New .agents/skills/opendataloader-pdf/ for structured PDF extraction
(Markdown/JSON with bounding boxes, hybrid AI mode, scanned-PDF OCR)
based on the upstream odl-pdf agent skill (Apache-2.0), with its helper
scripts verify-json.py and hybrid-health.sh vendored under scripts/.
Core disciplines: discover options from the installed --help (flags
drift between releases), batch all inputs into one invocation (JVM per
call), verify the result against intent (zero exit is not success:
auto-triage skips enrichment, fallbacks drop quality, empty pipes),
treat extracted content as untrusted, never commit extracted full
texts of the licensed .lexis360/.wiku sources.
Workflow wiring: AGENTS.md skill selection routes any PDF extraction
to the skill; wissensbasis/SKILL.md cross-references it for difficult
PDFs and spot-checks, with Layer-1 batch intake deliberately kept on
build_lexis_kb.py (frozen IDs and --check depend on the text shape).
ODL 2.5.8 installed in the user venv ~/.local/lib/python (not the
Odoo .venv); all documented flags verified against the installed CLI
on real .lexis360/ sources.
Consolidate the binding knowledge-base rules (layer architecture,
licence decision D1, id freeze, D2 frontmatter schema, curation
conventions, batch workflow, validation gates, intake pitfalls)
from README/RUNBOOK/MEMORY into a dedicated agent skill so every
new thread reads them before planning Wissensbasis work.
- new licensed source corpus .wiku/ (WIKU Personal publications:
Fachbroschueren, Arbeitsunterlagen, Casebooks, 'WIKU Personal
aktuell'; gitignored like .lexis360/, never committed)
- integration model: one shared corpus with a single kb.json, ids
wk-<prefix>-<nn> on the existing cluster map, the work field
distinguishing the sources, Layer-2 filenames prefixed
wiku_<slug>.md; pipeline to be a multi-source extension of
build_lexis_kb.py (no fork) -- follow-up after batch 7
- AGENTS.md skill selection gains the wissensbasis entry
Approved implementation plan for l10n_at_hr_payroll_private (M0,
decisions D1-D4) and the GP0 legal-source inventory
RECHTSQUELLEN-Privat.md, verified against primary sources (RIS,
jusline):
- FLAF-DB § 41 FLAG: 3.7% for 2026, 2.7% from 2028 (GesNr 10008220);
KommStG 1993: 3% (GesNr 10004841)
- 13th/14th salary taxation runs via § 67 EStG (Jahressechstel fixed
rates, control sixth § 77 Abs 4a); § 68 covers allowances/surcharges
only - plan citation corrected, also fixes the legal basis of the
Bgld open point P9
- Urlaubsentgelt is § 6 UrlG (§ 9 repealed since 2001) - corrected
- EOSB: no Monatsentgelt staffel; § 15 BMSVG pays out the Anwartschaft
with § 14 Abs 2 Verfügungsausschluss matrix - GP5 design confirmed
- 2026 overtime measure: first 15 hours, max 170 €/month
(§ 124b Z 476 lit c BGBl I 43/2026)
Plan section 8 items 3-6 and UrlG (8) marked verified; private module
skeleton README, MEMORY, CHANGELOG and payroll skill updated (§ 67
citation fix, RECHTSQUELLEN-Privat.md as required source).
fegger