Your AI Agent is strong, but it can be limitless. **OneSkill** is the bridge connecting your Agent to the massive [OpenSkills](https://github.com/Starttoaster/openskills) ecosystem. By installing just this one tool, your Agent gains the ability to evolve itself: **discover new skills, install them more easily, and support a wide range of tools like Codex, Gemini, and more.** No more manual file downloads or configuration edits. Everything is automated.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add Felixlan11/oneskill --skill guide --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Guide?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/felixlan11-guide)More formats (shields.io, HTML) on the badges page.
# What is OneSkill?
Your AI Agent is strong, but it can be limitless.
**OneSkill** is the bridge connecting your Agent to the massive [OpenSkills](https://github.com/Starttoaster/openskills) ecosystem. By installing just this one tool, your Agent gains the ability to evolve itself: **discover new skills, install them more easily, and support a wide range of tools like Codex, Gemini, and more.**
No more manual file downloads or configuration edits. Everything is automated.
## Core Value
* **Massive Skill Library**: Instantly connect to thousands of community-maintained Skills (Web browsing, Database management, Code auditing, Cloud infrastructure ops, etc.).
* **Universal Compatibility**: Built on OpenSkills, working seamlessly with **Claude Code, Cursor, Windsurf, Aider, Codex**, and more.
* **Gemini Enhanced**: Includes specialized mapping support for **Gemini CLI**, enabling it to access the entire skill ecosystem effortlessly.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
