prompt-writerlisted

# Prompt Writer Guide for writing maximally terse agent prompts with built-in constitutional governance and epistemic stance. Combines compression-by-default authoring (tersify), governance primitives (constitution), and epistemological foundations (epistemology) into a single progressive-disclosure skill. ## When to Use - Creating new agent specifications or skill prompts - Writing command/skill prompts with governance built in - Drafting instruction sets for AI agents - Applying constitutional or epistemic review to existing prompts - Running the six-stage prompt pipeline via `/build-prompt` ## Core Principles **Structure-First**: Start with skeleton, not prose. Choose section pattern, fill minimally. **Compression-by-Default**: Every word must earn its place. Remove before adding. **Preserve Exactness**: Normative language (MUST/SHOULD/MAY), literals, constraints stay verbatim. **Governed-by-Design**: Constitutional primitives and epistemic stance are selected upfront, not bolted on. ## Skill Files ### Reference Layers | File | Purpose | When to Load | |------|---------|--------------| | `references/tersify.md` | Compression discipline, section patterns, abbreviation policy, style rules, validation checklist | Direct `/prompt-writer` invocation; prompt-validation pipeline stage | | `references/constitution.md` | 10 governance primitives (anti-loop, output discipline, role, scope limits, orchestrator purity, error degradation, exploration bounds, anti-bias, truth