Safest Skills

ClawScanner Verified

Week 8, 2026 · Ranked by security score

1
self-improving-agent/self-improving-agentB · 93

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails...

by self

→
2
Proactive Agent/proactive-agentB · 86

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with...

by proactive

→
3
API Gateway/api-gatewayB · 86

API gateway for calling third-party APIs with managed OAuth connections, provided by Maton (https://maton.ai). Use this ...

by api

→
4
Gog/gogB · 83

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

by gog

→
5
Clawdbot Documentation Expert/clawddocsB · 82

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config ...

by clawddocs

→
6
Stock Analysis/stock-analysisB · 82

Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management, watchlists with alerts, div...

by stock

→
7
Agent Browser/agent-browserB · 81

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type,...

by agent

→
8
Ontology/ontologyB · 81

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Pr...

by ontology

→
9
ByteRover/byteroverB · 81

Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (...

by byterover

→
10
Nano Banana Pro/nano-banana-proB · 81

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Suppor...

by nano

→

Security scores powered by ClawScanner static analysis. A (95+) = excellent · B (80–94) = good · C (60–79) = fair · D (<60) = caution. Updated weekly.