jiang-episode-publisher — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited jiang-episode-publisher (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this after content/lens/episodes/<source-slug>/read.json exists. This skill is mechanical publication and validation. It should not become the episode writer.
content/sources/videos/<source-slug>/content/lens/evidence/videos/<source-slug>.semantic.jsoncontent/lens/episodes/<source-slug>/read.jsonops/scripts/node ops/scripts/compile-content.mjsnode ops/scripts/validate-content.mjscd website && npm run buildwebsite/src/data/lens/episodes/<source-slug>.json
/episodes/<source-slug>/
/episodes/<source-slug>/transcript/
# or, when source_class is interview:
website/src/data/lens/interviews/<source-slug>.json
/interviews/<source-slug>/
/interviews/<source-slug>/transcript/Confirm:
timed_chunks exist,Do not rewrite public prose except for small structural fixes required by validation. If the read is shallow, wrong, or missing Jiang's voice, hand it back to jiang-episode-read-writer.
Do not edit generated files by hand.
After successful publication, stop. Corpus impact, lens links, concept extension, new lens seeds, atlas mutation, and canon-candidate review are downstream jobs for separate agents. Mention obvious follow-up in the handoff, but do not create or require corpus-impact.json as part of episode publication.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.