From respect
This skill should be used when the user types "/respect-export", asks to "export learnings", "export preferences", "generate CLAUDE.md from feedback", or wants to create portable AI preferences from their respect economy data.
How this skill is triggered — by the user, by Claude, or both
Slash command
/respect:respect-exportThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Exports all learnings from the respect economy into a portable CLAUDE.md section that works without the plugin installed. This lets users share their "training" with teammates or carry it to other projects.
Exports all learnings from the respect economy into a portable CLAUDE.md section that works without the plugin installed. This lets users share their "training" with teammates or carry it to other projects.
respect-feedback.md in ~/.claude/projects/[encoded-cwd]/memory/
/ and . in the current working directory with -~/.claude/respect/wallet.json for stats context## Learnings)## Mistakes to Avoid)## Patterns)# AI Preferences (exported from respect plugin)
## Do
[Convert each learning's **Lesson** into a directive, e.g.:]
- Push repository changes before version bumping when publishing plugins
- Run tests before claiming work is complete
## Don't
[Convert each mistake's **Lesson** into a negative directive, e.g.:]
- Don't commit without running tests first
- Don't skip version bumps when updating plugins
## Patterns the user values
[Copy from the Patterns section, e.g.:]
- Systematic workflows and proper git practices
- Attention to detail in configuration files
./CLAUDE.md if the user wants (append, don't overwrite)npx claudepluginhub nixon2/respect --plugin respectGraduates proven patterns from auto-memory (MEMORY.md) into permanent CLAUDE.md or .claude/rules/ files for enforced project conventions.
Evaluates its own work, catches mistakes, and improves permanently through self-reflection, self-criticism, and self-organizing memory. Use before starting work and after responding to the user.
Captures insights as markdown files, searches prior learnings, and promotes patterns to CLAUDE.md using tiered backends (local, qmd, agent-fs) for knowledge across projects.