1.9k ReScienceLab

archive Skill

将会议心得、调试方案和部署日志归档到 .archive/yyyy-mm-dd/ 目录,生成带可搜索标签的索引化 markdown 文档。适用于完成重要任务、解决棘手 bug、部署上线,或用户说"归档一下"时。维护 .archive/MEMORY.md 索引,实现跨会话知识复用。

安装方式:把技能目录放入 ~/.claude/skills/(Claude Code)或在 claude.ai 设置中启用;也可复制右侧安装命令一键添加。

查看源码

技能指令原文(SKILL.md)

Archive Skill

Capture, index, and reuse project knowledge across sessions.

When to Archive

  • After completing a significant task (deploy, migration, major feature)
  • After resolving a tricky debugging session
  • When the user says "archive this"
  • After any multi-step process with learnings worth preserving

When to Consult Archives

  • Before debugging infrastructure, deploy, or CI issues
  • Before repeating a process done in a past session
  • When encountering an error that may have been solved before

Search: grep -ri "keyword" .archive/
Index: .archive/MEMORY.md

Archive Workflow

  1. Read .archive/MEMORY.md — check for related existing archives
  2. Create .archive/YYYY-MM-DD/ directory if needed
  3. Write markdown file with YAML frontmatter (see references/TEMPLATE.md)
  4. Update .archive/MEMORY.md: add one-line entry under the right category
  5. If related archives exist, add related field in frontmatter

Lookup Workflow

  1. Read .archive/MEMORY.md to find relevant entries
  2. Read the specific archive file for detailed context
  3. Apply learnings to current task

Categories

  • infrastructure — AWS, ECS, IAM, networking, secrets, CloudWatch
  • release — TestFlight, versioning, Git Flow, CHANGELOG
  • debugging — Bug fixes, error resolution, gotchas
  • feature — Feature design, implementation notes
  • design — UI/UX, icons, visual design

Rules

  • .archive/ must be in .gitignore — local-only notes
  • Keep entries concise but reproducible
  • Focus on problems, fixes, and exact commands
  • Always update MEMORY.md after creating an archive
  • Use descriptive filenames (e.g., cloudwatch-logging.md not session.md)
  • Include YAML frontmatter with tags, category, and optional related

配合站内内容