David/dotfiles
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

session 2026-07-06 evening: skill-harvest register (graduate-chamber-source reinforced; completion-is-a-tripwire watch-item)

Browse Source
This commit is contained in:
David F Glidden
2026-07-06 21:55:49 +02:00
parent 8462cd6fb1
commit 5bed529cb7
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/skill-harvest-register.md
+5
View File
@@ -351,3 +351,8 @@ The single place proposed skills live so they don't evaporate between sessions.
### Harvest 2026-07-06 (pm — Olson pdftotext-scan graduation)
- **`/graduate-chamber-source` REINFORCED** (PROPOSED 2026-06-26; the `/convert-*` family the runbook plans). Today's Olson run is the **V-SCAN pdftotext variant** of the pipeline — a distinct empirical branch from the Levi OCR path: (1) `normalize_ocr.py --pdftotext` (form-feed + case-agnostic furniture + reflow; guard-verified) → (2) scan-verified + fail-loud-LOGGED `ocr_defects` correction pass (verify eccentricities/names vs the source PDF via `Read pages=N`) → (3) `insert_chapter_headings` (needs the occurrence-index extension for repeated section titles) → (4) frontmatter → (5) gates → (6) graduate + archive + attest. The skill, when built, should carry BOTH branches (born-digital/EPUB, OCR-scan) + the branch-selection heuristic. No new autonomous change — reinforcing the existing proposal. Also surfaced (build tasks, not skills): fix Phase-1 in-page-rejoin heading-glue in normalize_ocr; add occurrence-index to insert_chapter_headings.
### Harvest 2026-07-06 (evening — Olson graduation completed + tool-integration audit)
- **`/graduate-chamber-source` (proposed 2026-06-26) — REINFORCED, hardest run yet.** Today's Olson graduation exercised the full pipeline on the hardest V-SCAN case so far: heavy curatorial structure (73 headings), occurrence-indexed repeated titles, glued/wrapped/ALL-CAPS heads, dropped running-head chapter titles, a blank-page scan-noise region, source_verified. The empirical spec is now very rich; still PROPOSED (build-on-need), but today is a strong nudge it's ripe.
- **`completion-is-a-tripwire` → Symmetria §3 flag WATCH-ITEM (NOT yet proposed).** Recorded as `feedback-completion-is-a-tripwire.md` (steward-authorized 2026-07-06). Per the governed pattern (propose → watch → promote-on-recurrence), it stays a feedback memory until it recurs; then it earns a §3 flag ("the *feeling* of done is the cue to verify the tail"). Do not mint the flag from one session.
- **No CLAUDE.md change (freshness check).** chamber-library CLAUDE.md is pointer-style; `insert_chapter_headings` already in the fleet list; the new `localized_scan_noise` discipline lives in `graduation-spec.yaml` (which CLAUDE.md points to for conventions) — adding it to the CLAUDE.md disciplines section would be belt-and-suspenders bloat. Deliberately not proposed (steward's anti-bloat stance, same session).