Skill Claude CodeCodex
Use when a user wants a coding assistant to operate PromptBeat, asks about a coding-agent integration, or needs to distinguish legacy adapters from current AgentBeat evaluation.
Skill Claude CodeCodex
Use when Promptbeat validate, config inspect, generate, run, eval, report, provider-file loading, environment variables, workingdir, promptfoo, or coding-agent runtime execution fails.
Skill Claude CodeCodex
Use when a user has downloaded PromptBeat, wants a first local model or Prompt test, or needs help choosing the next supported command.
Skill Claude CodeCodex
Use when a user has a Promptbeat config or generated promptfoo config and wants to validate, generate a few cases, run a first small evaluation, inspect artifacts, or create a report.
Skill Claude CodeCodex
Use when a user needs help choosing PromptBeat model risks, scenarios, local seeds, dataset subscriptions, or a small first-test scope.
Skill Claude Code
Install, configure, test, and uninstall ClawVault AI security proxy.
Skill Claude Code
Mask sensitive company-project document content before analysis.
Skill Claude Code
Push high-risk ClawVault security events and daily security reports through OpenClaw agent messaging.
Skill Claude Code
Operate ClawVault services, configuration, vault presets, scanning, local sanitization, and OpenClaw plugin acceptance.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: