メニュー
Use this skill when importing synced Jiang Lens source artifacts, resolving YouTube metadata dates, creating canonical source transcripts, and preparing transcript packets for semantic agents.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | jiang-source-ingest |
| description | Use this skill when importing synced Jiang Lens source artifacts, resolving YouTube metadata dates, creating canonical source transcripts, and preparing transcript packets for semantic agents. |
Use this for the mechanical path from committed raw source artifacts into canonical source state.
This skill does not write public episode prose, public lens docs, glossary canon, or promotion records.
Treat time as part of provenance. A claim is not just "what Jiang says"; it is what a dated artifact records him saying, in a specific context, with a stable source ref.
Committed Colab text artifacts:
content/sources/raw/youtube/<channel>/<video-id>/
metadata.youtube.json
dump.json
grouped.json
transcription.json
content/sources/raw/youtube/Interviews/<host-channel-id>/<video-id>/
metadata.youtube.json
dump.json
grouped.json
transcription.json
If artifacts are still only in Google Drive or Colab, use colab-video-pipeline first, then commit the synced text artifacts. ops/staging/ is only a local disposable cache, not the worker source of truth.
First check the source-processing policy:
content/workflow/tasks/source-processing-policy.json
If the video ID is marked duplicate, blocked, skip, or archive-only,
do not import it as a new source. The raw folder remains useful archive
evidence, but it should not create a second episode, second transcript source,
or second downstream corpus-impact obligation. Use --force-policy only when
the maintainer explicitly overrides the policy.
Import:
node ops/scripts/import-colab-video.mjs \
--video-id VIDEO_ID \
--channel @PredictiveHistory
# for interview-format sources
node ops/scripts/import-colab-video.mjs \
--video-id VIDEO_ID \
--channel Interviews/<host-channel-id>
Inspect:
node ops/scripts/inspect-source.mjs \
content/sources/videos/<source-slug>
Prepare packets:
node ops/scripts/prepare-agent-transcript-packets.mjs \
--source content/sources/videos/<source-slug>
The E2E integration script can run these steps for one video:
node ops/scripts/process-video-e2e.mjs --video-id VIDEO_ID --channel @PredictiveHistory
# or, for interview-format sources:
node ops/scripts/process-video-e2e.mjs --video-id VIDEO_ID --channel Interviews/<host-channel-id>
content/sources/videos/<source-slug>/metadata.json
content/sources/videos/<source-slug>/transcripts/v1/transcript.clean.jsonl
content/sources/videos/<source-slug>/transcripts/v1/transcript.clean.md
content/workflow/tasks/<source-slug>/transcript-agent-packets.jsonl
Do not commit raw audio or video.
Each source should include:
source_class: episode for Predictive History lectures, interview for interview-format appearances.collection: episodes or interviews; this controls the public route generated by the compiler.recorded_at: when the statement was made, if known.published_at: when the artifact became public.date_precision: day, month, year, or unknown.chronology_status: dated or needs-date.Prefer recorded_at when reasoning about what Jiang believed at a time. Use published_at when recorded_at is unknown, but label precision honestly.
The importer reads raw metadata.youtube.json when present. If it is missing, it may try yt-dlp by video ID, cache compact metadata into the raw source artifact folder, and use published_at for chronology.
When transcription.json includes turns[].words[], preserve phrase-level timed_chunks inside each clean segment. The transcript page uses those chunks for speech-following highlights.
After import, verify when needed:
node -e "const fs=require('fs');const lines=fs.readFileSync('content/sources/videos/<source-slug>/transcripts/v1/transcript.clean.jsonl','utf8').trim().split('\n').map(JSON.parse);console.log(lines.reduce((s,x)=>s+(x.timed_chunks?.length||0),0))"
If this prints 0, the transcript can still highlight whole segments, but not phrase-by-phrase. Do not fake phrase timing in the website layer.
Use stable refs:
video:<source-slug>@transcript:v1#seg-0001
The importer owns segment IDs and transcript text. It does not decide what is a real interaction, claim, model, glossary item, or public episode argument. Those belong to later skills.
After ingest, hand off to:
jiang-transcript-boundary-review if boundary candidates require decisions,jiang-agent-transcript-pass for semantic packet outputs,jiang-episode-read-writer only after semantic bundle and transcript are ready,jiang-canon-promotion only after proposal and review records exist.Use this skill when a Jiang Lens autonomous agent needs to discover, claim, perform, validate, and hand off repo work without overwriting other agents or confusing authored, raw, and generated artifacts.
Use this skill after every published Jiang Lens episode, or when reassessing an existing episode, to decide and record how that source mutates the corpus, existing lens pages, lens points, atlas structure, chronology, and canon candidates.
Use this skill as the integration map for Jiang Lens work after episode publication, selecting the narrower corpus impact, concept writing, atlas maintenance, provenance linking, judging, or canon promotion skill needed for the task.
Use this skill as the integration map for turning one already-transcribed Jiang Lens video from synced Drive artifacts into a website-visible episode or interview, delegating detailed work to the narrower ingest, transcript, read-writing, and publishing skills.
Use Jiang Lens Moltnet through the local moltnet CLI: read episode-floor on request, send explicit room messages, and respect each participant's configured wake policy.
Use this skill when creating or revising a Jiang Lens glossary entry for a search-facing term, alias, person, institution, phrase, or query target from dated Jiang source refs and existing lens pages.