cancel-ralph
Cancel active Ralph Loop
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,299 results
configure
Set up the Discord channel — save the bot token and review access policy. Use when the user pastes a Discord bot token, asks to configure Discord, asks "how do…
example-skill
This skill should be used when the user asks to "demonstrate skills", "show skill format", "create a skill template", or discusses skill development patterns.…
hookify
Create hooks to prevent unwanted behaviors from conversation analysis or explicit instructions
m5-onboard
End-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware,…
mcp-integration
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol",…
new-sdk-app
Create and setup a new Antigravity Agent SDK application
ralph-loop
Start Ralph Loop in current session
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
skill-development
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill…
solo
Work on one hard mathematics problem in this session yourself, with no sub-agents: reason in stages, record each settled step in a notes file so that nothing…
tsk-coordinator
Coordinate a multi-agent build: plan the work, brief builder agents, gate every pull request with an independent review, live-test before merge, and report to…
acp
Use when implementing or integrating agents and clients that communicate via the Agent Client Protocol. Reach for this skill when building AI coding agents,…
loopforge
Loopforge: Turn vague workflows into reusable AI Agent workflow loop specifications and prompts.
storm-research-agent
STORM research assistant: uses multi-perspective evidence to analyze whether a topic, product, tool, or workflow is worth pursuing.
blog
Full-lifecycle blog engine with 12 commands, 12 content templates, 5-category 100-point scoring, and 4 specialized agents. Optimized for Google rankings…
blog-geo
AI citation optimization audit scoring blog posts for ChatGPT, Perplexity, and Google AI Overview citability. Evaluates passage-level citability, Q&A…
my-skill-name
Longer explanation including when to use, trigger keywords, and anti-patterns. Cortex Code matches user prompts against this field to automatically activate…
adversary-disable
Disable CocoAdversary challenge review mode.
adversary-enable
Enable CocoAdversary challenge review mode.
archetype-classifier
V2-native deterministic contract for the owning CocoPlus feature. Executes the behavior formerly delegated to archetype-classifier skill without registered…
behavior-maturity
Report the CocoPod's current automation maturity level (L0 Manual through L3 Autonomous-Eligible), computed deterministically from cocoplus.toml and active…
behavior-maturity-engine
V2-native deterministic contract for the owning CocoPlus feature. Executes the behavior formerly delegated to behavior-maturity skill without registered…
bloom-crystallize
CocoBloom crystallization — converts a successful ship execution trace into a reusable skill file. Requires recent successful $ship. Invoked via $bloom…