No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by typefully · Agent Tool · ★ 59
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-skills safe to install? View the security audit →
Typefully Skills []() AI agent skills for drafting, scheduling, and managing social media posts across X, LinkedIn, Threads, Bluesky, and Mastodon. Give your AI agent the ability to manage your social media scheduling directly from your IDE or terminal. Built on the Typefully API. Typefully is a writing and scheduling app used by 200k+ top creators and teams to grow on X, LinkedIn, Threads, and Bluesky. What Are Skills? Skills are markdown files that give AI agents specialized knowledge and workflows for specific tasks. Add this to your project and your AI agent will be able to create, schedule, and publish social media content. Setup Install the skill CLI (works with Claude Code, Cursor, Windsurf, and many other agents): Other installation methods Claude Code Plugin: Then: Cursor: Open Settings (Cmd+Shift+J) Go to "Rules & Command" → "Project Rules" Click "Add Rule" → "Remote Rule (GitHub)" Enter: https://github.com/typefully/agent-skills.gi
| Stars | 59 |
| Forks | 5 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 73.0732714222608/100 |
| Open Issues | 9 |
| Last Updated | 2026-09-18 |
| Created | 2026-01-26 |
| Platforms | node |
| Est. Tokens | ~11k |
Explore other popular agent tool tools:
agent-skills is AI agent skills for drafting and scheduling social media posts via Typefully. It is categorized as a Agent Tool with 59 GitHub stars.
agent-skills is primarily written in JavaScript.
You can find installation instructions and usage details in the agent-skills GitHub repository at github.com/typefully/agent-skills. The project has 59 stars and 5 forks, indicating an active community.
agent-skills is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: