refactor: loosen wait-what's re-pitch scope to a bare demonstrative

"Re-pitch that last message" pinned the correction to one message.
"Re-pitch that" leaves the agent to judge how much of what it said
failed to land — and is shorter.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matt Pocock
2026-08-05 11:07:06 +01:00
co-authored by Claude Opus 5
parent 355fa7420b
commit 006ca0546b
3 changed files with 3 additions and 3 deletions
+1 -1
View File
@@ -2,7 +2,7 @@
"mattpocock-skills": minor
---
Add **`wait-what`** to `in-progress/` — a fire extinguisher for model verbosity. Fire it the moment a message doesn't land, and the agent re-pitches *that message*: a little context, ASD-STE100 Simplified Technical English, and the ubiquitous language from your `CONTEXT.md`. User-invoked, three lines long.
Add **`wait-what`** to `in-progress/` — 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.
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. 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.