publish-blog-post — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited publish-blog-post (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.
list_my_articles — match the author's existing voice, and avoid re-coveringa topic they have already published.
search_articles — check what already exists platform-wide on the subject,so the piece has an angle rather than duplicating someone else's.
research_topic — gather angles and sources.Writing before doing this produces generic output that reads like every other post on the topic.
create_draft with title, body_markdown, and tags.
## headings and short paragraphs.makes a piece quotable by AI answer engines and eligible for featured snippets.
Show the draft and wait for approval before saving. Never publish in the same step as writing.
suggest_titles / generate_title_seo for candidates. Keep under 60characters so it is not truncated in search results.
generate_cover_image for a cover. Describe the subject concretely; abstractprompts produce unusable stock-feeling images.
publish_article makes it public — get explicit confirmation first. Pass schedule_at to schedule instead.
Use update_article for edits after the fact rather than creating a duplicate.
research_topic did not surfaceit, do not assert it.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.