hooks — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited hooks (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.
The first 8-12 words of an X post determine whether anyone reads the rest. Generate multiple high-impact hook options optimized for the Phoenix algorithm's dwell time signal.
The user provides:
What is the core message? Who is the audience? What emotion should the hook trigger?
Read patterns.md for the full hook pattern library.
Generate hooks across multiple pattern categories:
For each hook:
Rank all hooks by predicted effectiveness and annotate:
Present all hooks in a scored table, ranked by Phoenix Score. The score represents what a full post would score with that hook (assuming a solid body + CTA):
# Hook Score Best for
1. "2.3× faster than MLX — on a MacBook." 8.4/10 Dwell + bookmarks
2. "Your MacBook can fine-tune a 7B model in 12 min." 8.1/10 Specificity + curiosity
3. "Why I rewrote LLM inference in pure Rust." 7.9/10 Curiosity gap
4. "Most devs are overpaying for GPU cloud. Here's why." 7.6/10 Pain point + broad reach
5. "The local AI tipping point just arrived." 7.2/10 Boldest (high ceiling, more risk)
...Also include:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.