菜单
Update TLDR from GitHub and refresh installed agent hooks, skills, MCP, and rules. Triggers on /tldr-update, "tldr update", "update TLDR", or when the user asks to upgrade the TLDR install. Run via Bash: `tldr update` or `node <repo>/bin/install.js update`.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /tldr-commit. Auto-triggers when staging changes.
Compress natural language memory files (CLAUDE.md, todos, preferences) into TLDR format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /tldr-compress FILEPATH or "compress memory file"
Quick-reference card for all tldr modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /tldr-help, "tldr help", "what TLDR commands", "how do I use TLDR".
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /tldr-review. Auto-triggers when reviewing pull requests.
Verdict-first communication mode. Cuts token usage 60-75% by enforcing TLDR rules (1-sentence default, 3-word target, shape dispatch) while preserving full technical accuracy and truth priority. Supports levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "tldr mode", "talk TLDR", "verdict first", "no filler", or invokes /tldr. Auto-triggers on token efficiency or when TLDR style is requested.
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /tldr-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
| name | tldr-update |
| description | Update TLDR from GitHub and refresh installed agent hooks, skills, MCP, and rules. Triggers on /tldr-update, "tldr update", "update TLDR", or when the user asks to upgrade the TLDR install. Run via Bash: `tldr update` or `node <repo>/bin/install.js update`. |
When invoked, run the update CLI via Bash and report the result. Do not invent SHAs — quote the command output.
Pick the first that applies:
bin/install.js exists here:
node bin/install.js update $ARGUMENTS
tldr on PATH:
tldr update $ARGUMENTS
npx -y github:0p9b/TLDR -- update $ARGUMENTS
| Flag | Effect |
|---|---|
--check | Report available update; do not apply |
--dry-run | Show git + reinstall plan; write nothing |
--ref <tag|branch> | Update to that ref (alias: --tag) |
--force | Hard-reset local checkout to origin/<ref> if ff-only fails (never force-pushes) |
Tell the user: before SHA, after SHA, source path, and what the installer reinstalled. Exit code 0 = success / already up to date; 1 = failure.