Not in the top 1,000 by GitHub stars
PrunaAI/pruna-skills
Agent skills and plugins to give your agents access to Pruna API and generation workflows.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/audio/gemini-3.1-flash-tts/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/audio/music-2.5/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/audio/stable-audio-2.5/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/audio/whisperx/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/guides/audio-prompting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/guides/generation-diversity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/guides/image-prompting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/guides/pruna-api/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/guides/video-editing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/guides/video-prompting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/image/p-image/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/image/p-image-edit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/image/p-image-ideogram/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/image/p-image-try-on/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/image/p-image-upscale/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/suite/pruna/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video-2/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video-2-pro/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video-2-pro-reference/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video-animate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video-avatar/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video-edit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/video/p-video-replace/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/avatar-multi-scene/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/avatar-single-scene/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/illustrated-story-reel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/image-to-video/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/interactive-explainer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/music-video/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/narrated-multi-scene/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
skills/workflows/visual-transition-reel/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1a69de9103de → 1a69de9103de
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1a69de9103de
No earlier version was observed for comparison.
Verified commit 1a69de9103def138809123e2390f8e8f615d5cc1
git clone --filter=blob:none --no-checkout https://github.com/PrunaAI/pruna-skills.git .hotskills/prunaai-pruna-skills && git -C .hotskills/prunaai-pruna-skills checkout --detach 1a69de9103def138809123e2390f8e8f615d5cc1
# Copy each selected skill directory from .hotskills/prunaai-pruna-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/PrunaAI/pruna-skills.git .hotskills/prunaai-pruna-skills && git -C .hotskills/prunaai-pruna-skills checkout --detach 1a69de9103def138809123e2390f8e8f615d5cc1
# Copy each selected skill directory from .hotskills/prunaai-pruna-skills into .agents/skills/<skill-name>/Heat
1.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- gemini-3.1-flash-tts
skills/audio/gemini-3.1-flash-tts - music-2.5
skills/audio/music-2.5 - stable-audio-2.5
skills/audio/stable-audio-2.5 - whisperx
skills/audio/whisperx - audio-prompting
skills/guides/audio-prompting - generation-diversity
skills/guides/generation-diversity - image-prompting
skills/guides/image-prompting - pruna-api
skills/guides/pruna-api - video-editing
skills/guides/video-editing - video-prompting
skills/guides/video-prompting - p-image
skills/image/p-image - p-image-edit
skills/image/p-image-edit - p-image-ideogram
skills/image/p-image-ideogram - p-image-try-on
skills/image/p-image-try-on - p-image-upscale
skills/image/p-image-upscale - pruna
skills/suite/pruna - p-video
skills/video/p-video - p-video-2
skills/video/p-video-2 - p-video-2-pro
skills/video/p-video-2-pro - p-video-2-pro-reference
skills/video/p-video-2-pro-reference - p-video-animate
skills/video/p-video-animate - p-video-avatar
skills/video/p-video-avatar - p-video-edit
skills/video/p-video-edit - p-video-replace
skills/video/p-video-replace - avatar-multi-scene
skills/workflows/avatar-multi-scene - avatar-single-scene
skills/workflows/avatar-single-scene - illustrated-story-reel
skills/workflows/illustrated-story-reel - image-to-video
skills/workflows/image-to-video - interactive-explainer
skills/workflows/interactive-explainer - music-video
skills/workflows/music-video - narrated-multi-scene
skills/workflows/narrated-multi-scene - visual-transition-reel
skills/workflows/visual-transition-reel
How it works
gemini-3.1-flash-tts
When your agent uses it
Use when someone needs spoken narration or voiceover — explainer tracks, documentary lines, or voice to pair with generated video.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,659 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- When NOT to use
- Environment
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
../../../.claude-plugin/marketplace.jsonasset10,257 bytes../../../.claude-plugin/marketplace.jsonasset10,257 bytes../../../.claude-plugin/marketplace.jsonasset10,257 bytesSKILL.mdcore6,110 bytesSKILL.mdcore6,110 bytesSKILL.mdcore6,110 bytesSKILL.mdcore6,110 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.View the complete source on GitHubmusic-2.5
When your agent uses it
Use when someone wants an original AI song with vocals — sung lyrics, a style prompt track, or source audio for a music video.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,349 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- When NOT to use
- Environment
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore4,932 bytesSKILL.mdcore4,932 bytesSKILL.mdcore4,932 bytesSKILL.mdcore4,932 bytesSKILL.mdcore4,932 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubstable-audio-2.5
When your agent uses it
Use when someone wants light instrumental background music — an ambient bed under dialogue or underscore for reels and explainers.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,225 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- When NOT to use
- Environment
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore4,613 bytesSKILL.mdcore4,613 bytesSKILL.mdcore4,613 bytesSKILL.mdcore4,613 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubwhisperx
When your agent uses it
Use when someone needs word-level timestamps from audio — lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,192 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- When NOT to use
- Environment
- HTTP / pipeline
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore4,682 bytesSKILL.mdcore4,682 bytesSKILL.mdcore4,682 bytesSKILL.mdcore4,682 bytesSKILL.mdcore4,682 bytesSKILL.mdcore4,682 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
## Agent habitView the complete source on GitHubaudio-prompting
When your agent uses it
Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
1,888 tokensWhen the skill is activated
Reference documents
3,754 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- When to use
- Works with
- When NOT to use
- Guide habit
- Before generating
- Song structure (vocals)
- Layered explainer audio
- Related skills
- Pruna / Replicate tools
Files
SKILL.mdcore7,384 bytesSKILL.mdcore7,384 bytesSKILL.mdcore7,384 bytesSKILL.mdcore7,384 bytesreferences/audio-post-production.mddoc7,604 bytesreferences/music-and-bed-prompting.mddoc3,709 bytesreferences/tts-style-prompting.mddoc2,888 bytesskill.manifest.jsonasset121 bytes
Read SKILL.md
# Audio prompting
Vendor-neutral craft for **speech, music, and beds**. Works with Gemini TTS, ElevenLabs, Music 2.5, Stable Audio, Suno, and similar APIs.
## Install
| Skill | Description | Install |
| --- | --- | --- |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
## When to use
- Director-style TTS prompts and inline performance tagsView the complete source on GitHubgeneration-diversity
When your agent uses it
Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
1,536 tokensWhen the skill is activated
Reference documents
19,423 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- When to use
- Works with
- Guide habit
- Before generating
- Red flags
- Related skills
Files
SKILL.mdcore6,216 bytesreferences/clarification-intake.mddoc8,329 bytesreferences/generation-diversity.mddoc51,115 bytesreferences/generation-quality-checklists.mddoc9,064 bytesreferences/still-image-prompt-flow.mddoc6,935 bytesreferences/workflow-feedback-gates.mddoc2,141 bytesskill.manifest.jsonasset195 bytes
Read SKILL.md
# Generation diversity
Vendor-neutral playbook for **diverse, explicit prompts** and output QA. Apply before every generation on any model (Pruna, Flux, Midjourney, Runway, ElevenLabs, …).
