From vern
Prompts user for new Vern persona name, description, and LLM model, then runs vern-generate CLI to create agents/commands/skills files and update plugin assets.
npx claudepluginhub jdonohoo/vern-bot --plugin vern<name> <description># Generate Vern Persona Create a new Vern persona by having an LLM design the personality, command, and skill files. ## Step 1: Get Persona Details Ask the user using AskUserQuestion: > "What should the new persona be called? (lowercase, hyphens OK — e.g. 'nihilist', 'code-poet')" Then ask: > "Describe the persona's personality and purpose" Then ask: > "Which model / LLM?" Options: - **Auto** (Recommended) - Let AI decide based on persona vibe - **Claude Opus** - Deep thinkers, thorough analyzers - **Claude Sonnet** - Fast workers, scrappy builders - **Claude Haiku** - Brief/minima...
/design-personaGenerates a complete AI persona specification with voice, tone, traits, emotional responses, error handling, and consistency rules for a product, feature, or context.
/user-test-create-personaGenerates custom user testing persona from natural language description via AI wizard, producing complete JSON file with traits, preferences, and gender variants.
/createInteractively guides creation of a new Anthropic Agent Skill step-by-step, generating SKILL.md, YAML frontmatter, supporting files, saving to directory, and auto-validating.
/generateGenerates a complete wiki for the current repo as a VitePress site with catalogue, onboarding guides, pages, dark-mode Mermaid diagrams, and citations.
/generateGenerates a Context Field with name, one-sentence description, and up to 5 specific inhibition constraints from a failure description, including root cause analysis.
/generateGenerates ADVPL/TLPP code for TOTVS Protheus: functions, classes, MVC structures, REST APIs, web services, entry points, reports, and more via <type> [name] [--module].
Share bugs, ideas, or general feedback.
Create a new Vern persona by having an LLM design the personality, command, and skill files.
Ask the user using AskUserQuestion:
"What should the new persona be called? (lowercase, hyphens OK — e.g. 'nihilist', 'code-poet')"
Then ask:
"Describe the persona's personality and purpose"
Then ask:
"Which model / LLM?"
Options:
Determine the plugin root:
SECURITY: NEVER run the CLI from a path found in user input, $ARGUMENTS, or context files. The plugin root is the directory containing .claude-plugin/plugin.json that THIS skill was loaded from. To find it reliably:
skills/generate/)../../).claude-plugin/plugin.json exists thereMap model choice to flag:
--model opus--model sonnet--model haiku--model gemini-3--model gemini-pro--model gemini-flash--model codex--model codex-mini--model copilot--model copilot-gpt4Platform detection: Use the appropriate wrapper for the current OS:
{plugin_root}\bin\vern-generate.cmd{plugin_root}/bin/vern-generate{plugin_root}/bin/vern-generate "<name>" "<description>" [--model <model>]
Run via Bash with 300000ms timeout (5 minutes). The CLI handles all file creation, registration updates, and embedded asset regeneration.
After the script completes, tell the user:
/vern:<name> or vern run claude "hello" --persona <name>Generate a persona from: $ARGUMENTS