An Agent Skill for saving, deduplicating, and retrieving read-later articles with MongoDB
SaferSkills independently audited read-later-skill (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 skill when the user wants to:
readlaterarticlesreferences/mongodb-collection-schema.md.url_hash from normalized URL.canonical_url.url_hash.When user asks questions (for example "last week the xxx article said what?"):
Always include:
Answer: direct response in plain language.Why: evidence from stored summary/key points.Links: original URL first, record id second.Never invent article details. If record data is insufficient, say so explicitly.
tags: generate 3-6 specific tags from the article content. Tags are free-form and should not be limited to the topic taxonomy.topic: choose one primary category from this stable taxonomy:AIEngineeringProductBusinessDesignDataScienceMediaSocietyHealthLifestyleKey Points and Evidence Snippets.readlater.articles.titlesummarykey_pointstagstopicuser_notelast_updated_atreferences/mongodb-collection-schema.mdreferences/reply-templates.mdreferences/smoke-test.md~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.