## Install
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
## When to use
- Starting a new image, video, or audio generation
- Outputs feel repetitive or “AI sloppy”View the complete source on GitHubimage-prompting
When your agent uses it
Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
1,394 tokensWhen the skill is activated
Reference documents
12,808 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- When to use
- Works with
- When NOT to use
- Guide habit
- Before generating
- Pruna tools
Files
SKILL.mdcore5,523 bytesSKILL.mdcore5,523 bytesreferences/character-turnaround-sheet.mddoc4,272 bytesreferences/p-image-edit-prompting.mddoc3,966 bytesreferences/p-image-edit-quality-checklist.mddoc1,008 bytesreferences/p-image-quality-checklist.mddoc1,973 bytesreferences/p-image-try-on-prompting.mddoc2,060 bytesreferences/p-image-try-on-quality-checklist.mddoc3,495 bytesreferences/p-image-upscale-guidance.mddoc1,814 bytesreferences/p-image-upscale-quality-checklist.mddoc998 bytesreferences/prompt-golden-rules.mddoc5,200 bytesreferences/realistic-persona-example-prompt.mddoc6,298 bytesreferences/realistic-persona-showcase.mddoc20,914 bytesskill.manifest.jsonasset439 bytes
Read SKILL.md
# Image prompting
Vendor-neutral craft for **still-image** generation and editing. Works with Pruna `p-image` family, Flux, Midjourney, Ideogram, Stable Diffusion, and similar APIs.
## Install
| Skill | Description | Install |
| --- | --- | --- |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
## When to use
- Writing photo generation promptsView the complete source on GitHubpruna-api
When your agent uses it
Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,445 tokensWhen the skill is activated
Reference documents
4,804 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- When to use
- Agent habit
- When NOT to use
- Before generating
- Related skills
Files
SKILL.mdcore5,735 bytesreferences/agent-safety.mddoc2,432 bytesreferences/api-credentials.mddoc3,066 bytesreferences/pruna-api.mddoc5,837 bytesreferences/pruna-models.mddoc4,974 bytesreferences/replicate-api.mddoc1,230 bytesskill.manifest.jsonasset140 bytes
Read SKILL.md
# Pruna API
HTTP patterns for the **Pruna P-API** and **Replicate** (audio tools). Install this before paid `POST` calls from Pruna tool skills.
## Install
| Skill | Description | Install |
| --- | --- | --- |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -y` |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
## When to use
- Setting up `PRUNA_API_KEY` / Replicate tokensView the complete source on GitHubvideo-editing
When your agent uses it
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.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
2,612 tokensWhen the skill is activated
Reference documents
14,098 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- When to use
- Works with
- When NOT to use
- Guide habit
- Structure and creativity (multi-act pieces)
- Before assembling
- Combination videos (Hyperframes)
- Related skills
Files
SKILL.mdcore10,583 bytesSKILL.mdcore10,583 bytesSKILL.mdcore10,583 bytesreferences/assembly-concat.mddoc2,545 bytesreferences/background-music.mddoc2,433 bytesreferences/captions.mddoc10,680 bytesreferences/combination-hyperframes.mddoc11,488 bytesreferences/comparison-sliders.mddoc1,238 bytesreferences/export-presets.mddoc1,888 bytesreferences/motion-composition-craft.mddoc8,013 bytesreferences/narrated-showcase.mddoc5,888 bytesreferences/overlays.mddoc1,524 bytesreferences/social-usecase-reel.mddoc5,758 bytesreferences/transitions.mddoc2,101 bytesskill.manifest.jsonasset319 bytes
Read SKILL.md
# Video editing
Vendor-neutral craft for **local post-production** on finished media. Works with any clips, stills, VO, or beds you already have — from any source.
**This skill is not generative video editing.** It does not write motion prompts or call video generation APIs. Produce or collect media first; assemble and polish here.
## Install
| Skill | Description | Install |
| --- | --- | --- |
| `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` |
## When to use
View the complete source on GitHubvideo-prompting
When your agent uses it
Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
2,482 tokensWhen the skill is activated
Reference documents
19,318 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- When to use
- Works with
- When NOT to use
- Guide habit
- Before generating
- Pruna tools
Files
SKILL.mdcore9,541 bytesreferences/audio-in-video-prompting.mddoc3,342 bytesreferences/camera-lighting-vocabulary.mddoc2,812 bytesreferences/clip-chaining.mddoc2,668 bytesreferences/p-video-2-pro-prompting.mddoc8,550 bytesreferences/p-video-2-pro-quality-checklist.mddoc5,371 bytesreferences/p-video-2-prompting.mddoc3,352 bytesreferences/p-video-2-quality-checklist.mddoc2,231 bytesreferences/p-video-animate-prompting.mddoc2,230 bytesreferences/p-video-animate-quality-checklist.mddoc1,940 bytesreferences/p-video-avatar-prompting.mddoc2,733 bytesreferences/p-video-avatar-quality-checklist.mddoc2,586 bytesreferences/p-video-edit-prompting.mddoc3,745 bytesreferences/p-video-edit-quality-checklist.mddoc2,068 bytesreferences/p-video-quality-checklist.mddoc2,507 bytesreferences/p-video-replace-prompting.mddoc3,103 bytesreferences/p-video-replace-quality-checklist.mddoc3,852 bytesreferences/physics-safe-motion.mddoc2,859 bytesreferences/prompt-dramaturgy.mddoc3,959 bytesreferences/scene-anchor-pair.mddoc11,655 bytesreferences/scene-anchor-triple.mddoc7,523 bytesskill.manifest.jsonasset729 bytes
Read SKILL.md
# Video prompting
Vendor-neutral craft for **short video / motion** generation. Works with Pruna `p-video-2-pro` / `p-video-2-pro-reference` / `p-video-2` / `p-video` family, Runway, Kling, Luma, Veo, and similar APIs.
## Install
| Skill | Description | Install |
| --- | --- | --- |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
## When to use
- Text-to-video or image-to-video promptsView the complete source on GitHubp-image
When your agent uses it
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.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,275 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- When NOT to use
- HTTP (curl)
- Generation flow
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore8,911 bytesSKILL.mdcore8,911 bytesSKILL.mdcore8,911 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubp-image-edit
When your agent uses it
Use when someone wants to edit an existing photo — change outfits or backgrounds, compose from reference images, or apply prompt-driven edits.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
2,390 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- When NOT to use
- HTTP (curl)
- Edit flow
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore9,263 bytesSKILL.mdcore9,263 bytesSKILL.mdcore9,263 bytesSKILL.mdcore9,263 bytesSKILL.mdcore9,263 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.View the complete source on GitHubp-image-ideogram
When your agent uses it
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.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
3,639 tokensWhen the skill is activated
Reference documents
2,816 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- vs `p-image`
- Prompt craft (dynamic + faithful)
- Thinking & resolution
- When NOT to use
- HTTP (curl)
- Generation flow
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore14,084 bytesSKILL.mdcore14,084 bytesSKILL.mdcore14,084 bytesreferences/domain-configurations.mddoc6,008 bytesreferences/ideogram-json-prompting.mddoc4,494 bytesskill.manifest.jsonasset91 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubp-image-try-on
When your agent uses it
Use when someone wants virtual try-on — dress a person in clothes from reference photos for fashion or ecommerce.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
2,415 tokensWhen the skill is activated
Reference documents
1,051 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- When NOT to use
- Pricing
- Request shape
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore8,894 bytesSKILL.mdcore8,894 bytesSKILL.mdcore8,894 bytesSKILL.mdcore8,894 bytesSKILL.mdcore8,894 bytesexample-prompt.mddoc3,895 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubp-image-upscale
When your agent uses it
Use when someone wants to upscale or sharpen an existing image for print, large crops, or higher-quality delivery.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
1,487 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore5,541 bytesSKILL.mdcore5,541 bytesSKILL.mdcore5,541 bytesSKILL.mdcore5,541 bytesSKILL.mdcore5,541 bytesSKILL.mdcore5,541 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubpruna
When your agent uses it
Use when installing the full Pruna generative media suite — all guides, tools, and workflows in one package.
