Automate Buff's three-tier memory system across global and project scopes.
npx skills add https://github.com/qkal/claude-beta-script --skill buff-counterfeit
Please help me install this Agent Skill. Skill: buff-counterfeit Source: https://github.com/qkal/claude-beta-script/tree/main/skills/counterfeit Command: npx skills add https://github.com/qkal/claude-beta-script --skill buff-counterfeit
Counterfeit automates Buff's three-tier memory system (preferences, patterns, corrections) across global and project contexts to ensure persistent recall, faster context switching, and smarter responses.
Ask Buff to show memory to review current preferences and recent corrections.
High-intent search queries and answers about installing and using this skill.
Persistent AI memory is managed by a three-tier system that records preferences, patterns, and corrections across global and project scopes to keep context consistent between sessions.
Saving AI corrections is handled during ongoing interactions by capturing user feedback and applying project-level overrides, ensuring learnings improve future outputs and decisions automatically.
Merging global AI preferences with project-specific context is supported, allowing project-level overrides to align learning with the current working environment while retaining broader session history.
Incremental graph updates are supported on-demand, applying during session starts and correction flows to maintain lean memory payloads while preserving user intent and decisions for large projects.
Reviewing current AI memory requires asking Buff to show memory, which displays active preferences, captured patterns, and recent corrections across the global and project scopes.
chadanandaCreate and validate isolated Git worktrees for feature work.
xavierfuentesPreserve and restore user context across Claude Code sessions.
enbiyagoralPersist session learnings and corrections to memory files with YAML frontmatter.
gula00Store learned user corrections and patterns in a tiered memory system.
