wtf · everyinc — Claude Code skill: what it does, how to install
wtf explains an agent message, file, link, or passage in plain language. Use it when the meaning is unclear and you need to know what to decide or do next.
MIT 373 installs ★ 26,183 updated 2026-10-25
npx skills add EveryInc/compound-engineering-plugin --skill wtf -a claude-codeWhat wtf does
The skill explains the agent’s latest message or a target you provide: a file path, URL, pasted passage, or a pointer to part of the conversation. With no argument, it uses the latest message. It starts with the main point, then covers the current state, required decisions, next actions, and caveats.
wtf keeps file names, commands, and values that affect what you do next. It condenses the source instead of rewriting it and briefly defines technical terms when they matter. If the target is ambiguous, it asks one short question. Automatic invocation is disabled, so the user must call wtf.
What it helps with
- understand an agent’s latest message
- interpret a file or linked passage
- extract decisions and next actions
- clarify one part of a conversation
Example prompts for the agent
- Explain your last message in plain language and tell me what I need to do.
- Read
README.mdand explain its meaning, open decisions, and required actions. - Explain the migration section in this conversation.
How to install wtf
1Skills CLI (Vercel)
npx skills add EveryInc/compound-engineering-plugin --skill wtf -a claude-code2Manually: put the files in place
~/.claude/skills/wtf/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/wtf/
1Skills CLI (Vercel)
npx skills add EveryInc/compound-engineering-plugin --skill wtf -a codex2Manually: put the files in place
.agents/skills/wtf/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add EveryInc/compound-engineering-plugin --skill wtf -a cursor2Manually: put the files in place
.cursor/skills/wtf/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install EveryInc/compound-engineering-plugin skills/wtf2Manually: put the files in place
.github/skills/wtf/SKILL.md1Skills CLI (Vercel)
npx skills add EveryInc/compound-engineering-plugin --skill wtf -a gemini-cli2Platform CLI
gemini skills install https://github.com/EveryInc/compound-engineering-plugin --path skills/wtfManually: put the files in place
.devin/skills/wtf/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add EveryInc/compound-engineering-plugin --skill wtf -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about wtf
How do I install wtf in Claude Code?
Run npx skills add EveryInc/compound-engineering-plugin --skill wtf -a claude-code, then check ~/.claude/skills/wtf/SKILL.md.
What does the wtf skill do?
It turns an agent message, file, URL, pasted passage, or conversation pointer into a shorter explanation. The result covers the meaning, current state, actions, and caveats that affect the user.
Does wtf run automatically?
No. The user invokes it with wtf. An empty invocation targets the latest message; an argument can identify a file, URL, passage, or conversation section.
Source text
SKILL.md · MIT
--- name: wtf description: "Explain the last message, or a supplied file, link, or passage, in plain language a person follows on the first read. Use when the user invokes wtf because they did not follow something. Use ce-explain to investigate how or why code works, and ce-noslop to rewrite prose." disable-model-invocation: true argument-hint: "[file path, URL, pasted text, or which part lost you; blank for the last message]" --- # wtf The user did not follow something. Explain it the way you would to a smart colleague who was not in the room. **Done:** the user can say what the source means and what, if anything, they need to decide or do, without going back to the source. ## What to explain The text the user passed with the invocation decides the target: - Nothing passed: your most recent message. - A file path or a link: read it, then explain it. - A pasted passage: that passage. - A short pointer such as "the migration part" or "step 3": only that part of the conversation. If the target is still unclear, ask one short question instead of guessing. ## How to explain - Open with the point in one or two sentences: what this says and why the user should care. Write no preamble and no apology for the earlier wording. - Then say what it means for them: what happened, what state things are in, and anything they need to decide or do. - Explain the source; do not rewrite it. The explanation is shorter than the source because it leaves out whatever the user does not need in order to understand it or act on it. Do not walk a document section by section. - Use everyday words. When a technical term matters, keep it and say what it means once, in passing. Keep the exact file names, commands, and values the user will need to use. - Keep everything that changes what the user would do: failures, caveats, open questions, and requests. The explanation must not sound more positive or more certain than the source. - Add no claims the source does not make. If the source is vague or contradicts itself, say so. If re-reading your own message shows it was wrong, say that and correct it. - Plain does not mean childish. Do not force analogies, cheerlead, or talk down.
© EveryInc · MIT · EveryInc/compound-engineering-plugin
Similar skills
SKILL.md skills catalog →wtf by other authors comes first.