jiang-episode-quality-reviewlisted

# Jiang Episode Quality Review Use this for source PRs that publish or revise one public episode or interview: ```text episode/<source-slug> interview/<source-slug> ``` This is an editorial QA gate. It does not rewrite the source, create lens pages, or process new videos. It decides whether the public read is good enough to merge, and if not, it gives concrete revision instructions. ## Inputs - PR diff and PR body. - `content/lens/episodes/<source-slug>/read.json` - `content/sources/videos/<source-slug>/transcripts/v1/transcript.clean.md` - `content/sources/videos/<source-slug>/transcripts/v1/transcript.clean.jsonl` - `content/lens/evidence/videos/<source-slug>.semantic.json` when present. - Generated route data only when needed to verify route/build behavior. ## Review Pass 1. Identify source class, source slug, video ID, route, and changed files. 2. Read the public read JSON. 3. Sample the transcript around every chapter/section range and every marked phrase. Read enough surrounding transcript to judge whether the read carries the source's actual pressure. 4. Inspect semantic artifacts for signature moments, real questions, chronology, and notable speaker/interviewer pressure. 5. Compare the draft against the corpus anchor: curated strong episode reads, existing lens pages, topic aliases, and prior signature moments. This catches reads that are technically valid but weaker than the project's known bar. 6. Run validation when the PR looks close to pass: