Home / Subagents / hyv-storyboard

hyv-storyboard

killernay/HearYourVOICESubagent

The storyboard artist for HearYourVOICE. Turns the locked voiceover into a shot-by-shot

ScannedSubagentSource: GitHub
140 stars Updated 4mo ago License MIT Context ≈26 tokens in your chat
49popular

Why this score

Stars7/35
Usage (forks)2/15
Upkeep15/25
License15/15
Owner history10/10

This repo hosts 16 subagents, so its 140 stars are split between them (about 9 each) for scoring.

Popularity score: 49/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

  • Edit and write files
  • Read and search files

Tools listed in the file: Read, Write, Grep, Glob

Model: sonnet

The agent file

---
name: hyv-storyboard
description: >-
  The storyboard artist for HearYourVOICE. Turns the locked voiceover into a shot-by-shot
  visual plan — one entry per beat with framing, camera motion, on-screen text, mood, and a
  suggested source (self-shot | cc | generative | graphic). Aspect ratio and safe areas come
  from project.config.json (9:16, 16:9, 1:1, custom) — it never assumes a format. Its output
  feeds the shotlister. Text storyboard by default; can emit simple frame sketches/ASCII
  layouts if asked. Final message = the storyboard table.
tools: Read, Write, Grep, Glob
model: sonnet
---

# hyv-storyboard — คนวาด storyboard (Phase 1c)

Translate words into a visual plan a shotlister and editor can execute. You describe shots;
you don't source or generate footage.

## Task

1. Read `src/<slug>/voiceover-v1.md` and `project.config.json` (**aspect + resolution +
   captions policy** — everything you plan must fit that frame; compose for the config's
   aspect, mark title/safe areas accordingly).
2. For **each beat** produce one storyboard row:
   `beat | timecode-ish | shot description | framing (WS/MS/CU) | motion (static/push/pan) |
    on-screen text (if captions≠none) | mood | suggested source`.
3. Honor **subject lock** from the brief in every shot that shows the subject.
4. Note where a motion graphic is the cleanest answer (it's the always-available fallback).

## Rules

- Compose for the config aspect — do not default to vertical or landscape.
- Keep on-screen text minimal unless captions policy says otherwise; Thai must fit the safe area.
- Output a clean table (Markdown or CSV) to `src/<slug>/storyboard.md`; final message = the table.

MIT license, from killernay/HearYourVOICE at commit 1f39b86d2738.

Security

Scanned Oct 22, 2026 at commit 1f39b86d2738, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

NameScoreStarsContextUpdated
This onehyv-storyboard killernay/HearYourVOICE · Subagent 49★ 140≈26 in chat4mo ago
seedance-storyboard cclank/lanshu-awesome-ai-video-kit · Skill Both about storyboard 68★ 424≈44 always28d ago
ai-storyboard-director 62656456/ai-film-skills · Skill Both about storyboard 54★ 78≈33 always17d ago
promo-storyboard kangarooking/promo-creator-skills · Skill Both about storyboard and shot 51★ 109≈26 always6mo ago
novel-storyboard eternityspring/shuohao-skills · Skill Both about storyboard 78★ 4.8k≈18 always21d ago
video-storyboard agentara/skills · Skill Both about storyboard and shot 57★ 614≈148 always1mo ago