/bruh
Say the last message again in plain language and shorter, like one person talking to another.
$ npx -y skills add bendrucker/claude --skill bruh --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/bruh
Context preview
The summary Claude sees to decide when to auto-load this skill.
Say the last message again in plain language and shorter, like one person talking to another.
SKILL.md
bruh.SKILL.mdname: bruh description: Say the last message again in plain language and shorter, like one person talking to another. argument-hint: "[<what lost me>]" disable-model-invocation: true
Bruh
Say that again in plain language, like one person talking to another. $ARGUMENTS names what lost me, where I said.
Shorter is the point. Cut the claims that were carrying nothing, rather than restating all of them in smaller words.
Start with what the message was responding to and what changed. A message loses me on the setup it skipped as often as on its words.
Name the thing that does the work in place of the abstraction over it, expand an acronym on first use, and give the mechanism where a metaphor stood in for one. Reuse the names this conversation and this repository already use, since a fresh synonym for something already named is often what lost me.
Where I pointed at a file or a PR body, that is the target, and `writing:no-diary` is the skill for it.
Write the rest of the conversation in your normal register.
My personal plugin marketplace for Claude Code, Anthropic's AI coding assistant.
Repo: bendrucker/claude
Other skills on bendrucker-claude.
cleye
Type-safe CLI argument parsing with cleye, the standard parser for this repo's Bun scripts. Use when writing or editing any script that takes arguments (flags,…
activity
Report real device usage from ActivityWatch. Covers per-app time, window titles, and active vs idle spans. Use when asked "what apps did I use", "how long was…
history
Report shell history from atuin's local capture. Covers what commands ran, when, where, and how they exited. Use when asked "what commands did I run", "what…
bun
Bun runtime patterns. Use when running bun commands, working with package.json/bun.lock, writing TypeScript scripts under Bun, or developing Claude Code…
agent-team
Orchestrating Claude Code agent teams. Use when creating teams, spawning teammates, assigning tasks, configuring teammate modes, or setting up team quality…