What it loads into context
Frontmatter
275 tokensAlways available to the agent
SKILL.md
2,509 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install
- What's included
- Reading order
- Requirements
Files
SKILL.mdcore9,538 bytesSKILL.mdcore9,538 bytesSKILL.mdcore9,538 bytesSKILL.mdcore9,538 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
# pruna
All Pruna generative media skills — **guides**, **tools**, and **workflows** — in one recommended install.
## Install
```bash
npx skills add PrunaAI/pruna-skills@pruna -y
```
After install, start a **new chat**. Your agent picks skills from the suite by name.
## What's included
View the complete source on GitHubp-video
When your agent uses it
Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
3,461 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- Skill boundary
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Related
Files
SKILL.mdcore13,237 bytesSKILL.mdcore13,237 bytesSKILL.mdcore13,237 bytesSKILL.mdcore13,237 bytesSKILL.mdcore13,237 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.View the complete source on GitHubp-video-2
When your agent uses it
Use when someone wants a polished short clip from text, images, or imported audio — 1080p B-roll, start/end frame animation, or a motion shot with a mixed track. Not for cinematic generated-audio clips or talking-head-only hosts.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
4,070 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- Skill boundary
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Related
Files
SKILL.mdcore15,402 bytesSKILL.mdcore15,402 bytesSKILL.mdcore15,402 bytesSKILL.mdcore15,402 bytesSKILL.mdcore15,402 bytesSKILL.mdcore15,402 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.View the complete source on GitHubp-video-2-pro
When your agent uses it
Use when someone wants a cinematic clip from text or start/end frames — product ads, documentary shots, or dialogue with generated audio. Not for 1080p, imported audio tracks, or talking-head-only hosts.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
4,145 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- Skill boundary
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Related
Files
SKILL.mdcore15,703 bytesSKILL.mdcore15,703 bytesSKILL.mdcore15,703 bytesSKILL.mdcore15,703 bytesSKILL.mdcore15,703 bytesSKILL.mdcore15,703 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.View the complete source on GitHubp-video-2-pro-reference
When your agent uses it
Use when someone wants one cinematic clip that locks a subject from references — a product still, character, clip, or voice — using image or video references plus optional audio kept as the soundtrack or used as guidance. Not for text-only generation, 1080p, or drafts.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
5,005 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- Skill boundary
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Related
Files
SKILL.mdcore19,223 bytesSKILL.mdcore19,223 bytesSKILL.mdcore19,223 bytesSKILL.mdcore19,223 bytesSKILL.mdcore19,223 bytesSKILL.mdcore19,223 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.View the complete source on GitHubp-video-animate
When your agent uses it
Use when someone wants a photo to move like another video — motion transfer, dance remixes, or performance variations from a template clip.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
2,195 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- Skill boundary
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesSKILL.mdcore8,641 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubp-video-avatar
When your agent uses it
Use when someone wants a person on camera speaking a script — lip-synced host, spokesperson, or narrated avatar from a portrait photo.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
2,736 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Skill boundary
- Prompt craft (dynamic + faithful)
- When NOT to use
- HTTP (curl)
- Before generating
- Typical next steps
Files
SKILL.mdcore10,786 bytesSKILL.mdcore10,786 bytesSKILL.mdcore10,786 bytesSKILL.mdcore10,786 bytesSKILL.mdcore10,786 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.View the complete source on GitHubp-video-edit
When your agent uses it
Use when someone wants to edit an existing video with a text instruction — recolor, restyle, remove or add objects, change environment or lighting, update on-screen text, or apply optional reference-guided product and accessory edits. Not for a new clip from scratch or ffmpeg assembly.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
2,496 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- Skill boundary
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesSKILL.mdcore10,715 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubp-video-replace
When your agent uses it
Use when someone wants to swap a person, outfit, or product inside existing footage while keeping the camera move and audio.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
2,267 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Agent habit
- Prompt craft (dynamic + faithful)
- Skill boundary
- When NOT to use
- HTTP (curl)
- Before generating
- Required input
- Common optional fields
- Typical next steps
Files
SKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesSKILL.mdcore8,882 bytesskill.manifest.jsonasset23 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -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.
View the complete source on GitHubavatar-multi-scene
When your agent uses it
Use when someone wants the same person hosting several clips — multi-segment UGC, comparison reels, or mixed speaking and animated scenes with continuity.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
4,243 tokensWhen the skill is activated
Reference documents
5,881 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Purpose
- Quick reference
- Feedback gates (required)
- Intake: ask before generating
- Cast ledger & character sheet
- Scene plan (dynamic beats)
- Identity & ritual seed policy
- Natural voice (mandatory for avatar social / founder content)
- Source portrait / hero (same character across styles and scenes)
- Confirmation gate (mandatory)
- How the agent runs this
- Core rules
- API surface (this workflow)
- Parallel execution
- Slider comparison (animate rows)
- Workflow
- Related
Files
SKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesSKILL.mdcore17,161 bytesanimate-beats.mddoc5,827 bytesexamples.mddoc6,231 bytesprompt-templates.mddoc12,080 bytesskill.manifest.jsonasset165 bytestemplates/batch.template.jsonasset1,275 bytes
Read 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` |
| `p-video-animate` | Use when someone wants a photo to move like another video — motion transfer, dance remixes, or performance variations from a template clip. | `npx skills add PrunaAI/pruna-skills@p-video-animate -y` |
Or install the full suite once: `npx skills add PrunaAI/pruna-skills@pruna -y`
View the complete source on GitHubavatar-single-scene
When your agent uses it
Use when someone wants one polished host-on-camera beat — a speaking person with intake and approval gates before generation.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,857 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Feedback gates (required)
- Natural language script
- Voice and image continuity
- Intake: ask before generating
- Confirmation gate (mandatory)
- How the agent runs this
- Workflow (after confirmation)
- Related
Files
SKILL.mdcore7,423 bytesskill.manifest.jsonasset23 bytes
Read 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`
View the complete source on GitHubillustrated-story-reel
When your agent uses it
Use when someone wants a slideshow story with narration or music — picture-book illustrated frames with Ken Burns or gentle p-video motion.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
3,434 tokensWhen the skill is activated
Reference documents
3,656 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Overview
- When to Use
- Security & scope
- Feedback gates
- Quick reference
- Intake — ask before generating
- Generation phases
- How the agent runs this
- Workflow
- Common mistakes
- Related
Files
SKILL.mdcore13,023 bytesSKILL.mdcore13,023 bytesSKILL.mdcore13,023 bytesSKILL.mdcore13,023 bytesSKILL.mdcore13,023 bytesreferences/illustrated-story-reel-api.mddoc2,108 bytesreferences/illustrated-story-reel-gates.mddoc4,019 bytesreferences/illustrated-story-reel-p-video-motion.mddoc3,249 bytesreferences/illustrated-story-reel-prompts.mddoc2,750 bytesreferences/illustrated-story-reel-quality.mddoc1,826 bytesskill.manifest.jsonasset479 bytestemplates/story-plan.landscape.template.jsonasset1,215 bytestemplates/story-plan.template.jsonasset2,300 bytes
Read 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-2` | Use when someone wants a polished short clip from text, images, or imported audio — 1080p B-roll, start/end frame animation, or a motion shot with a mixed track. Not for cinematic generated-audio clips or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2 -y` |
| `p-video` | Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p. | `npx skills add PrunaAI/pruna-skills@p-video -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` |
| `stable-audio-2.5` | Use when someone wants light instrumental background music — an ambient bed under dialogue or underscore for reels and explainers. | `npx skills add PrunaAI/pruna-skills@stable-audio-2.5 -y` |
View the complete source on GitHubimage-to-video
When your agent uses it
Use when someone wants one short film beat from images — a narrated scene, story moment, or cinematic B-roll with optional voiceover.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
3,062 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Skill boundary
- Feedback gates (required)
- Intake: ask before generating
- How the agent runs this
- Workflow (after intake)
- Related
Files
SKILL.mdcore11,712 bytesSKILL.mdcore11,712 bytesSKILL.mdcore11,712 bytesskill.manifest.jsonasset23 bytes
Read 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-2-pro` | Use when someone wants a cinematic clip from text or start/end frames — product ads, documentary shots, or dialogue with generated audio. Not for 1080p, imported audio tracks, or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2-pro -y` |
| `p-video-2-pro-reference` | Use when someone wants one cinematic clip that locks a subject from references — a product still, character, clip, or voice — using image or video references plus optional audio kept as the soundtrack or used as guidance. Not for text-only generation, 1080p, or drafts. | `npx skills add PrunaAI/pruna-skills@p-video-2-pro-reference -y` |
| `p-video-2` | Use when someone wants a polished short clip from text, images, or imported audio — 1080p B-roll, start/end frame animation, or a motion shot with a mixed track. Not for cinematic generated-audio clips or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2 -y` |
| `p-video` | Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p. | `npx skills add PrunaAI/pruna-skills@p-video -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` |View the complete source on GitHubinteractive-explainer
When your agent uses it
Use when someone wants an educational explainer with a host and characters — history or science shorts with dialogue, not voiceover-only B-roll.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
3,432 tokensWhen the skill is activated
Reference documents
6,251 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Quick reference
- Subject flavors (pick one `style_bible`)
- Defaults (720p / 24 fps)
- Motion (dynamic, physics-safe)
- Intake: ask before generating
- Feedback gates (required)
- Generation phases
- Scene table (template)
- Scene types
- How the agent runs this
- Workflow
- Scripting rules
- Common mistakes
- Related
Files
SKILL.mdcore13,211 bytesSKILL.mdcore13,211 bytesSKILL.mdcore13,211 bytesexample-prompt.mddoc2,230 bytesreferences/interactive-explainer-motion.mddoc5,244 bytesreferences/interactive-explainer-prompts.mddoc6,381 bytesreferences/interactive-explainer-scenes.mddoc11,203 bytesskill.manifest.jsonasset338 bytestemplates/explainer-plan.template.jsonasset5,005 bytes
Read 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-2` | Use when someone wants a polished short clip from text, images, or imported audio — 1080p B-roll, start/end frame animation, or a motion shot with a mixed track. Not for cinematic generated-audio clips or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2 -y` |
| `p-video` | Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p. | `npx skills add PrunaAI/pruna-skills@p-video -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` |
| `stable-audio-2.5` | Use when someone wants light instrumental background music — an ambient bed under dialogue or underscore for reels and explainers. | `npx skills add PrunaAI/pruna-skills@stable-audio-2.5 -y` |View the complete source on GitHubmusic-video
When your agent uses it
Use when someone wants a full music video — original song or vocals, performance clips, B-roll, and lyric-synced edits.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
3,875 tokensWhen the skill is activated
Reference documents
3,140 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Quick reference
- Model routing (performance vs B-roll)
- Intake: ask before generating
- Character continuity (when intended)
- Generation phases
- How the agent runs this
- Step 4 — Stills (`p-image-ideogram` / `p-image-edit`)
- Step 5 — Video clips
- Step 6 — Assemble
- Aesthetic guidelines
- Plan template
- Environment
- Anti-patterns
- Related
Files
SKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesSKILL.mdcore14,936 bytesexample-prompt.mddoc1,239 bytesexamples.mddoc2,929 byteslyrics-and-cuts.mddoc5,732 bytesreferences/music-video-quality-checklist.mddoc2,438 bytesskill.manifest.jsonasset290 bytestemplates/music-video-plan.template.jsonasset2,952 bytes
Read SKILL.md
## Prerequisites
Install and load these skills before generating (skip if already in context via `@pruna`):
| Skill | Description | Install |
| --- | --- | --- |
| `music-2.5` | Use when someone wants an original AI song with vocals — sung lyrics, a style prompt track, or source audio for a music video. | `npx skills add PrunaAI/pruna-skills@music-2.5 -y` |
| `whisperx` | Use when someone needs word-level timestamps from audio — lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing. | `npx skills add PrunaAI/pruna-skills@whisperx -y` |
| `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-2` | Use when someone wants a polished short clip from text, images, or imported audio — 1080p B-roll, start/end frame animation, or a motion shot with a mixed track. Not for cinematic generated-audio clips or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2 -y` |
| `p-video` | Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p. | `npx skills add PrunaAI/pruna-skills@p-video -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` |View the complete source on GitHubnarrated-multi-scene
When your agent uses it
Use when someone wants a multi-part story with voiceover — episodic B-roll, chaptered promo, or several linked video scenes without on-camera dialogue.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
2,872 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Feedback gates (required)
- Intake: ask before generating
- How the agent runs this
- Workflow (after intake)
- Frame-chain + narration example (dog story)
- Related
Files
SKILL.mdcore10,595 bytesSKILL.mdcore10,595 bytesSKILL.mdcore10,595 bytesSKILL.mdcore10,595 bytesskill.manifest.jsonasset23 bytes
Read 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-2` | Use when someone wants a polished short clip from text, images, or imported audio — 1080p B-roll, start/end frame animation, or a motion shot with a mixed track. Not for cinematic generated-audio clips or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2 -y` |
| `p-video` | Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p. | `npx skills add PrunaAI/pruna-skills@p-video -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` |
| `stable-audio-2.5` | Use when someone wants light instrumental background music — an ambient bed under dialogue or underscore for reels and explainers. | `npx skills add PrunaAI/pruna-skills@stable-audio-2.5 -y` |
View the complete source on GitHubvisual-transition-reel
When your agent uses it
Use when someone wants a montage with transitions between shots — action-sequence reel or multi-scene piece where narration is optional.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
3,596 tokensWhen the skill is activated
Reference documents
346 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow habit
- Skill boundary
- When NOT to use
- Feedback gates (required)
- Intake: ask before generating
- How the agent runs this
- Generation phases
- Workflow (after intake)
- Transition prompt shape
- When to chain vs hard cut
- Related
Files
SKILL.mdcore14,224 bytesSKILL.mdcore14,224 bytesSKILL.mdcore14,224 bytesSKILL.mdcore14,224 bytesexample-prompt.mddoc1,311 bytesskill.manifest.jsonasset206 bytestemplates/transition-plan.template.jsonasset3,053 bytes
Read 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-2-pro` | Use when someone wants a cinematic clip from text or start/end frames — product ads, documentary shots, or dialogue with generated audio. Not for 1080p, imported audio tracks, or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2-pro -y` |
