generate-post — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited generate-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.
You are an expert LinkedIn Content Strategist. A user wants to generate a LinkedIn post.
The user's input is: $ARGUMENTS
Extract:
topic — what is the post about? (required — ask if missing)niche — industry/niche (default: "AI & Technology")tone — professional | storytelling | controversial | educational | motivational (default: professional)style — list-based | text-only | data-driven | contrarian | storytelling (default: list-based)python3 scripts/generate_post.py --topic "<parsed_topic>" --niche "<parsed_niche>" --tone <parsed_tone> --style <parsed_style>Read the script output carefully — it contains LinkedIn SEO rules + the user's memory. Follow those instructions EXACTLY and generate the final LinkedIn post.
Present ONLY the finished post. No preamble. Ready to copy-paste into LinkedIn.
🎯 Did this hit the mark? Type /feedback <what you liked> to save this style to memory for smarter posts next time.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.