new-rule
AgentLoaded when the user invokes `/new-rule` or says "new rule" to add a rule from scratch (not tied to a correction).
Loaded when the user invokes `/learn-this`, says "learn this" / "remember this", or accepts your auto-detect offer to capture a correction.
Claude Code
$ npx -y skills add kakha13/think-like-me --agent claude-code
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
Loaded when the user invokes `/learn-this`, says "learn this" / "remember this", or accepts your auto-detect offer to capture a correction.
Extract these fields from the conversation:
Fill in the canonical block. `Don't` is often set here — it's literally what you just did wrong.
### <Short, searchable title> **When:** <domain> + <feature keywords> + <specific context> **Do:** <the fix, generalized> **Don't:** <what you reached for that was wrong> **Why:** <the mechanism> **Example:** <optional — include only if non-obvious>
Match to one of: `mobile`, `backend`, `ui`, `general`. If none fits, propose creating a new one (e.g. `devops`, `data`). Confirm the new category name with the user before writing.
Present in one message:
> **Draft rule → `rules/<category>.md`** > > [full block verbatim] > > Save? (`yes` / `edit` / `skip`)
A personal Claude Code skill that stores your curated engineering rules and actively consults them before Claude drafts code. Complements Claude Code's passive auto-memory: memory surfaces facts when relevant, rules shape the approach up front.
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard…