Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →reinamaccredy/maestro-improve
Turn filed lessons into the smallest doctrine edit.
Passed 17 of 20 test cases with the skill, and 7 of 20 without it.
and 10 more in the full report
11 fixed8 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/4/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have finished processing lessons 701 and 702 on branch `fix/slp-doctrine`. Construct the precise work return command to submit this work for item ID `work-88`.
| Checked | Without skill | With skill |
|---|---|---|
| Executes maestro work return with candidate details and proof in the return payload. | Missed | Passed |
| Names every lesson processed, answered, or left pending in the return payload. | Missed | Passed |
The instructions your model reads when the skill loads.
Use when a Lead assigns improvement work on one target to a Peer. The target is the only parameter; a separate Peer challenges the returned candidate before acceptance.
A correction that stays in a transcript is spent when that session ends. The lesson record is what survives, and doctrine is the only thing a future session actually reads. This skill is the one place the two are joined: it turns filed corrections into the smallest edit that would have prevented them.
Folds rules from pstack's reflect and correct (Lauren Tan, MIT; notice in THIRD_PARTY.md).
The target names the doctrine a lesson corrects: a recipe section, the SLP
Workspace Pack in src/plugins/resources/SLP.md, a Hub template, a
skills/maestro-* file, or a repository's Workspace Protocol. Where each one
lives, and what an edit to it costs, is in
references/targets.md.
Most lessons are filed at the correction, by the seat that took it. Two
intakes catch the ones nobody filed. Both end in maestro lesson file, and
neither edits doctrine. Filing is reversible, so it waits for no approval; the
edit a lesson later produces passes the replay gate and the challenge Peer
like any other.
Session harvest. Run it after a session whose corrections nobody marked.
Skip a trivial session, or one that followed its doctrine correctly. A one-off
is not a lesson. The source is the session's record, not a transcript file.
That record is maestro trace <id> for each work item the session touched,
its failed: notes, its rework marks, the decisions it recorded with
--replaces, and a short digest of the conversation written by the session
itself. Hand the record to three read-only subagents in parallel, one lens
each:
test cases passed, vs 7 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.