Skip to content

mehbylabs/creator-skills / skills/creator-character

creator-character

Flagged

Keep a person, mascot, or character consistent across many images and videos with whatever providers the user has. Builds a reusable character pack (reference sheet, anchor description, approved reference images) and reuses it in every generation; uses a Higgsfield Soul ID when available. Use when the user wants the same face or character in multiple images, a recurring mascot, a consistent AI influencer or presenter, "use my face", a character sheet, or a story with recurring characters. Not for one-off images (creator-image).

FileKindSize
SKILL.mdskill md3.3 KB
references/arabic-voice.mdmarkdown7.7 KB
references/audio.mdmarkdown3.4 KB
references/browser-aistudio-browser.mdmarkdown2.8 KB
references/browser-flow-browser.mdmarkdown4.5 KB
references/browser-gemini-browser.mdmarkdown4.8 KB
references/config.mdmarkdown2.5 KB
references/connect.mdmarkdown3.9 KB
references/image-prompting.mdmarkdown1.7 KB
references/media-ops.mdmarkdown2.4 KB
references/providers.mdmarkdown7.0 KB
references/video-prompting.mdmarkdown1.9 KB
scripts/connect.pyexecutablescript16.6 KB
scripts/creator.pyexecutablescript71.1 KB
scripts/media.pyexecutablescript15.7 KB

references/audio.md

View on GitHub
# Audio: voiceover, music, sound effects

## Voiceover (`creator.py speech`)

```bash
python3 scripts/creator.py speech --text-file script.txt --out vo.mp3 [--lang ar-EG] [--voice ID] [--style "warm, upbeat"] [--speed 1.05]
```

**Arabic or any Arabic dialect → read `arabic-voice.md` first** (script must be written in
the dialect; `--lang` picks dialect-aware routing and voices). **Add tashkeel to every word
whose meaning depends on its vowels before sending it to any TTS**; `speech` refuses Arabic
text with such words left bare (exit `5`), and `creator.py tashkeel-check --text-file F`
lists them ahead of time. Add `--verify` to transcribe the result back and list words the
voice read differently from the script (`verify` block in the JSON; `creator.py verify` checks
an existing file). Use it on every line of a long or fact-heavy script.

- Write for the ear: short sentences, numbers as words when ambiguous ("twenty twenty-six"),
  spell out acronyms you want letter-by-letter ("A-P-I").
- Long scripts: split into one file per scene/paragraph so retakes are cheap and the
  explainer can time scenes to audio.
- `--style` is delivery direction. Google TTS and OpenAI `gpt-4o-mini-tts` honour it;
  ElevenLabs ignores it (choose the voice instead; `eleven_v3` reads inline tags like
  `[whispers]`, `[laughs]`). Google also reads inline tags: `<short pause>`, `<laugh>`, `<sigh>`.

Voices:

| Provider | Default | Good alternatives |
|---|---|---|
| ElevenLabs | first voice in the account (set `voices.elevenlabs` in config) | list with `GET /v2/voices`; the legacy default voices retire Dec 31 2026 |
| Google | `Kore` | `Puck` (upbeat), `Charon` (deep, informative), `Zephyr` (bright), `Aoede`, `Fenrir`, `Leda`, `Orus`, `Enceladus`, `Sulafat` |
| OpenAI | `marin` | `cedar`, `coral`, `sage`, `ash`, `nova`, `onyx` |
| Google Cloud TTS | `Kore` | same names as Gemini; locale from `--lang` |
| Azure | per `--lang` country voice (e.g. `ar-EG-SalmaNeural`) | any `<locale>-<Name>Neural` |

Use the same provider + voice for every line of one project. If fallback switched provider
mid-project, regenerate the earlier lines on the new provider rather than mixing voices.

## Music (`creator.py music`)

```bash
python3 scripts/creator.py music --prompt "lo-fi hip hop, warm Rhodes, vinyl crackle, 80 bpm" --duration 60 --instrumental --out bed.mp3
```

Prompt with genre, instrumentation, tempo (bpm), mood, energy arc ("builds at 0:20").
Background beds under narration: always `--instrumental`, mixed by `media.py assemble`
(ducked automatically). Google's default `lyria-3-clip-preview` returns 30 s; pick
`lyria-3.5` in config for full-length tracks.

The router checks every track on disk: silent or truncated takes are thrown away and
retried; a track shorter than `--duration` (or over a provider cap, e.g. ElevenLabs 300 s)
is extended seamlessly to the exact length (`notes` in the JSON). Still listen once before
shipping: a check can prove a file has sound, not that the sound fits.

## Sound effects (`creator.py sfx`)

```bash
python3 scripts/creator.py sfx --prompt "whoosh transition, airy, fast" --duration 1.2 --out whoosh.mp3
```

Describe source, action, space, and length: "heavy wooden door creaks open in a stone hall".
`--loop` for ambiences.

## Licensing

Generated audio is subject to the provider's terms and the user's plan; mention this when
the user says the piece is for paid ads or broadcast.
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall