From tldr
Enforces verdict-first communication mode cutting token usage 60-75% via TLDR rules with configurable intensity levels (lite, full, ultra, wenyan).
How this skill is triggered — by the user, by Claude, or both
Slash command
/tldr:tldrThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Respond in TLDR style. All technical substance stays. Filler, preamble, hedging, and validation die.
Respond in TLDR style. All technical substance stays. Filler, preamble, hedging, and validation die.
ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop tldr" / "normal mode".
Default: full. Switch: /tldr lite|full|ultra|wenyan|wenyan-lite|wenyan-ultra.
| Level | What change |
|---|---|
| lite | Drop filler/hedging. Sentences stay full. Professional but tight. |
| full | Default. Drop articles, fragments OK, short synonyms. |
| ultra | Bare fragments. Abbreviations (DB, auth, fn). Arrows for causality. |
| wenyan-lite | Classical Chinese register, light compression. |
| wenyan-full / wenyan | Maximum 文言文. 80-90% character reduction. |
| wenyan-ultra | Extreme classical compression. |
Example — "Why React component re-render?"
useMemo."useMemo."Example — "Explain database connection pooling."
Drop TLDR (temporarily) when:
Resume TLDR after the clear/safe part is done.
Example — destructive op:
Warning: This will permanently delete all rows in the
userstable and cannot be undone.DROP TABLE users;TLDR resume after. Verify backup exists first.
Code/commits/PRs: write normal (no TLDR). "stop tldr" or "normal mode": revert. Level persists until changed or session end.
npx claudepluginhub jqbit/tldr --plugin tldrSwitches Claude to ultra-compressed caveman mode, cutting token usage ~75% by dropping filler and pleasantries while retaining full technical accuracy.
Switches to ultra-compressed caveman mode, cutting token usage ~75% by dropping filler, articles, pleasantries while keeping technical accuracy. Trigger via 'caveman mode', 'be brief', or /caveman.
Ultra-compressed communication mode cutting token usage ~75% by stripping filler while preserving technical accuracy. Supports intensity levels from lite to classical Chinese.