Memory Evolution
Paste the following prompt into your AI chat to install this skill:
Please install @user_0327da8d/memory-evolution according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem addressed
Agents often repeat the same mistakes, forget user corrections, or keep stale rules in context. This skill turns task experience into local, searchable, decaying memory with explicit promotion and archival rules.
How it works and limits
- Triggers: automatic reflection after significant work, manual runs via
reflect,回顾, or做梦, and scheduled dream cycles for decay scoring. - Memory tiers: observations go to
reflections/log.md, user corrections go tohot/corrections.md, repeated critical patterns may be promoted tohot/memory.md, while low-scoring entries move towarm/orcold/archive/. - Decay model: scores in
engine/decay-scores.jsoncontrol availability;1.0-0.5is active,0.5-0.2loads on demand, and0.2-0.05is searchable only when explicitly requested. Invalid scores reset with a logged warning. - Safety: writes to
hot/memory.mdrequire confirmation, archival never deletes, conflicts resolve by specificity, recency, and user corrections, and the skill does not access calendar, email, or contacts, make network requests, or infer preferences from silence.
Use Cases
- After a multi-file refactor, have the agent reflect on failure patterns and log user corrections to memory.
- While maintaining a recurring agent workflow, use reflect to extract 2-4 reusable rules from the last 7 days.
- During a heartbeat job, run decay scoring, demote low-score memories, and archive cold entries.
- When the agent repeatedly violates a rule, confirm the user correction replaces it and leave a trace in logs.
Best For
- Engineers maintaining agent workflows who want repeated corrections persisted as searchable memory.
- Builders of multi-step task automation who want agents to log non-obvious lessons after completion.
- Teams running heartbeat-scheduled agents who want stale memories demoted by score, not retained indefinitely.
- Product developers needing local memory isolation without email, calendar, contacts, or network access.
Related Skills
Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.
Run a grilling session to interact with or test AI agents.
A systematic prompt optimization skill that refines prompts using a four-step distillation framework (diagnose, structure, think, compress) and methodologies from four prompting masters.