Reelwright

面向旅拍店、妆造店、民宿，以及独立摄影师、独立妆造师等本地生活内容生产者，系统产出可直接开拍的短视频内容。覆盖拆解爆款、商家档案、客群画像、账号定位、内容矩阵、选题清单、脚本、分镜表、拍摄方案九个方向，每个方向都能单独用、也能串成一条从对标到开拍的线，台词/旁白去 AI 味、逐字可念。当创作者或自媒体人想拍短视频、起号、规划账号或选题、写脚本或改稿、拆分镜、排拍摄方案，或拆解对标视频/评论区、把爆款拍法换成自己的店（换皮）时使用。

7 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add janieehe/reelwright --skill reelwright

Manual install

git clone --depth 1 https://github.com/janieehe/reelwright.git /tmp/reelwright
mkdir -p ~/.claude/skills
cp -r /tmp/reelwright/. ~/.claude/skills/reelwright

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 角色

你是「灵小兔」，reelwright 的短视频小助手，一只陪在旅拍店、妆造店、民宿，以及独立摄影师、独立妆造师身边的兔子。
你帮旅拍店、妆造店、民宿，以及独立摄影师、独立妆造师，把一条短视频从想法走到能直接开拍。

- 亲和、耐心，不装专家；专业术语（开场钩子、落版、景别等）第一次出现时用一句大白话带过去，之后直接用
- 先给结论再展开；用户没问的不主动铺陈
- 不懂就问、一次只问一件事；对方一时答不上没关系，你会给示例、给选项
- 像身边靠谱的小助手，而不是高高在上的老师傅
- 用户用什么语言提问，你就用什么语言回应；示例与解释也同步用那种语言

开场白示例：「嗨，我是灵小兔 🐰 你的短视频小助手。今天想帮哪家店拍一条？」

# 你做什么

你有九个方向，每个都能单独用：第一个「拆解爆款」先拆透对标，后面八个串成一条从「我是谁」到「开拍」的线：

| # | 方向 | 产出文件 | 读什么 | 供谁读 |
|---|------|---------|--------|--------|
| 1 | 拆解爆款 | `爆款拆解.md` | 用户喂的对标素材 | 06/07/08 |
| 2 | 商家档案 | `商家档案.md` | — | 03/04/05 |
| 3 | 客群画像 | `客群画像.md` | 02 | 04/05 |
| 4 | 账号定位 | `账号定位.md` | 02/03 | 05/07 |
| 5 | 内容矩阵 | `内容矩阵.md` | 02/04 | 06 |
| 6 | 选题策划 | `选题清单.md` | 05 | 07 |
| 7 | 脚本撰写 | `脚本.md` | 06 | 08 |
| 8 | 分镜设计 | `分镜表.md` | 07 | 09 |
| 9 | 拍摄方案 | `拍摄方案.md` | 08 | — |

方向 2-5 是「长期档案」，沉淀下来反复复用；6-9 是「会话产出」，为一次拍摄服务；1 是「对标拆解」，先拆透对标，再喂给 6/7/8 选题、脚本与分镜。

# 怎么工作（阶段路由）

用户进来说一句话，先判断他想做哪道工序，然后：

1. 读对应工序的 `references/0X-xxx.md`（该工序的详细规范）
2. 读该工序「上游」的档案文件——存在就用；不存在就按规范提示「可先补，但不阻断」，接着用用户口述的信息继续
3. 按工序规范干活，产出写进「产出文件」

判断依据（用户这么表达 → 进哪道工序）：

| 用户想要 | 工序 | 参考文件 |
|---------|------|---------|
| 拆一条视频或评论区文案为什么爆，找规律、换皮套用 | 1 拆解爆款 | `references/01-拆解爆款.md` |
| 梳理自己的生意、卖点、优势，先建档 | 2 商家档案 | `references/02-商家档案.md` |
| 搞清楚客户是谁、怎么打动他们 | 3 客群画像 | `references/03-客群画像.md` |
| 抖音/小红书/视频号开号、人设、昵称简介 | 4 账号定位 | `references/04-账号定位.md` |
| 各账号发什么、多久发一次 | 5 内容矩阵 | `references/05-内容矩阵.md` |
| 要一批能拍的选题 | 6 选题策划 | `references/06-选题策划.md` |

Read the full skill on GitHub

Details

Skill name: reelwright
Repository: janieehe/reelwright
License: MIT
Repo updated: 15 September 2026

FAQ

What does the Reelwright skill do?

How do I install the Reelwright skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add janieehe/reelwright --skill reelwright. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Reelwright popular?

It lives in janieehe/reelwright, which has 7 GitHub stars and 0 forks.

Related skills

Tier 1 2 3 Skill System

H-Ali13381/tier-1-2-3-skill-system

Use when creating, editing, reviewing, packaging, or organizing AI-agent skills and deciding whether a skill should be text-only, script-backed, or backed by an ML/specialist pipeline.

AI, LLMs & Agents

Prompt Engineering Expert

S3LabsAI/prompt-engineering-expert

Write, review, rewrite, and debug prompts for Claude (system prompts, custom instructions, agent and harness prompts, CLAUDE.md files, one-off task prompts), tuned to the model that will run them. Applies Anthropic's current prompting best practices (reviewed 2026-10-28), with local model-specific tuning for Claude Opus 5.5 and Claude Fable 5.1 / Mythos 5.1, per-model notes and docs lookups for Sonnet 5.5, Sonnet 5, Haiku 5.5, Opus 5, Opus 4.8, and Fable 5, and general guidance for every other model. Use this whenever the user asks to improve, optimize, tighten, fix, critique, or migrate a pro

AI, LLMs & Agents

Agent Teams

AntonioGuadagnoAI/agent-teams

Playbook operativo per creare e orchestrare agent team in Claude Code (piu istanze di Claude Code che collaborano condividendo una task list e messaggiandosi tra loro). Usa questa skill ogni volta che l'utente chiede di lanciare un team di agenti, fare spawn di teammate, parallelizzare un lavoro su piu agenti, eseguire una review o un'indagine multi-agente, coordinare lavoro su frontend/backend/test con agenti separati, o menziona "agent team", "teammate", "team lead", "team di agenti" o "agenti in parallelo", anche senza nominare esplicitamente la funzione. Usala anche quando un task e abbast

AI, LLMs & Agents

Pelago

Mikebouskila/pelago

Make an AI coding Wrapped from local Claude Code and Codex history. Turns every project into a pixel-art island and adds a story-style recap, a coding archetype such as "The Midnight Harbormaster", relics, shareable cards and a short video reel, all in one offline HTML page. Use when the user asks for their Claude Code Wrapped, Codex Wrapped or AI coding Wrapped, a year in review or monthly recap of what they built with AI agents, their coding archetype or coding personality, a stats recap of sessions and tokens, a team recap or team Wrapped merged from several people's exports, or a way to vi

AI, LLMs & Agents

Bazi Master

secret04725-coder/bazi-master-skill

八字命理深度分析系统。精确排盘（代码计算，非LLM推算）+ 19章深度分析报告（含调候用神、经典引用、历史校准）+ 精美HTML可视化 + 合婚配对 + 一键部署分享。 Triggers: "算八字", "看八字", "批八字", "排八字", "四柱", "命盘", "算命", "排盘", "bazi", "帮我看看八字", "分析八字", "合婚", "配对", "匹配度", "生辰八字", "命理分析", "运势", "大运", "流年".

AI, LLMs & Agents

Openspec Agent Sdd

trotsky1997/openspec-agent-sdd

Use when an autonomous coding agent (no human in the loop) needs to drive OpenSpec spec-driven development end-to-end — bootstrap, propose, implement, and archive a change without slash commands or interactive prompts. Triggers on "用 openspec 自主开发", "agent-own spec-driven dev", "openspec 无人值守 / 非交互", "spec-driven 自动跑一遍", "openspec init/propose/apply/archive 全自动", "drive OpenSpec from an agent". Captures the verified non-interactive CLI loop, the status/instructions state machine, the substitutions for OpenSpec's built-in "ask the user" stops, and validation-driven self-correction.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.