with one click
prompt-generator
prompt-generator contains 6 collected skills from jl-cmd, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Caveman-trimmed variant of pmax. Builds prompts decision by decision. Asks structured multiple-choice questions in small rounds, posts each approved answer as a tagged line in chat, then assembles the final prompt only from those tagged lines so nothing unapproved is added. Use when the user wants a prompt built piece by piece without re-reading drafts. Triggers: '/pmax-cm', 'pmax-cm', 'caveman pmax', 'trimmed pmax'.
Builds prompts decision by decision. Asks structured multiple-choice questions in small rounds, posts each approved answer as a tagged line in chat, then assembles the final prompt only from those tagged lines so nothing unapproved is added. Use when the user wants a prompt built piece by piece without re-reading drafts. Triggers: '/pmax', 'build a prompt with me', 'pmax', 'incremental prompt builder'.
Single-pass XML formatter — takes a raw input block, emits one clean xml fence with context-adapted tags and an Outcome digest. Zero tool calls, zero plan mode, zero validation loop.
Mid-tier XML formatter — takes a raw input block, drafts context-adapted XML, runs the 15-row compliance audit and file-based validation loop, then emits the validated fence and Outcome digest. Zero plan mode, zero AskUserQuestion, zero Outcome preview gate.
Authors repository-grounded XML prompt artifacts for Claude: system and developer instructions, agent harnesses, tool-use patterns, evaluation rubrics, NotebookLM audio customization, and MCP or browser automation steering. Enters plan mode for deep codebase exploration, runs AskUserQuestion rounds during planning, gets user approval via ExitPlanMode, converts plan headers to XML tags at all depths, runs a mandatory Outcome preview gate, then delivers one fenced XML block and a skimmable Outcome digest after the fence. Trigger when the user asks to write, refine, or improve steering text for Claude. Execution of the described work belongs in /agent-prompt only after the user explicitly confirms they want it run.
Runs the prompt-generator workflow through its paste-ready XML handoff, then spawns a background subagent whose task is that user-approved XML. Triggers: '/agent-prompt', 'launch an agent', 'spawn agent to do X', 'delegate this', 'run in background', 'execute the prompt with an agent'. Does not apply when the user only needs the fenced prompt and digest with no subagent (/prompt-generator).