Merge pull request #760 from mattpocock/docs-wait-what-dead-prose

docs: drop the fire-extinguisher metaphor from wait-what

.changeset/wait-what.md

@@ -2,8 +2,8 @@
 "mattpocock-skills": minor
 ---
 
-Add **`wait-what`** — a fire extinguisher for model verbosity. Fire it the moment a message doesn't land, and the agent re-pitches it: a little context, ASD-STE100 Simplified Technical English, and the ubiquitous language from your `CONTEXT.md`. User-invoked, three lines long.
+Add **`wait-what`** — a one-word corrective for model verbosity. Type it the moment a message doesn't land, and the agent re-pitches it: a little context, ASD-STE100 Simplified Technical English, and the ubiquitous language from your `CONTEXT.md`. User-invoked, three lines long.
 
 The mechanism is the name. Concision skills fail by growing — a 400-line skill still leaves the model verbose — so this one is a single precise leading word and nothing else. Names that describe the *output* (`/tldr`, `/no-fluff`) make the model clip words and lose you further; naming the *listener's* state asks for both halves at once, fewer words **and** the context you were missing. It also reuses the leading words already in your global `CLAUDE.md`, so the skill, `CLAUDE.md` and every `CONTEXT.md` reach for the same tokens.
 
-It's the extinguisher, not the sprinkler. The cure for jargon is a shared language built upfront with `/grill-with-docs`; this is the in-the-moment corrective for when you don't have one yet.
+It repairs one message; it doesn't prevent the next one. The cure for jargon is a shared language built upfront with `/grill-with-docs`; this is what you reach for when you don't have one yet.

docs/productivity/wait-what.md

@@ -1,36 +1,36 @@
 ## What it does
 
-`wait-what` is the fire extinguisher for a message that didn't land. You fire it the moment you lose the thread, and the agent re-pitches what it just said: a little of the context you were missing, plain English, and the vocabulary from your project's `CONTEXT.md`.
+`wait-what` is what you type when a message didn't land. The agent then re-pitches what it just said. It adds the context you were missing, writes in plain English, and uses the vocabulary from your project's `CONTEXT.md`.
 
-It is three lines long, and that is the design rather than an unfinished draft. Skills that fight verbosity fail by growing — a four-hundred-line concision skill still leaves the model verbose, because the model reads the volume, not the plea. This one carries a single precise leading word and nothing else.
+The skill is three lines long. That is the design, not an unfinished draft. Skills that fight verbosity fail by growing: a four-hundred-line concision skill still leaves the model verbose, because the model reads the volume, not the plea. This one carries a single precise leading word and nothing else.
 
 ## When to reach for it
 
-You invoke this by typing `/wait-what` — the agent won't reach for it on its own, and it shouldn't: only you know when you stopped following.
+You invoke it by typing `/wait-what`. The agent will not reach for it on its own, and it shouldn't. Only you know when you stopped following.
 
-Reach for it the second you notice you're skimming — the agent has drifted into jargon it invented, stacked five acronyms, or explained a decision whose premise you never saw. It's a one-shot corrective on the conversation you're already in. To stop the jargon arriving in the first place, use [grill-with-docs](https://aihero.dev/skills-grill-with-docs) instead, which builds the shared language upfront.
+Use it the second you notice you're skimming. The agent has drifted into jargon it invented, stacked five acronyms, or explained a decision whose premise you never saw. It fixes the conversation you're already in. To stop the jargon arriving at all, use [grill-with-docs](https://aihero.dev/skills-grill-with-docs), which builds the shared language upfront.
 
 ## The name is the mechanism
 
-The leading word is **wait**. Not "be concise" — an instruction about the agent's output, which the model satisfies by clipping words and losing you further. **Wait** is about *your* state: it says comprehension failed here. An agent that hears "be brief" writes telegrams. An agent that hears "wait, you lost me" backs up and explains.
+The leading word is **wait**. "Be concise" is an instruction about the agent's output, and the model obeys it by clipping words and losing you further. **Wait** is about *your* state. It says comprehension failed here. An agent that hears "be brief" writes telegrams. An agent that hears "wait, you lost me" backs up and explains.
 
-That distinction is the whole skill. Every popular fix for verbosity — `/tldr`, `/no-fluff`, `/talk-normal` — names the *output*, so the model over-corrects into a caveman register that's shorter and no clearer. Naming the *listener* asks for both halves at once: fewer words **and** the context you were missing.
+That difference is the whole skill. Every popular fix for verbosity names the *output*: `/tldr`, `/no-fluff`, `/talk-normal`. The model over-corrects into a caveman register that is shorter and no clearer. Naming the *listener* asks for both halves at once: fewer words **and** the context you were missing.
 
