← All topics

Prompting

Prompt engineering, system prompts, and reusable patterns.

452 posts

Claude Skill 7

here you can create prompts for your own purpose on point which need mimimal changes

Python Apache-2.0 Updated 3w ago
Claude Skill 2

Claude Code skill that stops prompt-cache thrash: -88% token burn in image-heavy agent sessions, with an audit script that shows exactly whi...

JavaScript MIT Updated 1mo ago
Claude Skill 15

面向 Seedance 的 AI 短剧分镜 Agent Skill:把已审核剧本与资产转换为可执行的视频提示词表。

Python MIT Updated 1mo ago
Claude Skill 2

Codex skill for turning Chinese scripts and SRT subtitles into VOX-style editorial paper-collage storyboards and Google Flow prompts.

Python MIT Updated 1mo ago
Claude Skill 2

You are a different collaborator on every project. Your session history already knows. Reads your local Claude Code / Codex history and writ...

TypeScript MIT Updated 4w ago
Claude Skill 10

Restyle any ad into any visual style with one prompt — free Claude skill for Google Omni Flash video-to-video.

AGPL-3.0 Updated 1mo ago
Claude Skill 24

Agent-native design skill: ordinary prompts -> verified HTML-first prototypes, decks, dashboards, motion demos, and export-ready visuals.

HTML Apache-2.0 Updated 1mo ago
Claude Skill 6

A terminal script manager and launcher — Put any script, prompt, or program in one library; skit turns its inputs and flags into a TUI menu,...

Python MIT Updated 3w ago
Claude Skill 4

Official MutagenT skills for AI coding agents — Claude Code plugin marketplace for prompt optimization, evaluation, and observability.

Shell MIT Updated 4w ago
Claude Skill 1

Growth marketing skills for Claude Code, Cursor, and any AI agent: SEO, CRM, marketing automation, inbox triage, and pre-launch QA. Paste on...

Python MIT Updated 1mo ago
Claude Skill 2

Staff-level, evidence-backed release audits for vibe-coded apps, with real-flow testing, hard vetoes, fix prompts, and same-rubric retests....

Python MIT Updated 3w ago
Claude Skill 2

Claude Code skill: interviews you to turn a rough task idea into a high-level prompt (outcome + guardrails + self-verification) and picks th...

Shell MIT Updated 1mo ago