| `p-video-2-pro-reference` | Use when someone wants one cinematic clip that locks a subject from references — a product still, character, clip, or voice — using image or video references plus optional audio kept as the soundtrack or used as guidance. Not for text-only generation, 1080p, or drafts. | `npx skills add PrunaAI/pruna-skills@p-video-2-pro-reference -y` |
| `p-video-2` | Use when someone wants a polished short clip from text, images, or imported audio — 1080p B-roll, start/end frame animation, or a motion shot with a mixed track. Not for cinematic generated-audio clips or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2 -y` |
| `p-video` | Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p. | `npx skills add PrunaAI/pruna-skills@p-video -y` |
| `stable-audio-2.5` | Use when someone wants light instrumental background music — an ambient bed under dialogue or underscore for reels and explainers. | `npx skills add PrunaAI/pruna-skills@stable-audio-2.5 -y` |View the complete source on GitHubSkills included
- gemini-3.1-flash-tts
- music-2.5
- stable-audio-2.5
- whisperx
- audio-prompting
- generation-diversity
- image-prompting
- pruna-api
- video-editing
- video-prompting
- p-image
- p-image-edit
- p-image-ideogram
- p-image-try-on
- p-image-upscale
- pruna
- p-video
- p-video-2
- p-video-2-pro
- p-video-2-pro-reference
- p-video-animate
- p-video-avatar
- p-video-edit
- p-video-replace
- avatar-multi-scene
- avatar-single-scene
- illustrated-story-reel
- image-to-video
- interactive-explainer
- music-video
- narrated-multi-scene
- visual-transition-reel
Repository facts
- License
- Apache-2.0
- Created
- May 7, 2026
- Last pushed
- Oct 15, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 129 notes
.claude-plugin/marketplace.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/gemini-3.1-flash-tts/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/gemini-3.1-flash-tts/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/gemini-3.1-flash-tts/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/music-2.5/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/music-2.5/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/music-2.5/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/music-2.5/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/stable-audio-2.5/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/stable-audio-2.5/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/stable-audio-2.5/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/whisperx/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/whisperx/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/whisperx/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/whisperx/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/audio/whisperx/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/guides/audio-prompting/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/guides/audio-prompting/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/guides/audio-prompting/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 293 network referencesin 49 files: p-video-2-pro-reference/SKILL.md:38 pruna-api/references/pruna-api.md:3 p-image-try-on/SKILL.md:74 and 46 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 177 references to secretsin 32 files: p-image-try-on/SKILL.md:27 p-video-2-pro-reference/SKILL.md:30 p-video-2-pro/SKILL.md:30 and 29 more
- No requests to vote in Hot
Show all 470 signals by file
skills/audio/gemini-3.1-flash-tts/SKILL.md
- Access to secretsline 44
[Credential-related source omitted] - Network accessline 52
[Credential-related source omitted] - Access to secretsline 52
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Network accessline 61
} }' \ "https://api.replicate.com/v1/models/google/gemini-3.1-flash-tts/predictions" - Network accessline 62
}' "https://api.replicate.com/v1/models/google/gemini-3.1-flash-tts/predictions" - Network accessline 63
"https://api.replicate.com/v1/models/google/gemini-3.1-flash-tts/predictions" - Network accessline 70
1. Complete Prerequisites guide reading order. 2. Confirm **`text`**, **`voice`**, **`prompt`**, and **`language_code`** with the user. **`text`**, **`prompt`**, and inline `[tags]` must **align** — same emotional direction (see `audio-prom - Access to secretsline 71
[Credential-related source omitted] - Network accessline 72
3. **Model notes:** combined `text` + `prompt` ≤ ~8,000 bytes; output capped ~655s. When TTS feeds **`p-video`** as `input.audio`, keep each line **≤ ~19s** (`ffprobe`) — P-API clips audio at **20s**. Common voices: `Kore`, `Aoede`, `Sulafa
skills/audio/music-2.5/SKILL.md
- Access to secretsline 42
[Credential-related source omitted] - Network accessline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Network accessline 60
} }' \ "https://api.replicate.com/v1/models/minimax/music-2.5/predictions" - Network accessline 61
}' "https://api.replicate.com/v1/models/minimax/music-2.5/predictions" - Network accessline 62
"https://api.replicate.com/v1/models/minimax/music-2.5/predictions" - Network accessline 69
1. Complete Prerequisites guide reading order. 2. Confirm **`lyrics`** (with structure tags) and optional style **`prompt`**. When listing required fields, name **`REPLICATE_API_TOKEN`** (Replicate — not `PRUNA_API_KEY`). 3. **Model notes:* - Access to secretsline 70
[Credential-related source omitted] - Network accessline 71
3. **Model notes:** structure tags on their own lines — `[Intro]` `[Verse]` `[Pre Chorus]` `[Chorus]` `[Hook]` `[Bridge]` `[Solo]` `[Inst]` `[Build Up]` `[Drop]` `[Interlude]` `[Break]` `[Transition]` `[Outro]`. `\n` = line break (also a sa
skills/audio/stable-audio-2.5/SKILL.md
- Access to secretsline 42
[Credential-related source omitted] - Network accessline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Network accessline 59
} }' \ "https://api.replicate.com/v1/models/stability-ai/stable-audio-2.5/predictions" - Network accessline 60
}' "https://api.replicate.com/v1/models/stability-ai/stable-audio-2.5/predictions" - Network accessline 61
"https://api.replicate.com/v1/models/stability-ai/stable-audio-2.5/predictions" - Access to secretsline 69
[Credential-related source omitted]
skills/audio/whisperx/SKILL.md
skills/guides/audio-prompting/references/audio-post-production.md
- Access to secretsline 34
[Credential-related source omitted]
skills/guides/generation-diversity/references/generation-diversity.md
- Network accessline 43
The random seed ritual is a lean [String Seed of Thought](https://pub.sakana.ai/ssot/) (DAG) protocol. **Every** Pruna generation — every prompt, every `POST /v1/predictions`, every scene row — starts here. - Network accessline 83
Manifest: `"ritual_seed": "k7Qm2xP9"`. Derived: aspect_ratio 16:9, camera_tag fish-eye, render_category_tag cartoon_anime_fantasy. Prompt: Disco ball reflections on an otter DJ scratching vinyl at a packed 1970s roller rink, fish-eye lens, - Network accessline 85
…then curl / runner **without** `"seed"` in `input`. - Network accessline 203
Sources: [Arena text-to-image](https://arena.ai/leaderboard/text-to-image) · [AA text-to-image](https://artificialanalysis.ai/image/leaderboard/text-to-image) - Network accessline 225
Sources: [Arena image edit](https://arena.ai/leaderboard/image-edit) · [AA image editing](https://artificialanalysis.ai/image/leaderboard/editing) - Network accessline 235
Sources: [Arena text-to-video](https://arena.ai/leaderboard/text-to-video) · [AA text-to-video](https://artificialanalysis.ai/video/leaderboard/text-to-video) - Network accessline 243
Sources: [Arena image-to-video](https://arena.ai/leaderboard/image-to-video) · [AA image-to-video](https://artificialanalysis.ai/video/leaderboard/image-to-video) - Network accessline 251
Source: [Arena video edit](https://arena.ai/leaderboard/video-edit) - Network accessline 734
| **Avatar motion** | Unique **`video_prompt`** per clip; natural **`voice_script`** | | **Cast** | Diversity ledger — gender, age, ethnicity spread | | **Playground** | Pin try-on refs on [p-image-try-on](https://replicate.com/prunaai/p-im - Network accessline 736
| **Playground** | Pin try-on refs on [p-image-try-on](https://replicate.com/prunaai/p-image-try-on); match with diverse [p-video-avatar](https://replicate.com/prunaai/p-video-avatar) examples — @ShinyTaskForce |
skills/guides/generation-diversity/references/generation-quality-checklists.md
- Access to secretsline 101
[Credential-related source omitted]
skills/guides/generation-diversity/references/still-image-prompt-flow.md
- Network accessline 38
3. **Derive axes** — rotate ≥2 free axes vs the previous still in session (`aspect_ratio`, `camera_tag`, `render_category_tag`, setting materials, …). See [by model (p-image)](./generation-diversity.md#by-model-minimum-diversity). 4. **Draf - Network accessline 39
