LearnPromptLearnPromptCommunity·1 Agent Skills Included

luban-skill

Audit, benchmark, and polish your AI agent skills for public release

Audits your AI agent skill against real competitors, scores it across nine quality dimensions, and rewrites weak spots through verified, gated edits. Eliminates guesswork about why a skill gets no installs by checking live outputs, README hooks, and install friction with real evidence. Delivers a structured polishing report, ready-to-paste rewrite snippets, and a shareable before-and-after scorecard.
npx skills add LearnPrompt/luban-skill --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install luban-skill?

Run `npx skills add LearnPrompt/luban-skill --all -g -y` in your terminal to install the skill globally for your AI agent.

What does Luban do for my AI skill?

It challenges whether your skill is worth building, benchmarks it against at least five real competitors with URLs, scores it on nine dimensions, and proposes three improvement directions before editing anything.

Why is nobody installing my skill?

Luban diagnoses this by checking your README hook, install friction, missing demos, and silent failures like stale data behind green CI, then gives you a prioritized fix list.

Does Luban work with Claude Code and other agents?

Yes. It follows the universal SKILL.md standard and runs in Claude Code, Hermes Agent, Codex, OpenClaw, and other compatible runtimes.

Will Luban change my skill without permission?

No. It stops and waits for your explicit approval before rewriting, merging, tagging releases, or any user-visible deployment.

Related Repositories in Software Engineering

View All in Software Engineering