Skill Vetter
一个面向 Security 场景的 Agent 技能。原始说明:Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
name: x-post-audit
description: Audit X drafts before publishing. Use when scoring hooks, clarity, dwell, replies, repost value, profile-click potential, follow potential, and negative-feedback risk.
Use this before publishing important posts.
Apply the smallest useful fix:
Return:
Treat the public X algorithm as a signal map, not a cheat code. Optimize for posts and replies that earn useful positive actions (dwell, replies, reposts, shares, profile clicks, follows) while avoiding negative actions (not interested, mute, block, report, fast skips).