4. **Draft explicit prompt** — name cast/creature, objects, frozen action, setting, camera/light, style tag. Follow [explicit prompt structure](./generation-diversity.md#explicit-prompt-structure-required) and `image-prompting` golden rules - Network accessline 40
5. **Fidelity check** — brief locks still present; no copied SKILL curl examples. - Network accessline 104
| Wrong | Right | |-------|--------| | Copy otter/corgi curl examples from SKILL.md | Fresh ritual + brief-faithful prompt | - Network accessline 105
|-------|--------| | Copy otter/corgi curl examples from SKILL.md | Fresh ritual + brief-faithful prompt | | `cool product vibe, neon` | Named product, materials, action, setting, camera | - Network accessline 106
| Copy otter/corgi curl examples from SKILL.md | Fresh ritual + brief-faithful prompt |
skills/guides/generation-diversity/references/workflow-feedback-gates.md
- Network accessline 5
**Agents must pause** at each gate and **ask** when art direction is unclear. Never approve the plan and run paid video in the same turn. There are **no Python runners** — follow each workflow skill’s phase tables (curl + ffmpeg). - Network accessline 32
1. Complete `generation-diversity` ritual before any prompt work. 2. Install workflow tools via that skill’s **Prerequisites** (or `@pruna` once). 3. Parallelize independent curl jobs within a phase; never skip stills approval before paid v - Network accessline 33
2. Install workflow tools via that skill’s **Prerequisites** (or `@pruna` once). 3. Parallelize independent curl jobs within a phase; never skip stills approval before paid video. 4. Recipe picker for humans: WORKFLOW-RECIPES.md. - Network accessline 34
3. Parallelize independent curl jobs within a phase; never skip stills approval before paid video.
skills/guides/image-prompting/references/character-turnaround-sheet.md
- Network accessline 7
**Sources:** patterns adapted from [Square-Zero-Labs/video-prompting-skill](https://github.com/Square-Zero-Labs/video-prompting-skill) (Apache-2.0); rewritten for Pruna.
skills/guides/image-prompting/references/prompt-golden-rules.md
- Network accessline 7
**Sources:** patterns adapted from [smixs/visual-skills](https://github.com/smixs/visual-skills) (MIT) and [higgsfield-ai/skills](https://github.com/higgsfield-ai/skills) (MIT); rewritten for Pruna.
skills/guides/image-prompting/references/realistic-persona-example-prompt.md
- Network accessline 12
[Credential-related source omitted] - Access to secretsline 12
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted] - Network accessline 28
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Network accessline 75
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Network accessline 80
"image": "https://api.pruna.ai/v1/files/APPROVED_STILL_ID", - Network accessline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Network accessline 98
"image": "https://api.pruna.ai/v1/files/ANIME_STILL_ID",
skills/guides/image-prompting/references/realistic-persona-showcase.md
- Network accessline 337
Pin diverse try-on examples on [p-image-try-on](https://replicate.com/prunaai/p-image-try-on) per the playground table below. - Network accessline 341
| Model | Showcase spread | |-------|-----------------| | [p-image](https://replicate.com/prunaai/p-image) | Mixed mediums + angles + settings per [matrix](#scenario-matrix--8-slot-showcase-mixed-mediums) | - Network accessline 342
|-------|-----------------| | [p-image](https://replicate.com/prunaai/p-image) | Mixed mediums + angles + settings per [matrix](#scenario-matrix--8-slot-showcase-mixed-mediums) | | [p-image-try-on](https://replicate.com/prunaai/p-image-try- - Network accessline 343
| [p-image](https://replicate.com/prunaai/p-image) | Mixed mediums + angles + settings per [matrix](#scenario-matrix--8-slot-showcase-mixed-mediums) | - Network accessline 344
| [p-image-try-on](https://replicate.com/prunaai/p-image-try-on) | Five editorial/complex-garment refs + diverse cast | - Network accessline 345
| [p-video-avatar](https://replicate.com/prunaai/p-video-avatar) | Photoreal + anime + clay hosts; unique `video_prompt` each |
skills/guides/pruna-api/SKILL.md
skills/guides/pruna-api/references/agent-safety.md
- Network accessline 7
Local images, audio, scripts, and portraits are **uploaded to remote APIs** (primarily `https://api.pruna.ai/`; Replicate for TTS/song/bed/WhisperX). Uploads may include biometric-like portraits, personal voice, or copyrighted material. - Access to secretsline 15
[Credential-related source omitted] - Network accessline 22
Downloads (`curl -o …`, runners writing under an output dir) **create or overwrite** local files. Confirm the output path with the user before writing; avoid clobbering unrelated paths.
skills/guides/pruna-api/references/api-credentials.md
- Network accessline 9
[Credential-related source omitted] - Access to secretsline 9
[Credential-related source omitted] - Network accessline 10
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Network accessline 11
| **Sign up / get key** | [Pruna dashboard](https://dashboard.pruna.ai/) | - Network accessline 12
| **Docs** | [Quickstart](https://docs.api.pruna.ai/guides/quickstart) · [pruna-api.md](./pruna-api.md) | - Access to secretsline 16
[Credential-related source omitted] - Network accessline 18
> Pruna generation needs an API key. Sign up or sign in at **[dashboard.pruna.ai](https://dashboard.pruna.ai/)**, create an API key, then set: - Access to secretsline 21
[Credential-related source omitted] - Network accessline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Network accessline 31
[Credential-related source omitted] - Access to secretsline 31
[Credential-related source omitted] - Network accessline 32
| **Sign up / get token** | [Replicate API tokens](https://replicate.com/account/api-tokens) ([sign in](https://replicate.com/signin) first if needed) | - Network accessline 39
> This step uses Replicate (song, TTS, transcription, or background bed). Create a token at **[replicate.com/account/api-tokens](https://replicate.com/account/api-tokens)**, then set: - Access to secretsline 42
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 52
[Credential-related source omitted]
skills/guides/pruna-api/references/pruna-api.md
- Network accessline 3
Official docs: [Developer Portal](https://docs.api.pruna.ai/), [Quickstart](https://docs.api.pruna.ai/guides/quickstart), [Models](https://docs.api.pruna.ai/guides/models). - Access to secretsline 12
[Credential-related source omitted] - Network accessline 19
- Predictions: `https://api.pruna.ai/v1/predictions` - Network accessline 20
- File upload: `https://api.pruna.ai/v1/files` (multipart form field `content=@file`) - Network accessline 21
- Status: `https://api.pruna.ai/v1/predictions/status/{id}` - Network accessline 22
- Delivery: use `generation_url` from a succeeded status (may be relative; prefix with `https://api.pruna.ai` if needed) - Network accessline 58
for scene in 1 2 3 4 5; do curl -s -X POST 'https://api.pruna.ai/v1/predictions' \ - Network accessline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 61
[Credential-related source omitted] - Network accessline 77
Local files leave the machine and are processed at `https://api.pruna.ai/` — see [agent-safety.md](./agent-safety.md). - Network accessline 79
1. `POST /v1/files` with `-F "content=@/path/to/file.jpg"` and `apikey` header. 2. Use `urls.get` from the response (or construct `https://api.pruna.ai/v1/files/{id}`) as the **`image`**, **`last_frame_image`**, **`images[]`**, **`person_im - Network accessline 80
2. Use `urls.get` from the response (or construct `https://api.pruna.ai/v1/files/{id}`) as the **`image`**, **`last_frame_image`**, **`images[]`**, **`person_image`**, **`garment_images[]`**, **`audio`**, etc. value in `input`. - Network accessline 87
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Network accessline 99
[Credential-related source omitted] - Access to secretsline 99
[Credential-related source omitted] - Network accessline 100
"https://api.pruna.ai/v1/predictions/status/PREDICTION_ID" - Network accessline 110
[Credential-related source omitted] - Access to secretsline 110
[Credential-related source omitted] - Network accessline 115
If `generation_url` is relative, prefix with `https://api.pruna.ai`. - Network accessline 119
- **Sync:** `{ "status": "succeeded", "generation_url": "..." }` - **Async (create):** `{ "id": "...", "get_url": "https://api.pruna.ai/v1/predictions/status/..." }` - Network accessline 120
- **Async (create):** `{ "id": "...", "get_url": "https://api.pruna.ai/v1/predictions/status/..." }` - Access to secretsline 127
[Credential-related source omitted] - Network accessline 129
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted]
skills/guides/pruna-api/references/pruna-models.md
- Network accessline 3
Pricing and limits change; confirm on the official page: [Available models](https://docs.api.pruna.ai/guides/models).
