aytuncyildizli/reprompter

Two intents: Improve ("reprompt this") emits a scored spec prompt; Build ("one-shot this") emits a build prompt for a whole app/game/site. Entry point that routes to the reprompter-* mode skills. Use when: "reprompt", "clean up this prompt", "before /goal", "Codex /goal", "Claude Code /goal", "Hermes /goal", "repromptverse", "reprompter teams", "smart run", "run with quality", "engineering/ops/research/marketing swarm", "compile to workflow", "workflow preflight", "dynamic workflow", multi-agent tasks, audits, "reverse reprompt", "prompt dna", "extract prompt from", "one-shot this", "one-shot a X", "tek promptla", "tek seferde", "vibe a game", "build me a whole app/game/site". Don't use for simple Q&A, casual chat, or execution-only tasks. Outputs: structured XML/Markdown prompt + before/after score; /goal command card (Codex/Claude Code/Hermes); optional team brief + per-agent prompts + Agent Cards; Reverse Extraction Card; Workflow Command Card + runnable .workflow.js (Workflow preflight lane / Option H). Target score: spec >= 7/10; per-agent >= 8/10.

RePrompter Improve output formats — compress a finished spec-XML prompt to a /goal <objective> command (Codex CLI, Claude Code v2.1.139+, Hermes), compile it to a runnable .workflow.js for Claude's dynamic Workflow tool, or deliver it to another model via headless-relay. Use when: "before /goal", "for /goal", "Codex /goal", "Claude Code /goal", "Hermes /goal", improve a goal prompt, "compile to workflow", "workflow preflight", "dynamic workflow"; or the headless-relay delivery step after a finished Single/Reverse prompt. Don't use for outcome-prose / One-Shot build briefs (delivered as-is), simple Q&A, or execution-only tasks. Outputs: /goal command card (Codex/Claude Code/Hermes); Workflow Command Card + runnable .workflow.js (Workflow preflight lane / Option H); optional relay delivery offer. Target score: spec >= 7/10.

RePrompter Improve intent — turn a rough prompt into a scored, structured spec prompt (or an outcome-prose build brief when the ask is a whole product). Use when: "reprompt", "reprompt this", "clean up this prompt", "improve this prompt", "make my prompt better", "fix my prompt", "before /goal", "compile to workflow", "workflow preflight", or when the reprompter entry skill routes an Improve ask here. Don't use for simple Q&A, casual chat, or execution-only tasks. Outputs: XML/Markdown prompt with <success_criteria schema_version="1"> + before/after quality score table. Target score: >= 7/10.

RePrompter Build intent — one prompt that builds a whole app/game/site in one session (default), or a brief that seeds a Repromptverse team. Use when: "one-shot this", "one-shot a X", "tek promptla", "tek seferde", "vibe a game", "build me a whole app", "build me a whole game", "build me a whole site", "build me X like <product>", or when reprompter-improve's specifiability router picks outcome-prose. Don't use for bounded changes (bugfix, endpoint, a feature in named files) — use reprompter-improve. Outputs: three-paragraph prose build brief (named reference, staffing with a separate harsh checker, 5-12 item done-list + stack). Not scored on the six dimensions.

RePrompter Reverse mode (advanced) — extract the prompt DNA from a great output and emit the XML prompt that would have produced it, with extracted success criteria; optionally seeds the Prompt Flywheel. Use when: "reverse reprompt", "reverse reprompter", "prompt dna", "prompt genome", "extract prompt from", "reprompt from example", "reprompt from this", "learn from this", "reverse engineer prompt", "prompt from output". Don't use to improve a raw prompt (use reprompter-improve) or for simple Q&A. Outputs: Reverse Extraction Card + reverse-engineered XML prompt with extracted <success_criteria> + quality score. Target score: spec >= 7/10.

RePrompter team execution (Repromptverse / Agent Teams) — score the raw task, plan a 2-5 agent team, write a reprompted prompt per agent, run it on the detected runtime (Grok CLI, Hermes, Claude Code TeamCreate/Workflow/tmux, OpenClaw, Codex, or sequential), then evaluate and retry. Use when: "repromptverse", "reprompter teams", "smart run", "smart agents", "run with quality", "engineering/ops/research/marketing swarm", multi-agent tasks, audits, "parallel", tasks spanning 2+ systems; or a Build (One-Shot) brief the user wants "split across a team". Don't use for single-prompt improvement (use reprompter-improve), simple Q&A, or casual chat. Outputs: optional team brief + per-agent prompts + Agent Cards (Plan/Status/Result) + reprompt quality scorecard + final synthesis. Target score: per-agent >= 8/10.