Memory skill
Production AI agent skills for OpenClaw — extracted from a real personal AI OS. RAG memory, safety guards, cost tracking, architect agent and more.
npx -y skills add Mickos79/aria-skills --skill memory-skillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.5 KB, 366 tokens by cl100k_base, as published. Nobody here has run it
Memory Skill — Conversational RAG
Teaches an AI assistant to use RAG memory correctly in conversation.
When to use this skill
Load this when your assistant has access to a RAG memory system and needs to answer questions about past events, conversations, or decisions.
Instructions for the assistant
Answering questions about the past
- "что делали вчера / what did we do yesterday" → search ## Memory Context by date
- "когда обсуждали X / when did we discuss X" → search ## Relevant memories by topic
- "помнишь как / remember when" → check ## Recent messages and ## Relevant memories
Rules
- Always use ## Memory Context if present in the system prompt
- Prefer specific dates when describing past events (e.g. "on March 24th we...")
- If memory doesn't contain the answer — say "I don't see that in memory" — never fabricate
- For time-based queries, combine date metadata + semantic search
Query expansion
Before searching, mentally expand vague queries:
- "вчера" → actual date
- "проект" → project name + key terms
- "мы делали" → specific task names from context
Memory layers (if your system has them)
- Hot (rag.messages): last 7 days, exact messages
- Warm (daily_summaries): day-level summaries, older history
- Cold (monthly_summaries): long-term archive
Integration
This skill works with any RAG system that injects memory into the system prompt under headers like:
## Memory Context## Relevant memories## Recent messages
Gives 0 of the 12 instructions most memory context skills give in 366 tokens
Counted across 674 of the 847 authors here whose files we hold, read 2026-08-06
- inform the user when setup is completein 21 of 674, across 6 files
- confirm the draft with the user before writingin 21 of 674, across 6 files
- update the agent skills block in place if it existsin 21 of 674, across 6 files
- present findings to the userin 20 of 674, across 5 files
- write the three docs files from seed templatesin 20 of 674, across 5 files
- ask the user about each decision one at a timein 19 of 674, across 4 files
- edit CLAUDE.md if it existsin 18 of 674, across 3 files
- explore current repo statein 18 of 674, across 3 files
- do not overwrite user edits to surrounding sectionsin 18 of 674, across 3 files
- back up the original file before overwritingin 16 of 674, across 8 files
- keep the memory index under 200 linesin 15 of 674
- Provide actionable steps and verificationin 13 of 674, across 2 files
Said here and by no other author read
- use memory context if present
- use specific dates when describing past events
- say if memory lacks the answer
- combine date metadata and semantic search
- expand vague queries before searching
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.