skills/guides/pruna-api/references/replicate-api.md
- Network accessline 5
[Credential-related source omitted] - Access to secretsline 5
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted] - Network accessline 18
# POST https://api.replicate.com/v1/models/{owner}/{name}/predictions
skills/guides/video-editing/SKILL.md
- Network accessline 29
- Export for social aspect ratios (9:16, 1:1, 16:9) with loudness normalization - Compose a **multi-act narrated showcase** (hook, context, reel, close) via HyperFrames or ffmpeg — [narrated-showcase.md](./references/narrated-showcase.md) - - Network accessline 31
- Compose a **combination video** with UI chrome, chat mocks, or multi-panel layouts via [Hyperframes](https://github.com/heygen-com/hyperframes) (optional — see [combination-hyperframes.md](./references/combination-hyperframes.md))
skills/guides/video-editing/references/combination-hyperframes.md
- Network accessline 5
**External project:** [heygen-com/hyperframes](https://github.com/heygen-com/hyperframes) — install their agent skills; do not copy Hyperframes craft into Pruna skills.
skills/guides/video-prompting/references/camera-lighting-vocabulary.md
- Network accessline 5
**Sources:** patterns adapted from [smixs/visual-skills](https://github.com/smixs/visual-skills) and [inference-sh/skills](https://github.com/inference-sh/skills) (MIT); rewritten for Pruna.
skills/guides/video-prompting/references/prompt-dramaturgy.md
- Network accessline 7
**Sources:** patterns adapted from [smixs/visual-skills](https://github.com/smixs/visual-skills) (MIT); rewritten for Pruna.
skills/guides/video-prompting/references/scene-anchor-pair.md
- Network accessline 19
{ "prompt": "OPEN: hold wide. MID: slow crane down, neon signs flicker. CLOSE: settle on end pose.", "image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 20
"prompt": "OPEN: hold wide. MID: slow crane down, neon signs flicker. CLOSE: settle on end pose.", "image": "https://api.pruna.ai/v1/files/START_ID", "last_frame_image": "https://api.pruna.ai/v1/files/END_ID", - Network accessline 21
"image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 22
"last_frame_image": "https://api.pruna.ai/v1/files/END_ID", - Network accessline 204
- `image-to-video` — one pair beat - `p-video-2` — API reference (visual transition, quality path; `p-video` for simpler clips) - Workflow runner: agent follows `visual-transition-reel` (curl + ffmpeg) - Network accessline 206
- Workflow runner: agent follows `visual-transition-reel` (curl + ffmpeg)
skills/image/p-image-edit/SKILL.md
- Access to secretsline 28
[Credential-related source omitted] - Network accessline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 60
[Credential-related source omitted] - Network accessline 69
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Network accessline 75
"prompt": "Change background to soft gradient, keep subject identical", "images": ["https://api.pruna.ai/v1/files/FILE_ID"], - Network accessline 76
"images": ["https://api.pruna.ai/v1/files/FILE_ID"], - Network accessline 89
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Network accessline 96
"prompt": "Change background to soft gradient, keep subject identical", "images": ["https://api.pruna.ai/v1/files/FILE_ID"], - Network accessline 97
"images": ["https://api.pruna.ai/v1/files/FILE_ID"], - Network accessline 109
3. **Ritual seed** → draft edit prompt (`image-prompting` edit craft) → **fidelity check** (every keep clause present). 4. **Confirm** — `prompt`, refs, **`aspect_ratio`**, **`turbo`** (off for hard edits). 5. **POST** — async curl below; c - Network accessline 111
5. **POST** — async curl below; checklist before upscale/video. - Network accessline 123
- `prompt` (string) - `images` (array of 1–5 URLs, typically `https://api.pruna.ai/v1/files/{id}`) - Network accessline 124
- `images` (array of 1–5 URLs, typically `https://api.pruna.ai/v1/files/{id}`)
skills/image/p-image-ideogram/SKILL.md
- Access to secretsline 29
[Credential-related source omitted] - Network accessline 49
Official parameters: [P-Image-Ideogram](https://docs.api.pruna.ai/guides/models/p-image-ideogram) - Network accessline 55
| Do | Don't | | --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera, lighting, setting texture, render category) | Copy curl examples from this skill or reuse a prior session's prompt verb - Network accessline 56
| --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera, lighting, setting texture, render category) | Copy curl examples from this skill or reuse a prior session's prompt verbatim | | Lock u - Network accessline 57
| Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera, lighting, setting texture, render category) | Copy curl examples from this skill or reuse a prior session's prompt verbatim | - Network accessline 92
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Network accessline 114
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Network accessline 129
4. **Draft explicit prompt** — **Prompt craft** + `image-prompting` golden rules; **fidelity check** before pay. 5. **Confirm** — show `prompt` + knobs unless wording is locked. 6. **POST** — async curl below; poll via `pruna-api`; run `p-i - Network accessline 131
6. **POST** — async curl below; poll via `pruna-api`; run `p-image` quality checklist in `image-prompting` before upscale/video.
