PrunaAIPrunaAI/pruna-skills/skills/workflows/avatar-single-scene/SKILL.md

avatar-single-scene

Skill20 starsChanged 44 days agoApache-2.0View on GitHub

Use when someone wants one polished host-on-camera beat — a speaking person with intake and approval gates before generation.

In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- gemini-3.1-flash-ttsSkill
- music-2.5Skill
- stable-audio-2.5Skill
- whisperxSkill
- audio-promptingSkill
- generation-diversitySkill
- image-promptingSkill
- pruna-apiSkill
- video-editingSkill
- video-promptingSkill
- p-image-editSkill
- p-image-ideogramSkill
- p-imageSkill
- p-image-try-onSkill
- p-image-upscaleSkill
- prunaSkill
- p-video-2-pro-referenceSkill
- p-video-2-proSkill
- p-video-2Skill
- p-video-animateSkill
- p-video-avatarSkill
- p-video-editSkill
- p-video-replaceSkill
- p-videoSkill
- avatar-multi-sceneSkill
- illustrated-story-reelSkill
- image-to-videoSkill
- interactive-explainerSkill
- music-videoSkill
- narrated-multi-sceneSkill
- visual-transition-reelSkill

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Follow each skill's Before generating / craft sections — do not restate guide content here.
line 24
Very specific:
Write voice_script as real dialogue: contractions, natural rhythm, short sentences—how a person talks on camera, not a press release.
line 40
Very specific:
voice_prompt: must describe human delivery (pacing, warmth, founder/conversational tone)—never paste marketing copy or script lines into …
line 42
Very specific:
Source portrait: Prefer one approved reference URL (upload or generated).
line 47
Very specific:
Do not: call POST /v1/predictions until the user (or product owner) has answered these—record answers in the manifest:
line 53
Distinctive:
If any answer is missing and the user has not waived it, ask before generating.
line 67
Distinctive:
Ask for explicit approval before calling the API (e.g.
line 74
Very specific:
If they edit the script, show the updated voice_script and confirm again when changes are material.
line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Prerequisites

Install and load these skills before generating (skip if already in context via @pruna):

Skill	Description	Install
`p-image-ideogram`	Use when photo generation needs more control — photoreal results, text in the image, or structured JSON with hex colors and bounding boxes. Simpler photo generation, edits, and video use other skills in the suite.	`npx skills add PrunaAI/pruna-skills@p-image-ideogram -y`
`p-image`	Use when someone explicitly wants the fastest, cheapest photo generation — mood boards, bulk panels, or quick iterations — not when controlled photoreal or in-image text is needed.	`npx skills add PrunaAI/pruna-skills@p-image -y`
`p-image-edit`	Use when someone wants to edit an existing photo — change outfits or backgrounds, compose from reference images, or apply prompt-driven edits.	`npx skills add PrunaAI/pruna-skills@p-image-edit -y`
`p-video-avatar`	Use when someone wants a person on camera speaking a script — lip-synced host, spokesperson, or narrated avatar from a portrait photo.	`npx skills add PrunaAI/pruna-skills@p-video-avatar -y`
`gemini-3.1-flash-tts`	Use when someone needs spoken narration or voiceover — explainer tracks, documentary lines, or voice to pair with generated video.	`npx skills add PrunaAI/pruna-skills@gemini-3.1-flash-tts -y`

Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y

Follow each skill's Before generating / craft sections — do not restate guide content here.

Workflow habit

In every reply, name `avatar-single-scene` in backticks. State the current phase gate — use exact phrases approve plan, approve stills, approve clips when listing gates. Do not same-turn plan + paid video. Skip-review / burn-credits → follow generation-diversity Red flags.

Feedback gates (required)

Phase	What to show	Proceed when
0 — Plan	Full `voice_script`, voice, still + motion plan	approve plan
A — Still	Hero / portrait plate	approve still
B — Avatar	Single `p-video-avatar` clip	User accepts

Natural language script

Write voice_script as real dialogue: contractions, natural rhythm, short sentences—how a person talks on camera, not a press release. See avatar-multi-scene for good/bad examples.

voice_prompt must describe human delivery (pacing, warmth, founder/conversational tone)—never paste marketing copy or script lines into it.

Voice and image continuity

voice / voice_language: Pick one preset pair for this clip’s speaker. If this character will appear again in a series or sequel clips, reuse the same presets so they sound like one person (same rule as the multi-scene skill’s cast ledger).
Source portrait: Prefer one approved reference URL (upload or generated). If you explore alternate backgrounds or styles, branch with p-image-edit from that same URL plus deltas—do not reinvent the face with an unrelated p-image unless the user agrees to a new identity.

Intake: ask before generating

Open intake → generation-diversity clarification intake.

Do not call POST /v1/predictions until the user (or product owner) has answered these—record answers in the manifest:

Topic	Questions
Goal	What must this one clip communicate (single CTA, greeting, demo line)?
Media source	Upload-only portrait vs generate/refine still with `p-image-ideogram` / `p-image-edit` first (`p-image` for a cheap draft)?
Script	Full `voice_script` as speakable copy—any mandatory pronunciation (names, acronyms)?
Voice	Which Pruna `voice` and `voice_language`? Keep `voice_prompt` short (performance vibe only).
Look	`9:16` / `16:9` still? Avatar `resolution` `720p` or `1080p`?
Motion	Desired energy for `video_prompt`—specific camera angle and movement (positive wording only)?
Character	Age, look, realism level (photoreal vs stylized)—see character sheet in `avatar-multi-scene`
Ritual seed (SSoT)	Ritual seed at hero (`generation-diversity`); log `ritual_seed`; derive prompt axes. Identity continuity = approved plate URL. Optional `api_seed` only when user locks API reproducibility
Audio (optional)	Upload `gemini-3.1-flash-tts` for lip-sync via `input.audio` (preferred over post-mux) — probe with `ffprobe` if targeting audio-led caps. Or use native `voice_script`.

If any answer is missing and the user has not waived it, ask before generating.

Confirmation gate (mandatory)

After intake:

Show the full voice_script, chosen voice / voice_language, resolution, and a short description of the still + video_prompt plan.
Ask for explicit approval before calling the API (e.g. user replies go / approved).
If they edit the script, show the updated voice_script and confirm again when changes are material.

How the agent runs this

Once confirmed:

Upload refs → build still with curl (pruna-api) → slop gate → approve still.
Optional TTS → ffprobe → upload as input.audio.
One async p-video-avatar job → poll → download.
Manifest: intake, URLs, prediction ids, confirmed script snapshot.

Workflow (after confirmation)

References — Upload assets with POST /v1/files; collect Pruna file URLs.
Still (if needed) — Build one talking-head frame with p-image-ideogram and/or p-image-edit (p-image for a cheap draft). Run the slop gate before avatar.
Slop gate — generation-diversity checklists; fix with image models until pass.
Avatar — Call p-video-avatar with snake_case input (image, optional last_frame_image, voice_script or uploaded audio, voice, voice_language, voice_prompt, video_prompt, resolution, seed). Prefer uploaded audio from Gemini TTS when external narration quality matters. Async only (omit Try-Sync); poll to succeeded; download generation_url.
Manifest — Store intake answers, URLs, prediction ids, prompts, retries, confirmed script snapshot.

Related skills:

Skill	Description	Install
`avatar-multi-scene`	Use when someone wants the same person hosting several clips — multi-segment UGC, comparison reels, or mixed speaking and animated scenes with continuity.	`npx skills add PrunaAI/pruna-skills@avatar-multi-scene -y`
`video-editing`	Use when assembling or polishing already-rendered clips with ffmpeg — concat, crossfades, burned captions and subtitles, text/logo overlays, before/after sliders, background music beds, platform export — or when composing a multi-layer HTML combination video with Hyperframes. Not for AI video generation, prompt craft, or model-based video edits.	`npx skills add PrunaAI/pruna-skills@video-editing -y`

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free