feat(agent-context-optimizer): add community skill for multi-agent memory optimization#58
Open
roymaste wants to merge 2 commits intoMiniMax-AI:mainfrom
Open
feat(agent-context-optimizer): add community skill for multi-agent memory optimization#58roymaste wants to merge 2 commits intoMiniMax-AI:mainfrom
roymaste wants to merge 2 commits intoMiniMax-AI:mainfrom
Conversation
added 2 commits
April 2, 2026 21:56
…mory optimization - Add agent-context-optimizer skill for zero memory loss in LLM agents - Hot layer (<500 tokens) stores summaries, decisions, tasks - Cold layer (unlimited) stores full history with vector indexing - 60-70% token reduction for multi-agent systems Closes: context-optimizer社区贡献
…tion guide Updated from roymaste/context-optimizer@30fffb0 Added behavioral integration guide explaining: - Skill is a tool, NOT auto-triggering - SOUL.md/AGENTS.md rules required for startup behavior - HEARTBEAT.md rules required for end-of-session behavior Lesson (2026-04-03): Even with skill installed, if agent doesn't call memory_search on wake, context loss continues.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Add agent-context-optimizer skill for zero memory loss in LLM agents.
Why
Multi-agent systems suffer from context overflow and memory loss. This skill provides:
Problem: Previous version was missing integration instructions. Users installed the skill but it didn't auto-trigger, causing continued context loss despite installation.
Solution: Added behavioral integration guide in SKILL.md explaining:
Key Lesson: Tool + Rules + Execution = All three required. Installation alone is insufficient.
Files