wait-what
An agent skill by mattpocock, from mattpocock/skills. Tags: analysis, clarification, communication, re-pitch, workflow.
What it does
Stop. That last message did not land: re-pitch it.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add mattpocock/skills --skill wait-whatOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/productivity/wait-what ~/.claude/skills/wait-whatSafety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill only changes how the assistant replies: it asks for a re-pitch in Simplified Technical English and to use glossary terms. It does not ship scripts, touch files, call networks, or request credentials, so the blast radius is limited to conversation quality and wording.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No scripts or code are present; `SKILL.md` is plain text and `agents/openai.yaml` is config only. |
| Network access | 0 (none) | There are no URL fetches, API calls, uploads, or other remote data flows in the files provided. |
| Filesystem reach | 0 (none) | The skill does not read, write, or delete files; it only references `GLOSSARY.md` and `GLOSSARY-MAP.md` in text. |
| Secrets & credentials | 0 (none) | Nothing asks for tokens, passwords, `.env` files, keychains, or logged-in sessions. |
| Privilege & persistence | 0 (none) | There is no sudo, service registration, global install, shell/profile editing, or OS configuration change. |
| Instruction hijack surface | 0 (none) | The prompt content is stylistic guidance only; it does not tell the agent to ignore higher-priority rules, hide anything, or follow remote instructions. |
| Irreversible actions | 0 (none) | It does not send messages, deploy, publish, pay, book, merge, or delete anything; it only rephrases the assistant's reply. |
| Transparency | 0 (none) | All shipped files are readable text; there are no binaries, minified blobs, or runtime-decoded content. |
Before installing
- Confirm the referenced glossary files (`GLOSSARY.md` and, if present, `GLOSSARY-MAP.md`) exist in the repo so the wording guidance is usable.
Rated 2026-10-16 by an automated review of 2 files from the skill's repository.
Source
- Repository
- mattpocock/skills (all skills from this repository)
- Path
- skills/productivity/wait-what/SKILL.md
- Branch
- main
- Updated
- 2026-10-05
Related skills
- automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
- figure-it-out — Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.
- maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.
- principle-build-the-lever — Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
- principle-guard-the-context-window — Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
- recall — Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents).