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/browser-aistudio-browser.md

View on GitHub
# Playbook: Google AI Studio speech (computer use)

`https://aistudio.google.com/generate-speech` — Google's web playground for Gemini TTS.
Same voices and models as the API, usable with just a Google sign-in. Best manual route for
Arabic dialect voiceovers when the user has no `GEMINI_API_KEY`.

## Rules

- Navigate by snapshot/screenshot; control names below are hints and may change.
- Never type passwords or solve CAPTCHAs; ask the user to sign in.
- One scene/paragraph per generation so retakes are cheap.
- Verify the downloaded file (duration > 0) before reporting success.

## Steps

1. Open the URL; confirm the account is signed in and the speech page is showing.
2. Choose the model (the highest-quality Flash TTS offered) and **single-speaker** mode
   (multi-speaker only for dialogues with exactly two named speakers).
3. Pick the voice: the configured `voices["google-api:<lang>"]` if set, else audition 2–3
   voices on the first line and let the user choose. Designed voices (`voice_…`) appear in
   the user's library.
4. Style / instructions box: paste the delivery direction, e.g.
   `Speak in natural, native Egyptian (Cairene) Arabic with authentic colloquial pronunciation. Warm, upbeat, conversational.`
5. Paste the script text exactly as approved (dialect-spelled; see `arabic-voice.md`).
6. Run, listen in-page if possible, then download the audio.
7. Move it into place: `python3 scripts/creator.py adopt --src ~/Downloads/<file> --out vo/01.wav`.
8. Repeat per paragraph with the **same** voice and style text.

## Notes from production use (late 2026 UI)

- The speech playground: "Create new dialog" → a speech block with **Speaker**, **Style**
  and **Expression** chips. Type the style description in the Style popover and press
  Enter; it persists for the session.
- Voice picker: the "Speaker settings" card opens a library of 2,000+ voices grouped by
  use case. Trusted clicks often miss the voice rows; a JS `.click()` on the voice's
  `<button>` works. Confirm via the "Current voice" label.
- For dialects, **audition several voices** with the same line and style text. The voice
  matters as much as the prompt. For Tunisian, "Sami" scored 8.5/10 with a native-dialect
  judge, versus 6.5 (Rami) and 4 (Knox).
- The flagship model has a per-account daily quota. On a quota dialog, switch the model
  to the Flash Lite TTS, which has its own quota, or use another signed-in account
  (`/u/1/` URLs).
- **Voice Design and Voice Replication need a paid API key with billing linked**. Don't
  set up billing without the user's consent.

## Voice design (optional, once per dialect)

Open the Voice Design area, describe the speaker (age, city/region, accent, tone, pace),
generate, audition, save. Copy the `voice_…` id into config
`voices["google-api:<lang>"]` so API runs use the same voice later.
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