Safer agent skills

Web search via Tavily API (alternative to Brave).

Score basis：Source needs review · High risk signals · Claude

Humanize AI-generated text to bypass detection.

Score basis：Source needs review · High risk signals · Claude

Remove signs of AI-generated writing from text.

Score basis：Source needs review · High risk signals · Claude

The Runtime Security Layer for OpenClaw/Hermes-agent, the essential safety harness for PII & sensitive credentials protection.

Score basis：Clear source · Risk needs review · Universal

🗺️ Hermes Atlas — the community map of every tool, skill, and integration for Hermes Agent by Nous Research.

Score basis：Clear source · Risk needs review · Universal

Claw-R1: Empowering OpenClaw with Advanced Agentic RL.

Score basis：Clear source · Risk needs review · Universal

Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search.

Score basis：Clear source · Risk needs review · Universal

Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals.

Score basis：Source needs review · High risk signals · Claude

Lobster is a Openclaw-native workflow shell: a typed, local-first “macro engine” that turns skills/tools into composable pipelines and safe automations—and lets Openclaw call those workflows in one step.

Score basis：Clear source · High risk signals · Universal

Web search using Tavily's LLM-optimized API.

Score basis：Source needs review · High risk signals · Claude

Terminal-style Telegram Mini App for Hermes Agent — chat, cron jobs, and system monitoring in a dark TUI

Score basis：Clear source · Risk needs review · Universal

Browser automation via Playwright MCP.

Score basis：Source needs review · High risk signals · Claude

A self-evolution engine for AI agents.

Score basis：Source needs review · High risk signals · Claude

Complete toolkit for programmatic video creation with Remotion + React.

Score basis：Source needs review · Low risk signals · Claude

Virtual AI Office Dashboard for OpenClaw — visualize your multi-agent workflows in real-time

Score basis：Clear source · Risk needs review · Universal

Interact with GitHub using the `gh` CLI.

Score basis：Source needs review · High risk signals · Claude

Sync and query CalDAV calendars (iCloud, Google, Fastmail, Nextcloud, etc.) using vdirsyncer + khal.

Score basis：Source needs review · High risk signals · Claude

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Score basis：Source needs review · High risk signals · Claude

Convert documents and files to Markdown using markitdown.

Score basis：Source needs review · High risk signals · Claude

Browser automation via Playwright MCP server.

Score basis：Source needs review · High risk signals · Claude

Self-host Honcho memory layer for Hermes Agent — OpenRouter + Venice, no code changes

Score basis：Clear source · Risk needs review · Universal

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

Score basis：Source needs review · High risk signals · Claude

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection The skill is an instruction-only wrapper describing how to use the agent-browser CLI; its requeste

Score basis：Source needs review · High risk signals · Claude

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features The skill's requirements and runtime instructions line up with a

Score basis：Source needs review · High risk signals · Claude