mapick-ai

mapick-ai / mapick

Public

The Mapick Butler - Privacy layer + skill advisor for OpenClaw. Redacts secrets locally, recommends workflow-fit skills, cleans zombies, scores risk, generates persona, ships bundles. MIT.

13
1
89% credibility
Found Apr 29, 2026 at 13 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

Mapick is a skill manager for OpenClaw AI agents that redacts sensitive data for privacy, recommends useful skills, cleans unused ones, scores security, analyzes user personas, and offers bundles.

How It Works

1
🔍 Discover Mapick

While using your AI assistant, you learn about Mapick, a helpful butler that keeps your skills organized and private.

2
📦 Add Mapick easily

You install Mapick with a quick command, and it's ready to chat—no extra setup needed.

3
💬 Ask about your setup

You tell your AI 'Is my data safe?' and Mapick checks your privacy, showing what's protected.

4
Protect and improve
🧹
Clean unused skills

Remove forgotten tools to speed up your AI and free space.

🎯
Get smart suggestions

Discover missing skills that save you time based on your habits.

5
🌙 See your unique style

Mapick analyzes your work patterns and creates a fun persona profile just for you.

6
📦 Install bundles or tweak

Grab ready-made tool packs or fine-tune based on what you need.

Enjoy a better AI

Your assistant feels faster, safer, and perfectly matched to your needs.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 13 to 13 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is mapick?

Mapick is a JavaScript butler skill for OpenClaw that acts as a privacy layer and advisor, redacting secrets locally before they reach other skills, recommending workflow-fit ones with time savings estimates, cleaning zombie skills to slim context windows, scoring security risks, generating developer personas, and shipping bundles. With 57,000+ OpenClaw skills all peeking at your full chat history and code, it solves privacy leaks, skill overload, and bloat without setup—just install via `openclaw skills install mapick` and chat commands like "Recommend skills" or "Clean up." MIT-licensed, it runs entirely locally for redaction while syncing anonymized usage to a cloud API for smarts.

Why is it gaining traction?

It stands out with proactive features like quantified efficiency gaps ("save 9 hours/week"), one-command bundle installs for toolchains, and shareable persona cards, turning skill management into natural chat. Developers hook on the local-first redaction (20+ patterns for API keys, DB URIs, PII) that works regardless of skill trust, plus zombie detection that cuts context by 40%. No alternatives match this combo of privacy, cleanup, and advisor in one lightweight JS package for OpenClaw.

Who should use this?

OpenClaw power users juggling 20+ skills, like full-stack devs installing tutorial packs then drowning in zombies, or DevOps folks needing ci-monitor and log-analyzer recs without ClawHub scrolling. Ideal for late-night coders ("3AM Committer" persona) wanting security grades before installs and bundles like Full-Stack Developer or pnpm Monorepo.

Verdict

Try it if you're deep in OpenClaw—solid docs and chat UX make it useful now, despite 13 stars and 0.9% credibility signaling early days. MIT openness invites audits, but wait for more users before trusting cloud recs fully.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.