SR
SkillRadar
Agent security + benchmarks
Menu⌄

Security first

Safety Radar beta now; performance benchmarks, private registries, and runtime skill recommendations next.

Agent Skill Kit

Automation Kit

Extend an agent with autonomy, MCP building, model routing, and command/plugin workflows.

Best for advanced users who want more capable agents and understand that automation/extensibility skills need careful monitoring.

4
Skills
67
Avg trust
78
Avg overall
1 Low / 2 Medium / 1 High
Risk mix
Watch this kitCopy install listAll kits

Included skill #1

agent-autonomy-kit

Stop waiting for prompts. Keep working.

Risk
Low
Trust
85
Overall
82
Why included: Pushes agents to keep working productively instead of waiting for repeated prompts.
View trust reportSource SKILL.md

Included skill #2

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Risk
Medium
Trust
74
Overall
83
Why included: Helps create MCP servers, expanding what an agent can safely integrate with.
View trust reportSource SKILL.md

Included skill #3

acp-router

Route plain-language requests for Pi, Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow).

Risk
High
Trust
47
Overall
68
Why included: Adds routing/extensibility surface area that is powerful but worth monitoring closely for command and integration changes.
View trust reportSource SKILL.md

Included skill #4

Command Development

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in c

Risk
Medium
Trust
62
Overall
78
Why included: Supports command/plugin workflow development for deeper agent customization.
View trust reportSource SKILL.md

Watch the bundle

Recommendations should not go stale quietly.

Watch this kit closely for changes because automation skills can gain new commands, hooks, permissions, installer patterns, and external service dependencies.

Add Automation Kit to watchlist

Install manifest

Unlock the manifest with email + newsletter signup.

The manifest includes the kit source links, trust metadata, safety review steps, and watchlist context. Email capture keeps the install path tied to future change alerts instead of becoming a stale download.