auto-improve
由 mcben90 提供
Health & Fitness简介
Automatische Selbst-Verbesserung durch Fehler-Lernen und Pattern-Erkennung.
描述
该技能的功能
Auto-improve runs a persistent learning loop across sessions, loading past mistakes and project context at session start, then saving patterns or logging errors after each task. It maintains a `.antigravity.md` file per project to carry forward specific lessons. Metrics track whether repeated mistakes and verification failures decrease over time.
Unlike session-scoped context, this persists lessons to disk and reloads them automatically, so the agent doesn't repeat documented mistakes.
何时使用
- Avoiding the same coding mistake in a new session
- Getting a warning before touching code that caused past bugs
- Building a project-specific pattern library from successful approaches
- Reviewing what went wrong in a previous refactor before starting a new one
- Tracking whether first-attempt success rate improves over weeks
示例工作流
User starts a new coding session on a project
- 1
Load
.antigravity.mdfrom project root - 2
Recall tagged mistake memories for this project
- 3
Warn about any known issues relevant to the current task
- 4
Execute the task, then run verification (tests + lint)
- 5
Save successful approach as a reusable pattern, or log the error with root cause and fix to
.antigravity.md
Session ends with updated `.antigravity.md` and new memory entries; next session starts with those lessons pre-loaded
安装
clawhub install mcben90/auto-improve运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。