← ClaudeAtlas

revenantworks-foundation-promptwrightlisted

Writes, fixes and red-teams prompts — system prompts, templates, meta-prompts, agent or bot instructions — as copy-paste-ready artifacts, and picks the model tier for a prompt, task or plan's subtasks. Trigger to write, improve, debug or rewrite a prompt; which model should run this; a prompt that costs too many tokens, to cut with behavior held; or say /rw-promptwright (model, optimize — tune against test cases, slim, refresh). Not for a fan-out's units (dispatchwright), installed local models (lmstudiorunner), skills or their slim (skillwright), sourced comparisons (researchscribe), handoffs (handoffwright) or a pre-build interview (grillwright).
revenantworks/claude-skills · ★ 2 · AI & Automation · score 81
Install: claude install-skill revenantworks/claude-skills
# revenantworks-foundation-promptwright *history in CHANGELOG.md · sources in SOURCES.md · Apache-2.0 (LICENSE)* Turn a rough idea, parameters, or an existing prompt into a scored, copy-paste-ready artifact. **Workflow:** Intake → Analyze + Score → Pick structure → Clarify (only if needed) → Build → Re-score & self-check → Output Model-invocable: on claude.ai the description is the only trigger; `compatibility` states its one write. Web search never for design. ## Turn shape — read before doing anything 1. **Full builds show every phase header 1–7:** `── Phase N / 7 — [name] ──`, none merged or silently skipped (Phase 4 may be marked skipped). The Phase 7 header sits directly above the prompt code block; the prompt appears there and **never under Phase 5**. Only the quiet build (rule 5) and the Fast path trade the ladder for one trace line. 2. **The Keep going selection is the turn's final element**, after the prompt block, footer and test tip. Run the tool-list test first: if any tool presents tappable options or questions, render the selection with it; otherwise use the plain-text fallback line. 3. **A Model line ships with every prompt block**, improvement runs included. 4. **No phase headers** for bare invocations, Refresh, Model, restraint, guidance-only, report-only runs (score-only, a named red-team) and improvement runs (the `Changed` diff replaces the ladder). 5. **Quiet build — opt-in only** ("quiet build", "just the prompt"): Phases 1–6 collapse into one trac