Stop — that last message did not land. Re-pitch it in plain language.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add lttr/claude-marketplace --skill wait-what --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Wait What?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/lttr-wait-what)More formats (shields.io, HTML) on the badges page.
---
name: wait-what
description: Stop — that last message did not land. Re-pitch it in plain language.
disable-model-invocation: true
---
Wait — I don't follow where you've got to. That message didn't land. Re-pitch it.
- **Lead with the context I'm missing.** What problem this solves, and where it sits in the work we're doing.
- **Write in ASD-STE100 Simplified Technical English.** Short sentences, one idea each, active voice, plain approved words. Expand every acronym on first use.
- **Use the project's canonical terms.** If `GLOSSARY.md` exists (or `CONTEXT-MAP.md` points to per-area glossaries), take the terms from there and use them exactly. Otherwise use the terms already established in this conversation and in the codebase — no new coinages mid-explanation.
- **Explain the idea before any code.** Show a snippet only when it is the shortest way to say the thing, and keep it to the few lines that carry the point.
- **Change the framing, don't repeat it louder.** The first pitch already failed; a longer version of it fails too. Try a different angle — a concrete scenario, a before/after, a comparison to something already agreed.
Then stop and let me respond. Don't continue the work until I say the re-pitch landed.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.