From claude-code-starter
Records lessons from pitfalls, technical decisions, and project rules into CLAUDE.md for persistent knowledge. Use after debugging to prevent repeats or logging choices.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-code-starter:learnThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
把这次踩的坑或做的决策记录到 CLAUDE.md 中,防止下次再犯。
把这次踩的坑或做的决策记录到 CLAUDE.md 中,防止下次再犯。
如果用户已经说了,直接分析。否则问:
你想记录什么?
- 刚踩了个坑,想防止下次再犯
- 做了个技术决策,想记录原因
- 发现了项目的特殊规则,想让 Claude 记住
根据类型收集信息:
踩坑记录:
技术决策:
项目规则:
用精确简洁的语言写一条记录:
踩坑格式:
- [现象描述] — [正确做法]
例:uv sync 会删除未在 pyproject.toml 中声明的包 — 运行前后对比 uv pip list
决策格式:
- 选择 [方案] 而不是 [备选] — 原因:[理由];否决 [备选] 因为 [理由]
例:选择 SQLite 而不是 PostgreSQL — 原因:单用户项目不需要并发;否决 PostgreSQL 因为运维成本高
读取当前 CLAUDE.md,将新条目追加到对应区块:
写入前展示给用户确认:
准备在 CLAUDE.md 的「已知陷阱」中添加:
- [新条目内容]
确认写入?
用户确认后写入文件。
已更新 CLAUDE.md。下次 Claude 会自动遵守这条规则。
npx claudepluginhub lightpointventures/claude-code-starterExtracts learnings from the current conversation and appends them to the project's CLAUDE.md as generalized rules. Captures non-obvious solutions and workarounds.
Guides identifying learnings, gotchas, architectural decisions for documentation in CLAUDE.md. Assesses significance, classifies sections, skips trivial changes.
Records project-specific learnings on gotchas, bugs, and unexpected behaviors into LEARNINGS.md via ctx CLI. Prompts for context, lesson, and application; checks for novelty before adding.