Havuz

Chinese AI video micro-expression and emotional acting prompt skill

Managing prompts，, skills, MCP tools & wallpaper for DeepSeek Harness

Drop-in instructions, prompts, and workflows to reduce token usage across Codex, Claude Code, GitHub Copilot, Cursor, and other AI coding ag

私教.skill — 输入任何想学的技能，蒸馏出一个带你从 0 学会它的有状态私教 skill

Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillat

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

Token-efficiency linter for LLM prompts and payloads

Sách miễn phí tiếng Việt về vibe coding cho Tester, PM, BA — người làm IT không viết code. 20 chương, 3 phụ lục, 54 hình. Học cách chỉ đạo A

An Agent Skill that makes any AI explain like Richard Feynman: mechanism before name, one honest analogy with its limits, and a ladder from

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

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

A single SKILL.md skill giving coding agents task-aware working modes (debug, fix, review, migrate, …) — works with Hermes, Claude Code, Cod

Open WebUI filter that defers MCP and builtin tool schemas until the model asks for them by name, cutting per-call prompt tokens

Seedance 2.5 视频分镜提示词生成 Skill for Agent | 把商业意图+素材转成可直接用的视频脚本prompt | Turn business intent + assets into ready-to-use Seedance 2.5 storyboard

Agents config for development

Local CLI for auditing AI agent skills, conflicts, duplicates, safety risks, and context cost across coding agents.

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

700-rule design library and 89-source reference atlas that stops Claude Code and other AI agents from building generic-looking websites

AI4S 科研 Agent 技能 | AI-for-Science research workflow skill for coding agents: literature review · experiment design · figures · paper reading

Comprehensive research co-pilot for Claude Code and claude.ai — 14 skills covering literature review, methodology, ethics review, data analy

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

Disciplined AI coding mode. Understand deeply, write minimally, never hallucinate, stay consistent. Based on Ponytail & LLM Wiki.

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)

A curated, safety-conscious collection of reusable Grok-compatible agent skills for workflow automation, research, integrations, and quality

Curated AI presentation prompt library — 120+ copy-ready PPT & slide prompts with real slide previews, 1-click copy and direct generate. Fil

短视频解析 · AI 剧本复刻 · 一键成片 | LangGraph 多 Agent 流水线

Penelopa.ai, Codex ve Claude Code oturumlarını analiz ederek coding agent iş akışlarını iyileştirmeye yönelik öneriler ve yeniden kullanılabilir çıktılar sunar.

Neden yükseliyor · Agent kullanımının artmasıyla oturumları analiz edip iyileştirme önerilerine dönüştürme fikri güncel bir ihtiyaca hitap ediyor. 24 günde 139 yıldız ve 71 commit ilgi ve yoğun geliştirme gösteriyor; ancak commitlerin tek yazardan gelmesi topluluk desteğine dair kanıtı sınırlıyor. Yükselişin kesin nedeni mevcut verilerden bilinmiyor.

Agent Dispatcher, Claude Code ve Codex için görevle ilgili kod bağlamını bulup uzman yönergeleri ve doğrulama adımlarıyla sunar.

Neden yükseliyor · 9 günlük yaşında 52 yıldız ve 108 commit dikkat çekiyor; ancak farklı yazar sayısı 1. Bu, yoğun geliştirme ve erken ilgi gösterir, bağımsız benimseme veya olgunluk kanıtı değildir.

Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor,

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with d

AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.

Opus에 근접한 품질을 Sonnet 단가에 — 가성비 AI 운영 모델을 직접 구축한 Claude Code 프로젝트

可同时输入多个初版提示词，开启多轮自动优化，连续得到高分后得到最终结果。

让 Agent 的工作方式可组合、可审查、可持续改进，最终实现 Agent Self Evoling。 DeepSeek Harness Web plugin with composable task controls and isolated, human-reviewed s

🪼 Lagune AI is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).

Global instructions for coding agents: evidence, parallelization, validation, all in one AGENTS.md / CLAUDE.md

Local-first Chrome extension that turns images into generator-ready prompts.

Codex skill for analyzing still images and writing restrained, image-specific motion prompts.

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development

Goal-based planning and proof gate for AI coding agents

Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком

Nano Banana Pro prompts: tested prompt recipes with example renders, aspect ratios, the model id (gemini-3-pro-image-preview) and the cost e

Top 10 Claude Prompt Optimization Frameworks 2026

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

Private Skill distribution platform for AI coding agents: publish, install, update, and rollback team skills across Cursor, Claude Code, Cod

HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explici

⚡ Unit tests for AI. Test prompts, compare models, save money.

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforce