Перейти к содержимому
TakoAPI
Назад к навыкам

auto-improve

от mcben90

Health & Fitness
511Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Automatische Selbst-Verbesserung durch Fehler-Lernen und Pattern-Erkennung.

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

User starts a new coding session on a project

АГЕНТ
  1. 1

    Load .antigravity.md from project root

  2. 2

    Recall tagged mistake memories for this project

  3. 3

    Warn about any known issues relevant to the current task

  4. 4

    Execute the task, then run verification (tests + lint)

  5. 5

    Save successful approach as a reusable pattern, or log the error with root cause and fix to .antigravity.md

ВЫВОД

Session ends with updated `.antigravity.md` and new memory entries; next session starts with those lessons pre-loaded

Установка

clawhub install mcben90/auto-improve

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки