MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It addresses a specific niche need for content creators to quickly generate attention-grabbing hooks tailored to tech/AI videos, with flexible language, count, character limit, and emotional style options.
Who it is for
- Content creators making short tech/AI videos
- Video editors needing quick hook variations
- Social media managers optimizing reels/shorts
- AI tool developers promoting their products
Use cases
- Creating cold opens for tech tutorials
- A/B testing hook styles (curiosity, fear, etc.)
- Generating bilingual or Chinese-only hooks
- Producing multiple hook variants for the same video
Strengths
- Supports English, Chinese, and bilingual outputs
- Customizable count (10-30), max characters, and emotional style
- Open source (MIT license) and installable via npx or monorepo
- Specifically scoped to tech/AI, ensuring relevant hooks
Considerations
- Only for the first 1-3 seconds of videos
- Scoped strictly to tech and AI content
- Requires installation via npx skills add or monorepo setup, with no standalone examples in the README
README quick start
Subtitle Hooks
Generate first-3-second on-screen subtitle hooks for short tech/AI videos (many variants).
中文简介： 你写科技向短视频前 1–3 秒的画面字幕钩子。 — 详见 README.zh.md.
What this skill does
- You write punchy on-screen hooks for the first 1–3 seconds of tech videos
- Scope: AI tools, coding, productivity, gadgets
- Deliverable: See SKILL.md deliverable.
- Triggers: subtitle hooks, cold open text, hook lines, 前三秒字幕, reel hooks.
Install
After this package is on GitHub:
npx skills add / --skill subtitle-hooks
Local monorepo: point your agent at skills/subtitle-hooks/ (this folder).
Options
| Option | Values | Default |
|---|---|---|
lang | en · zh · bilingual | en |
count | 10 · 20 · 30 | 20 |
max_chars | 18 · 24 · 32 (EN soft); ZH 12·16·20 | EN 24 / ZH 16 |
style | curiosity · contrarian · result · fear · identity · mix | mix |
Runtime output language follows lang (default en). Skill docs stay EN-primary.
When to use
| Use | Don't |
|---|---|
| (see bullets) | (see bullets) |
Use
- When you need
subtitle-hooksworkflow
Don't
- Out-of-scope tasks listed in SKILL.md
Deliverable
See SKILL.md deliverable.
Full workflow, hard rules, and QA: see SKILL.md.
Example
Monorepo sample (if present): ../../output/samples/subtitle-hooks-example-01.md
License
MIT — see LICENSE.
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.