By agent-sh
Curate production-grade system prompts for autonomous coding agents and multi-agent orchestration
Expert system for creating and refining production-grade system prompts for autonomous coding agents and multi-agent orchestration.
This plugin is the canonical reference for writing high-quality agent identities, workflows, and completion criteria that work reliably across Claude Code, Cursor, Codex, OpenCode, Kiro, Devin-style agents, and other modern coding agents.
agentsys install system-prompt-curator
/system-prompt-curator "senior software engineer that resolves GitHub issues end-to-end"
/system-prompt-curator --improve path/to/existing-prompt.md --for-orchestrator
/system-prompt-curator --improve path/to/prompt.md --minimal
skill-curator — sibling plugin for writing excellent SKILL.md filesenhance — broader prompt/plugin/agent improvementkarpathy-guidelines — foundational behavioral rules often included in promptsThe best agents are not the ones with the cleverest tricks in the prompt — they are the ones with:
This curator exists to make those patterns easy to apply consistently.
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 agent-sh/system-prompt-curator --plugin system-prompt-curatorDeep repository analysis to realign project plans with actual code reality - discovers drift, gaps, and produces prioritized reconstruction plans
Master workflow orchestrator with autonomous task-to-production automation, quality gates, and multi-agent review
Plugin structure and tool use analyzer - validates plugin.json, MCP tools, and security patterns
AI slop cleanup with minimal diffs and behavior preservation
Multi-agent iterative code review until zero issues remain
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
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.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.