Plugins

Build production-grade prompts from a short brief. Runs a short discovery interview, picks an appropriate detail level and structure, then produces a fully-scaffolded prompt with role, context, task, inputs, instructions, output spec, examples, and an optional self-verification block.

from P47Phoenix/Claude-Plugins

Structured prompt engineering: guides users step-by-step through a 6-phase framework to build high-quality, reusable prompts

Research-backed rules for creating, auditing, modifying, or designing Claude Code skills, CLAUDE.md files, rules files, hooks, subagents, or any system-prompt instruction file. Auto-fires on skill / CLAUDE.md / hook / subagent / instruction-file authoring intents.

Turn a description into an optimized, ready-to-paste LLM prompt for a Gemini Gem, Claude Project, or custom GPT, grounded in the promptingguide.ai guide — a bundled distilled reference for offline use, plus the NotebookLM MCP for live sources when connected. Auto-engages when you write or refine a prompt.

Master prompt engineering with 7 specialized agents

아이디어를 실행 가능한 프롬프트로 정리해주는 도구 — /prompt v2.10.0 + 모델별 최적화 전략 스킬

Improve and enhance prompts — turn a raw, vague, or first-draft prompt into a clearer, stronger instruction by applying an ordered set of prompt-engineering techniques (clarity, context, multishot examples, XML structure, role, chain-of-thought, prompt chaining) and returning the rewrite plus a tagged change log

from bennoloeffler/maude-claude-vunds-plugins

Manage prompts in production at scale: prompt versioning, A/B testing, prompt registries, regression prevention, and eval pipelines for production AI features. NOT for writing individual prompts, RAG design, or cost reduction (separate skills).

プロンプトログを自動収集・分析し、繰り返しパターンをスキル化・CLAUDE.md化する提案を行う。

v1.1.2 | 사용자 prompt + 도구 호출 통계를 동의한 프로젝트에서만 jsonl로 누적. /project-init 통합 동의, plugins/prompt-log/uninstall.sh 1줄 제거.

Prompt-engineering skills that build ready-to-paste prompts through a short interview, each saved to Adriaan's prompt library: prompt-master-chat (Claude.ai chat prompts), prompt-master-cowork (depth-first agentic Cowork task briefs with guardrails), prompt-master-design (Claude Design visual prompts), prompt-master-copilot-research (Microsoft 365 Copilot Researcher prompts) and prompt-master-office (Claude Office add-in prompts for Excel, Word, PowerPoint, Outlook). prompt-master-handoff covers every hand-off moment in one skill (live Agent-tool subagent, chat detour with resume, fresh Cowork chat, fresh Claude Code session, and the Cowork-to-Claude-Code handover). project-master sets up and self-heals Cowork projects. html-builder builds interactive HTML pages and small websites on a size ladder, deploying via website-toolkit.

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.

from sultano/claude-code-marketplace

Forges weak Claude Code prompts into structured, credit-saving, framework-aware prompts.

モデル非依存のプロンプト分析・最適化パターン（BP-001〜BP-008）

Thirty-five reusable workflows for model routing, personal productivity, code comprehension, knowledge systems, agent evaluation, consumer AI strategy, and Office documents.

from benjaminjackson/ai-engineering-skills

Sistema de catalogación de prompts y gestión de agentes para herramientas AI

from f/awesome-chatgpt-prompts

Store / keep / retrieve a research project's knowledge as gated markdown — a substrate for the LLM agent; grannie is the human read-port (plain-language, grounded answers).

QA & testing engineer — test strategy, E2E suites, integration testing, test infrastructure, flaky test triage

Plugin from ncaq/konoka

Property Management Operations specialist team — 4 agents (property-management-lead, occupancy-leasing-analyst, maintenance-operations-specialist, noi-financial-analyst), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A property-operations team for a property/asset manager accountable for occupancy, NOI, and resident retention — it reads occupancy as a leasing funnel plus renewals, treats delinquency as cash with an aging clock, manages unit-turn time as cost and retention, and scores the asset on NOI not gross rent. Inherits ravenclaude-core protocols.

A plugin that proposes commit messages.

Product track: refine, build, quick, announce and ask, with recon handoff, verified project memory and completed-task archives

Tech-quality track: audit+refactor and lint-audit+lint-fix, with verified project memory and safe completed-candidate/ladder archives

Streamlines creation of company internal communications (status reports, leadership updates, announcements) in standard formats using Claude's multi-agent capabilities.

Generates company-standard internal communications including status reports, leadership updates, and project announcements.