last30days-skill

Files

T

Matt Van Horn 499074b564 fix(youtube): pass full transcripts to LLM instead of truncating to 200 chars

TRANSCRIPT_MAX_WORDS raised from 500 to 5000 so the LLM gets the full
content of most videos (up to ~25 minutes). Removed the second 200-char
truncation in render.py that was reducing transcripts to a single sentence
before the judge agent ever saw them.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-23 17:28:01 -07:00

lib

fix(youtube): pass full transcripts to LLM instead of truncating to 200 chars

2026-03-23 17:28:01 -07:00

briefing.py

feat(open): Port web search backends, persistence layer, and env merge from openclaw

2026-02-14 23:35:44 -08:00

evaluate_search_quality.py

Harden local search evaluation harness

2026-03-14 00:38:43 -07:00

evaluate-synthesis.py

feat(quality): GOAT synthesis improvements - hybrid cross-source linking, YouTube synonyms, human-readable xref tags