-The re-pitch is deliberately vague about its own scope. It says re-pitch **that**, not "that last message", because what lost you is usually bigger than one paragraph — the agent decides how far back to go.
+The skill says re-pitch **that**, not "that last message". What lost you is usually bigger than one paragraph, so the agent decides how far back to go.
 
 ## It plugs into the language you already have
 
-The body reuses the leading words already sitting in your global `CLAUDE.md` and your project's `CONTEXT.md`: ASD-STE100 Simplified Technical English for the register, ubiquitous language for the nouns. Skill, `CLAUDE.md` and `CONTEXT.md` reach for the same tokens, so firing it isn't a new instruction — it's a reminder of one the agent already agreed to.
+The body reuses the leading words already in your global `CLAUDE.md` and your project's `CONTEXT.md`. ASD-STE100 Simplified Technical English sets the register. The ubiquitous language supplies the nouns. The skill, `CLAUDE.md` and `CONTEXT.md` reach for the same tokens, so invoking it is not a new instruction. It is a reminder of one the agent already agreed to.
 
-If you have no `CONTEXT.md`, it still works; you just lose the domain-vocabulary half.
+If you have no `CONTEXT.md`, the skill still works. You lose only the domain-vocabulary half.
 
 ## It's working if
 
 - The re-pitch is **shorter and clearer**, not shorter and blunter.
-- It adds the premise you were missing rather than just deleting words.
-- Project nouns replace invented ones — the terms in your `CONTEXT.md` come back.
-- You can fire it twice in a row without it degrading into terseness.
+- It adds the premise you were missing, instead of only deleting words.
+- Project nouns replace invented ones. The terms in your `CONTEXT.md` come back.
+- You can use it twice in a row, and it does not degrade into terseness.
 
 ## Where it fits
 
-`wait-what` is a reach-for-it-anytime standalone — it sits inside whatever conversation you're already having, in any skill, at any point. It's the extinguisher; [grill-with-docs](https://aihero.dev/skills-grill-with-docs) is the sprinkler system, because a shared language agreed upfront is the real cure for jargon, and [domain-modeling](https://aihero.dev/skills-domain-modeling) is what you reach for when the *words themselves* are the problem rather than one bad message. When you're unsure which skill fits the moment, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
+You can use `wait-what` at any point, in any conversation, inside any other skill. It repairs one message after the fact. The real cure is a shared language agreed upfront, and that is [grill-with-docs](https://aihero.dev/skills-grill-with-docs): a grilling session that runs [domain-modeling](https://aihero.dev/skills-domain-modeling) as it goes, so the words you both use land in your `CONTEXT.md`. If you're unsure which skill fits the moment, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.

skills/engineering/ask-matt/SKILL.md

@@ -79,7 +79,7 @@ Off the main flow entirely.
 - **`/research`** — delegate reading legwork to a **background agent**: it investigates a question against **primary sources**, then leaves a cited Markdown file in the repo. Keep working while it reads. The file it produces is something to take *into* the main flow at `/grill-with-docs` — research feeds the thinking, it doesn't replace it.
 - **`/to-questionnaire`** — when the thing blocking you isn't in your head or the codebase but in **someone else's**, this writes them a questionnaire to fill in. It's the inverse of `/grill-me`: instead of interviewing you about the subject, it interviews you about the **send** — who it's going to, what you need back — and aims the questions at the gap. What comes back is material for `/grill-with-docs` or `/to-spec`.
 - **`/wizard`** — for the steps only a **human** can take: clicking through a third-party dashboard, running a one-off migration, moving the project from state A to state B. It generates an interactive bash script that opens each URL, captures each value, and writes it into `.env` and GitHub secrets — so the procedure stops being something you re-explain to an agent every time. If the agent could just do it itself, it should; reach for this only where a human is genuinely in the loop.
-- **`/wait-what`** — the fire extinguisher for a message that didn't land. Fire it mid-conversation, inside any other skill, and the agent re-pitches what it just said with the context you were missing, in plain English, using the `CONTEXT.md` vocabulary. It's the in-the-moment corrective; `/grill-with-docs` and `/domain-modeling` are the upfront cure, because a shared language agreed early is what stops the jargon arriving at all.
+- **`/wait-what`** — the corrective for a message that didn't land. Use it mid-conversation, inside any other skill, and the agent re-pitches what it just said with the context you were missing, in plain English, using the `CONTEXT.md` vocabulary. It works after the fact; `/grill-with-docs` is the upfront cure, because a shared language agreed early is what stops the jargon arriving at all.
 - **`/teach`** — learn a concept over multiple sessions, using the current directory as a stateful workspace.
 - **`/writing-for-agents`** — reference for writing documents agents consume: skills, AGENTS.md, pointed-at docs.