things once the conversation gets summarised. Session Checkpoint keeps a STATUS.md at your project root — current state, the exact next command, decisions with their reasons, pitfalls already hit — and installs a session hook that reloads it automatically, so every new session opens with a briefing instead of amnesia.
Turn web research into verified answers, evidence trails, durable memory proposals, long-form notes, and reusable agent playbooks.
AI Agent Skill：根據你主動提供的作息、當下情境與修正，提出可解釋的下一步假設。跨對話分層記憶與提醒都需要相容的宿主工具、欄位揭露及你的確認；沒有工具時只使用目前對話或提供未排程計畫。
Compile how you actually decide into one paste-in a file any AI can run. Proven with your own task, two drafts side by side. File always stays yours.
This Skill is built on practical expertise in AI persona design, brand voice governance, character bible maintenance, dialogue QA, tone drift detection, and role-boundary review. It helps AI agents keep role, vocabulary, emotional range, relationship context, forbidden phrases, and channel fit consistent across support bots, sales assistants, companion bots, fictional characters, and long-running conversations.