Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From claude-orator
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
npx claudepluginhub vvkmnn/claude-emporium-beta --plugin claude-oratorHow this skill is triggered — by the user, by Claude, or both
Slash command
/claude-orator:claude-oratorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Prompt optimization. Scores prompts across 7 dimensions and restructures them using 8 Anthropic techniques. Deterministic — no LLM calls, no network, in-memory only.
Scores prompts across 7 dimensions and restructures using 8 Anthropic techniques like XML tags and chain-of-thought. Auto-triggers on PreToolUse for unstructured subagent prompts; manual via /reprompt-orator.
Audits and rewrites prompts for Claude Opus 4.7 instruction-following best practices. Produces a scored audit and rewritten prompt for system prompts, CLAUDE.md, agent definitions, slash commands, SKILL.md, Jinja2 templates, and Pydantic/Zod schemas.
Improves prompts via Anthropic best practices: queries official docs first, applies 4-step workflow with chain-of-thought, XML tags, and examples for accuracy and structure.
Share bugs, ideas, or general feedback.
Prompt optimization. Scores prompts across 7 dimensions and restructures them using 8 Anthropic techniques. Deterministic — no LLM calls, no network, in-memory only.
| Hook | When | Action |
|---|---|---|
| PreToolUse(Task) | Subagent prompt lacks structure | Suggests orator_optimize before dispatching |
Token cost: 0 on well-structured prompts (XML tags, markdown headers, action verbs). ~25 on vague prompts.
| Command | Description |
|---|---|
/reprompt-orator <prompt> | Optimize a prompt using Anthropic best practices |
/reprompt-orator "your prompt here" or call orator_optimize(prompt: "...")| Tool | Purpose |
|---|---|
orator_optimize | Score prompt across 7 dimensions, apply techniques, return restructured version |
Clarity · Specificity · Structure · Context · Examples · Constraints · Tone (each 1-10)
System prompts · XML tags · Chain of thought · Few-shot · Prefill · Long context · Extended thinking · Tool use
In-memory only. Zero disk storage. No databases, no external services.
claude mcp add orator -- npx claude-orator-mcp