/reprompter

name: reprompter
description: |
  Two intents: Improve ("reprompt this") emits a scored spec prompt; Build ("one-shot this") emits a build prompt for a whole app/game/site.
  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.
compatibility: |
  Single mode works on Claude surfaces, OpenClaw, Codex, Grok CLI, and Hermes Agent.
  `/goal` preflight mode works on Codex CLI (any version exposing the `goals` feature), Claude Code CLI v2.1.139+, and Hermes Agent; all three runtimes accept the same `/goal <objective>` shape. Disabled on Claude surfaces without `/goal` support, OpenClaw, and Grok CLI.
  Repromptverse mode supports Claude Code (TeamCreate or tmux → Option B/A), OpenClaw (sessions_spawn → Option C), Codex CLI (native subagents or `codex exec` → Option D), Grok CLI 4.3+ (spawn_subagent F1 or `grok -p` F2 → Option F), and Hermes Agent (delegate_task G1, shell-level G2, Kanban G3 → Option G). Sequential fallback (Option E) works with any LLM runtime.
  Workflow preflight lane + Repromptverse Option H target Claude Code's dynamic `Workflow` tool (JS-scripted background fan-out with schema-validated returns and resume); additive, detected by tool presence, with first-class ultracode.
  A post-output delivery step can — offered once as a structured choice (plain-text fallback) over the relay targets headless-relay's preflight marks available (built-in lanes plus user-connected custom/local targets), never auto-executed — hand a finished Single/Reverse prompt to the headless-relay skill; the orchestrator reviews the relayed answer against the prompt's success criteria by default. When the relay skill is not installed, no target is available, or availability cannot be verified, the step is invisible.
metadata:
  author: AytuncYildizli
  version: 13.1.0

RePrompter v13.1.0

> **Your prompt sucks. Let's fix that.** Two intents — improve my prompt, or build this whole thing — with `/goal`, Workflow, team execution and cross-model delivery as places the result can go. **v13 (RePrompter v2) restructures six lanes into two intents: a specifiability router picks spec-XML or an autonomous build prompt inside Improve, and Build can run as one prompt or split across a team. Every v12 trigger keeps working.**

---

Two intents

Users learn two sentences. Everything else is machinery underneath them.

| Intent | Trigger | What happens | |--------|---------|-------------| | **Improve** — "make my prompt better" | "reprompt this", "clean up this prompt" | Interview → the specifiability router picks the shape: **spec-XML** when the done-state is enumerable up front (bugfix with a repro, endpoint with a contract, bounded feature), **outcome-prose** in the One-Shot shape when done can only be judged against a quality bar (whole product, "like X", aesthetic outcome) → score (spec-XML only) → output-format step | | **Build** — "build this whole thing" | "one-shot this", "one-shot a X", "tek promptla", "tek seferde", "vibe a game", "build me a whole app/game/site" | Plain-language interview (max 4) → done-list brief → execution choice: **one prompt** (default; finishes in one session, maximal/loop opt-in) or **split across a team** (the brief seeds Repromptverse: done-list becomes the team's success criteria, the harsh checker becomes the evaluator) |

**Output formats (Improve):** these apply to **spec-XML results only** — an outcome-prose build brief is delivered as-is (it must not be compressed to `/goal` or compiled to a workflow, which would discard its staffing plan and checklist). paste (default) · compress to a `/goal <objective>` command (Codex CLI, Claude Code v2.1.139+, Hermes) · compile to a runnable `.workflow.js` (Claude Workflow tool) · deliver to another model via headless-relay (post-output step). The `/goal` and Workflow sections below define these formats; their triggers ("before /goal", "workflow preflight", "compile to workflow", "dynamic workflow", ...) jump straight to Improve with that format.

**Team execution (Build and beyond):** "repromptverse", "reprompter teams", "smart run", "smart agents", "run with quality" and the swarm triggers route to the Repromptverse machinery below — either standalone as today, or seeded by a Build brief.

**Advanced:** Reverse mode (extract the prompt DNA from a great output — "reverse reprompt", "prompt dna") keeps working exactly as before and feeds the flywheel; it lives in its own section below.

**Specifiability rule (Improve):** when the router picks outcome-prose, announce it in one line — "This looks like a whole-product ask — generating an autonomous build prompt; say 'spec' for the structured version." — and switch shapes if the user objects. Outcome-prose always keeps a constraints sentence (the home for "never touch auth"); it is not scored on the six dimensions.

Auto-detection: if task mentions 2+ systems, "audit", or "parallel" → ask: "This looks like a multi-agent task. Want to use Repromptverse mode?"

Definition — **2+ systems** means at least two distinct technical domains that can be worked independently. Examples: frontend + backend, API + database, mobile app + backend, infrastructure + application code,