A ten minute voice ramble transfers more context than any prompt a person
would type, and models reconstruct rambles well. The failure is
downstream and invisible: the model fills every gap in the ramble
confidently. "The usual model" silently becomes a specific model. "The
standard size" becomes a specific viewport. A position the user reversed
mid-ramble survives as fact. None of this registers as uncertainty from
the inside, so none of it ever becomes a clarifying question. The model
then acts on a misreading it fully believes, and the user discovers it an
hour of generated work later.
This skill is the fix: before acting on any ramble, produce an echo, a
short structured audit of everything absorbed, with the model's own
additions quarantined from the user's words. The user corrects three
lines instead of debugging a built artifact.
Asking clarifying questions is good, and the interview below does it.
But questions alone cannot secure a ramble, for two structural reasons:
model believes.** A clarifying question requires felt uncertainty, and
confident misreadings feel like knowledge. The echo forces every
inference and gap-fill into the open whether or not it felt uncertain.
facts and half-decisions. Even good questions probe three or four; the
rest of the model's understanding goes unverified into action. The
echo inventories the entire transfer, and it works by recognition, not
recall: the user reads and spots what is wrong, which is far cheaper
than producing answers, and ramblers often do not know their answer
until they see the wrong guess written down.
fragments, until the echo is approved. Reconstruct first.
section, apart from the user's own content. Never present a guess in
the user's voice.
flip. Never silently average or pick.
and restarts are resolved silently from context. Keep the user's own
vocabulary and project names.
saved unprompted.
restarts, filler, and mid-message reversals ("actually no, scrap that")
recognition, sorry for any typos", "dictating this")
while keeping their exact words
One structured reply. Dense, scannable, and short: the user should find
and fix an error in seconds. Full template with a worked example in
references/echo-format.md.
achieve. Often this differs from what they said first; that is fine.
list. Mark anything they called a top priority.
parked tangents (one line each).
(strongly implied but never stated) and "Guessed" (gaps you filled).
Tell the user to correct these first.
Compression rules, non-negotiable:
own content by definition; only the model's additions get called out.
or it is bloat.
"standard size", "soon": each lands in Open or Guessed, never absorbed
into a locked item as if it were specified.
Close by inviting corrections and offering the interview.
Follow-up questions have their place: after the audit, not instead of
it. Only if the user accepts the offer, or asked to be interviewed up
front.
Not needed for dictation tools, where the whole ramble arrives as one
message. Use it when the user invokes the skill before rambling and then
adds thoughts across several messages, possibly over a long stretch.
'done' when you want the echo.")
("Listening."). Vary it slightly so it does not feel robotic.
sentences, then return to listening.
any clear equivalent, then deliver the echo.
After the user approves the echo, offer exactly three options:
docs/rambles/YYYY-MM-DD-<topic>.mdThe approved brief then governs the rest of the session: honor its
decisions and constraints without re-asking.