skill: five lessons filed by position, now in the numbered base - #3268
Merged
Merged
Conversation
Five `###` sub-headings were appended with `cat >> SKILL.md` and landed under whichever numbered section happened to be last at that moment -- two under 571 (`X of Y` where X can exceed Y) and three under 572 (a guard that cannot run), none of them on those sections' topics. They were uncounted by `tri skill claims` and unvalidated by `tri skill check`. Promoted to 572-577 in FILE ORDER, which required renumbering the previous 572 to 574 so the numbers still ascend with position. Nothing references it: the `572` hits elsewhere in the tree are Wave Loop reports, a different sequence. This also corrects an overstatement I published last pass. I wrote that EVERY lesson I appended was misplaced and implied about fifteen. Measured: 140 `###` sub-headings exist and FIVE are misplaced. The rest are genuine sub-points, written inside their parent section and on its topic, across 63 sections -- the convention working as intended. The claim I got wrong was about my own working habits, which is the kind I have least reason to check. Verified: heading TEXTS 676 = 676, zero missing, zero invented; `##` 536 -> 541 and `###` 140 -> 135, exactly the five moved; six lines changed. `skill check` exit 0, `claims` 537, `refs` exit 0, 780 tests. Refs #3265 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
gHashTag
enabled auto-merge (squash)
September 5, 2026 09:50
Contributor
|
📓 NotebookLM Notebook linked to this PR
This notebook contains session context, decisions, and artifacts for this work. |
Contributor
Contributor
|
📓 NotebookLM Notebook linked to this PR
This notebook contains session context, decisions, and artifacts for this work. |
Contributor
PR DashboardGenerated at: 2026-09-05 10:17:48 UTC
Summary
Seal Status
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Finishes finding 3 of #3265 — and corrects it.
What was wrong
Five
###sub-headings were appended withcat >> SKILL.md, so each landedunder whichever numbered section happened to be last at that moment:
X of Ywhere X can exceed YThey were uncounted by
tri skill claimsand unvalidated bytri skill check,and a reader following a cross-reference to §572 found three unrelated lessons
under it.
Promoted to 572–577 in file order, which required renumbering the previous
§572 to 574 so numbers still ascend with position. Nothing references it — the
other
572hits in the tree are Wave Loop reports, a different sequence.Correcting what I published last pass
I wrote that "every lesson I appended over the last several passes" was
misplaced, and implied about fifteen.
140
###sub-headings exist. Five are misplaced.The rest are genuine sub-points, written inside their parent section and on its
topic — "The prototype was right for the wrong reason" under §567 (The
prototype gave the right number…), "The half of a fix is not the fix" under
§571 (
X of Y…) — the convention working as intended across 63 sections.So the consequence is real but four times smaller than I stated. The claim I
got wrong was about my own working habits, which is the kind I have least
reason to check and most reason to. Same class as #3253.
Verification
##count###counttri skill checktri skill claimstri skill refscargo test -p tri --bin triThe
##/###deltas are equal and opposite, which is what makes the promotionvisibly a move rather than an addition.
Refs #3265