benbrown/peltier.io
2
1
Fork 0
mirror of https://github.com/bdbrown4/peltier.io.git synced 2026-11-07 10:58:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #23 from bdbrown4/skill/explain-parity

Browse Source 
skill: attempt mode points at explain for the next hypothesis
This commit is contained in:
benbrown
2026-07-20 10:11:40 -04:00
committed by GitHub
parent c42a46cc92 3946438fd6
commit ffc6674e13
2 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/skills/peltier/references/attempt.md
+12
View File
@@ -84,6 +84,18 @@ dollars, and/or latency percentiles — every figure with its CI, workload, and
methodology printed inline. It flags any row that was not accepted, so a methodology printed inline. It flags any row that was not accepted, so a
rejected attempt cannot be laundered into a dollar figure. rejected attempt cannot be laundered into a dollar figure.
## Explain — read this before your next hypothesis
just explain <run-id>
Advisory diagnosis of the row you just wrote (SPEC §3.7): *why* it won or
lost, derived solely from the ledger — deterministic, never on the accept
path, with everything beyond the machine record prefixed `inference:`. Run it
on every rejection before forming the next hypothesis: "real improvement,
below the ship bar", "indistinguishable from no change", and "a measured
regression" are three different next moves, and the verdict string alone does
not tell you which one you got. Quote the record, not the inferences.
## Unattended ## Unattended
just agent-attempt <target> <run-id> just agent-attempt <target> <run-id>
.claude/skills/peltier/references/attempt.md
+12
View File
@@ -84,6 +84,18 @@ dollars, and/or latency percentiles — every figure with its CI, workload, and
methodology printed inline. It flags any row that was not accepted, so a methodology printed inline. It flags any row that was not accepted, so a
rejected attempt cannot be laundered into a dollar figure. rejected attempt cannot be laundered into a dollar figure.
## Explain — read this before your next hypothesis
just explain <run-id>
Advisory diagnosis of the row you just wrote (SPEC §3.7): *why* it won or
lost, derived solely from the ledger — deterministic, never on the accept
path, with everything beyond the machine record prefixed `inference:`. Run it
on every rejection before forming the next hypothesis: "real improvement,
below the ship bar", "indistinguishable from no change", and "a measured
regression" are three different next moves, and the verdict string alone does
not tell you which one you got. Quote the record, not the inferences.
## Unattended ## Unattended
just agent-attempt <target> <run-id> just agent-attempt <target> <run-id>