Havuz

江南 × 烽火戏诸侯文风蒸馏 Agent Skills（Claude Code/Codex/Cursor/Trae/Antigravity 通用）｜1465万字语料实证 + 自动风格审计 + 独立盲测 95/100·A

Curated PRD prompts that turn a spec into a fully working, mock-data-driven frontend prototype with one AI coding assistant run.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently ro

3,400+ curated AI prompt templates with auto-optimization. Works with OpenClaw, Claude Code, Cursor, Gemini CLI, and any AI. One command to

Prompt builder for Krea-2 in ComfyUI. Fill structured fields and get flowing prose in the format the model expects, not a keyword list.

Multi-agent engineering with cold review, artifact validation and resumable run state.

AI生图提示词模板库，按角色与模板分类整理，包含写实cos、漫展场景、镜头、灯光、材质和负面词模板

Reverse-engineer how you think, talk, and make decisions — then turn it into a stress-tested AI System Prompt. Works on any LLM. Full pipeli

Audits Claude-directing artifacts (CLAUDE.md, SKILL.md, subagent, hook, MCP, prompts, api_config) against 189 cited Anthropic rules across 1

Arming AI with Marxist methodology for deep structural analysis

20 production-ready AI prompts optimized for n8n workflows. Copy-paste system prompts with model recommendations, cost estimates, and integr

Exploring agent "thinking" animation.

Agents config for development

Build AI agents using the same architecture patterns as Claude Code. Skill + 6 examples + runnable Python code. No framework.

Claude Code workflow for mapping projects into clean-room behavior docs, file maps, batch reports, verification, and rebuild-ready blueprint

Plugin-first AI terminal workspace for Codex and Claude Code with planning, CI/CD debugging, reusable agents, skills, TODOs, and MCP tool in

Readable agent skills with optional declarative YON protocols you can inspect and validate. A personal, field-used pack by Alexandru Mares.

ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, re

Skills for AI agents, built from real work: a working discipline plus playbooks for planning, shipping, documents, images, video and sales.

Claude Code skill: turn raw requirements, engineering PRDs (incl. Feishu docs), or competitor analysis into a concise, coding-agent-ready PR

Plan, build, review, and ship to the real world. Full opinionated harness with built-in Project Management and DevSecOps to code and maintai

Postmodernist critique skill for Claude and Codex. Pressure-test AI-generated strategy and marketing slop. Debug reality.

针对中文AI编程的Top 20 提示词，做skill用于辅助codex/claude生成代码

Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD met

Reverse-engineer any video into a production-ready prompt for Veo, Sora, Seedance, Kling, and Runway. Powered by Google Gemini, runs in your

Six Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.

Chinese template for designing Multica multi-agent + skill workflows around task type, budget, models, and verification gates.

A methodology so aggressive it demands to be replaced.

AI film-production skill pack for Claude Code and OpenAI Codex: 11 creator-* skills from screenplay to final cut, with a recorded production

Diagnosis-first Agent Skills that turn AI from answer machine into learning tutor.

Prompt optimizer for Claude Fable 5, built as a claude.ai Project — 43 source-backed rules, complexity routing, and API parameter recommenda

A minimalist yet powerful prompt engine crafted for seamless AI execution. Engineered to bridge the gap between simple inputs and sophistica

A personal AI intelligence system for solo builders. Filter daily AI noise against your active projects using AI.

Claude Code skill for adversarial AI code & plan review. One AI writes, another tears it apart. Iterative fix loop until approved.

Make It Right — constraint-first backend reliability skills for AI coding agents. 3 tiers (generic → runtime → framework) across 9 runtimes;

AI reasoning skills distilled from 4,665 real Claude Fable 5 chain-of-thought traces. Mathematically tuned. Grade A (100%) emulation accurac

A portable agent skill (SKILL.md + reference playbooks) for writing top-conference embodied-AI papers — distilled from 63 papers (CoRL/RSS/I

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.

The recursive self-improvement loop for your skills (including itself) — runs a retro after every session and turns corrections into permane

Installable Codex/AgentSkills workflow pack for dev, Agent/RAG, API/data, Office artifacts, research diagrams, and authorized security revie

Generate a production-ready, best-practice Claude Code harness tailored to your use case in minutes -- at any skill level. Or validate, upda

The canonical standard for building production-grade agentic products — autonomy × oversight, composition patterns, the 9-layer harness, a 3

Typed evaluation for OpenCode skills and AI agents: capability, regression and product checks; provider-neutral evidence grading, provenance

A strategic-reasoning AI tuned to the Hammerstein framework. Portable system prompt + retrieval. The framework survives the model.

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code,

A benchmarking suite for Agent Skills (SKILL.md files) that measures whether a skill actually improves LLM output quality, and by how much.

AI 漫剧 / MV 端到端制作流水线 Skill 套装 · 1 小时出方案，180 元跑成片 (Claude Code Skills)

Prompt Engineering skill for Claude Code — rewrites and optimizes prompts using proven techniques (Anthropic, OpenAI, Gemini, The Prompt Rep