Prompt improvement for Claude Code. Two operating modes injected via SessionStart hook: co-pilot (one-line nudge with approval, default) and auto-pilot (silent rewrite with annotation). Coding-focused with use-case awareness across writing, creative, and strategy. /prompy:prompy gives a full deep-dive report card on demand. /prompy:mode switches modes (auto-pilot | co-pilot | off).
Switches Prompy's operating mode between co-pilot, auto-pilot, and off. Invoked via /prompy:mode [auto-pilot|co-pilot|off]. With no argument, shows the current mode. Persists via ~/.claude/prompy-mode file, overridable by PROMPY_MODE env var. Trigger phrases - "/prompy:mode", "switch prompy to auto-pilot", "turn prompy off", "disable prompy", "what mode is prompy in".
Deep-dive prompt improvement workflow with a full before/after report card and edit iteration. Use this skill when the user explicitly wants the comprehensive analysis instead of the inline co-pilot/auto-pilot trace from the hook. Trigger phrases - "/prompy", "/prompy:prompy", "deep dive on this prompt", "give me the full report card", "show me the prompy report".
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub navarroangelo/prompy --plugin prompyReliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.