/wait-what
Stop — that last message did not land. Re-pitch it. Use when the user says "wait, what", "I don't follow", "say that again", or otherwise signals that an explanation missed.
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill wait-what --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
/wait-what
Context preview
The summary Claude sees to decide when to auto-load this skill.
Stop — that last message did not land. Re-pitch it. Use when the user says "wait, what", "I don't follow", "say that again", or otherwise signals that an explanation missed.
SKILL.md
wait-what.SKILL.mdname: wait-what description: Stop — that last message did not land. Re-pitch it. Use when the user says "wait, what", "I don't follow", "say that again", or otherwise signals that an explanation missed. disable-model-invocation: true
Wait, what
That last message did not land. Do not repeat it louder, and do not apologize — restate it.
Re-pitch it:
- **Lead with the context** the explanation assumed. One or two sentences on where we are and what the message was answering. The gap is usually a missing frame, not a missing word.
- **Write it in ISO 24495-1 English.** Short sentences, active voice, direct address, and a common word wherever jargon appeared. This is conversation with the user, so ISO 24495-1 governs it — not the ASD-STE100 register that maintainer docs use.
- **Use the project's ubiquitous language.** Read `CONTEXT.md` at the repository root (or the per-context `CONTEXT.md` beside the relevant source, when the project keeps a `CONTEXT-MAP.md`) and name domain things the way the project names them. If no glossary exists, use the names already in the code.
Re-pitch the same claim. Softening it, hedging it, or swapping it for an easier one answers a question nobody asked.
Formerly known as the ODIN Claude Plugin. The repo URL stays the same; the brand has matured.
Repo: OutlineDriven/odin-claude-plugin
Other skills on odin.
- /ai-collab-protocols
Surface in-task AI collaboration protocols one tactic at a time, replacing ambiguous references with durable, recoverable handles.
Open skill - /askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via `/askme`.
Open skill - /ast-grep
Run code analysis and refactoring with ast-grep. Use when doing AST-based modifications, structural search, linting across code shape, or replacing regex-fragile transformations.
Open skill - /atomic-issues-prs
Publish a change-set as atomic GitHub issues or PRs. Use when the user says "atomic PRs" or wants one issue/PR per logical change.
Open skill - /audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
Open skill - /autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
Open skill