skills/image/p-image-ideogram/references/ideogram-json-prompting.md
- Network accessline 3
**Vendor SSoT:** [JSON Prompting (Ideogram 4.0)](https://docs.ideogram.ai/using-ideogram/getting-started/prompting-guide/4.-json-prompting-ideogram-4.0) · [Markdown mirror](https://docs.ideogram.ai/using-ideogram/getting-started/prompting-g
skills/image/p-image-try-on/SKILL.md
- Access to secretsline 27
[Credential-related source omitted] - Network accessline 74
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Network accessline 78
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Network accessline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted] - Network accessline 94
"person_image": "https://api.pruna.ai/v1/files/PERSON_FILE_ID", - Network accessline 95
"garment_images": ["https://api.pruna.ai/v1/files/GARMENT_FILE_ID"] - Network accessline 107
[Credential-related source omitted] - Access to secretsline 107
[Credential-related source omitted] - Access to secretsline 109
[Credential-related source omitted] - Network accessline 114
"person_image": "https://api.pruna.ai/v1/files/PERSON_FILE_ID", - Network accessline 115
"garment_images": ["https://api.pruna.ai/v1/files/GARMENT_FILE_ID"] - Network accessline 123
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Network accessline 129
"person_image": "https://api.pruna.ai/v1/files/PERSON_FILE_ID", - Network accessline 130
"garment_images": [ "https://api.pruna.ai/v1/files/MULTI_GARMENT_SHOT_ID", "https://api.pruna.ai/v1/files/BOTTOM_ID" - Network accessline 131
"https://api.pruna.ai/v1/files/MULTI_GARMENT_SHOT_ID", - Network accessline 132
"https://api.pruna.ai/v1/files/BOTTOM_ID" - Network accessline 133
], "reference_pose": "https://api.pruna.ai/v1/files/POSE_REF_ID", "prompt": "the green t-shirt from image 1 and the trousers from image 2", - Network accessline 134
"reference_pose": "https://api.pruna.ai/v1/files/POSE_REF_ID",
skills/image/p-image-try-on/example-prompt.md
- Network accessline 13
1. [Editorial seated + artistic shirt](https://replicate.com/p/p47vaj1f91rmw0cyt4er0z2zd4) - Network accessline 14
2. [Complex collaged suit, high angle](https://replicate.com/p/tf7gqansnnrmt0cyt4j8mpx1c8) - Network accessline 15
3. [Mirror selfie + cap + logo tee](https://replicate.com/p/hp60wyj355rmy0cyt4psnc2mh0) - Network accessline 16
4. [Multi-garment streetwear stack](https://replicate.com/p/bak21xr79srmr0cyt52tap1nw8) - Network accessline 17
5. [Pleated blouse, golden-hour portrait](https://replicate.com/p/g9hd22x26drmr0cytmtsx11c5g) - Network accessline 19
## Person plate → try-on (minimal curl flow) - Access to secretsline 22
[Credential-related source omitted] - Network accessline 24
# 1) Generate photoreal plate (or upload your own) curl -X POST 'https://api.pruna.ai/v1/predictions' \ - Network accessline 25
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Network accessline 32
# 2) Upload person + garment refs → /v1/files, then try-on (normal mode for finals) curl -X POST 'https://api.pruna.ai/v1/predictions' \ - Network accessline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Network accessline 38
"person_image": "https://api.pruna.ai/v1/files/PERSON_ID", - Network accessline 39
"garment_images": ["https://api.pruna.ai/v1/files/GARMENT_ID"],
skills/image/p-image-upscale/SKILL.md
- Access to secretsline 27
[Credential-related source omitted] - Network accessline 46
[Credential-related source omitted] - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 47
[Credential-related source omitted] - Network accessline 56
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Access to secretsline 58
[Credential-related source omitted] - Network accessline 62
"image": "https://api.pruna.ai/v1/files/FILE_ID", - Network accessline 75
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Access to secretsline 77
[Credential-related source omitted] - Network accessline 82
"image": "https://api.pruna.ai/v1/files/FILE_ID", - Network accessline 105
- `target`: integer megapixels **1–128** (default 4). Confirm current limits on [p-image-upscale model docs](https://docs.api.pruna.ai/guides/models/p-image-upscale).
skills/image/p-image/SKILL.md
- Access to secretsline 29
[Credential-related source omitted] - Network accessline 35
| Do | Don't | | --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera, lighting, setting texture, render category) | Copy curl examples from this skill (`otter DJ`, `corgi cowboy`, …) or reu - Network accessline 36
| --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera, lighting, setting texture, render category) | Copy curl examples from this skill (`otter DJ`, `corgi cowboy`, …) or reuse a prior sess - Network accessline 37
| Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera, lighting, setting texture, render category) | Copy curl examples from this skill (`otter DJ`, `corgi cowboy`, …) or reuse a prior session's prompt | - Network accessline 63
[Credential-related source omitted] - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Network accessline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Network accessline 96
3. **Draft explicit prompt** — **Prompt craft (dynamic + faithful)** + `image-prompting` golden rules; **fidelity check** before pay. 4. **Confirm** — show `prompt` + `aspect_ratio` unless wording is locked. 5. **POST** — async curl below; - Network accessline 98
5. **POST** — async curl below; poll via `pruna-api`; run `p-image` quality checklist before upscale/video.
skills/suite/pruna/SKILL.md
- Network accessline 106
3. `pruna-api` — credentials, upload/poll/download 4. The **tool** skill for the API call 5. A **workflow** skill when the job is multi-step (agent runs curl + ffmpeg) - Network accessline 108
5. A **workflow** skill when the job is multi-step (agent runs curl + ffmpeg) - Network accessline 112
[Credential-related source omitted] - Access to secretsline 112
[Credential-related source omitted]
skills/video/p-video-2-pro-reference/SKILL.md
- Access to secretsline 30
[Credential-related source omitted] - Network accessline 38
| Assign **one role per asset** (image A = subject identity, image B = material/style, video A = camera or motion rhythm, audio A = timing/voice) and name those roles in the prompt | Upload a pile of references with no roles, or let two ref - Network accessline 39
| Treat references as **conditioning**: say what to preserve and what may change | Promise exact identity, choreography, framing, or pixel-matched first/last frames | | Run the `generation-diversity` random seed ritual; rotate ≥2 free axes - Network accessline 40
| Run the `generation-diversity` random seed ritual; rotate ≥2 free axes (camera move, lighting shift, pacing) only where the brief and references leave room | Copy curl examples from this skill or reuse a prior session's prompt | - Network accessline 85
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Network accessline 95
[Credential-related source omitted] - Access to secretsline 95
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Network accessline 101
"prompt": "Keep the product identity and materials from the reference. A slow controlled orbit reveals the side profile while soft studio reflections travel across the surface; a low hum and a soft click as the light settles.", "image - Network accessline 102
"image": [ "https://api.pruna.ai/v1/files/IMAGE_ID" ], - Network accessline 103
"https://api.pruna.ai/v1/files/IMAGE_ID" - Network accessline 135
[Credential-related source omitted] - Access to secretsline 135
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Network accessline 141
"prompt": "The character from the reference image speaks the line in the uploaded voice, lips matching each word, a slow push-in as the last word lands.", "image": [ "https://api.pruna.ai/v1/files/CHARACTER_ID" - Network accessline 142
"image": [ "https://api.pruna.ai/v1/files/CHARACTER_ID" ], - Network accessline 143
"https://api.pruna.ai/v1/files/CHARACTER_ID" - Network accessline 144
], "audio": [ "https://api.pruna.ai/v1/files/VOICE_ID" - Network accessline 145
"audio": [ "https://api.pruna.ai/v1/files/VOICE_ID" ], - Network accessline 146
"https://api.pruna.ai/v1/files/VOICE_ID" - Network accessline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 163
[Credential-related source omitted] - Network accessline 167
"prompt": "Use the reference clip for restrained camera rhythm, the images for subject and material identity, and the audio for timing. Begin near the opening frame and resolve near the closing frame.", "image": [ "https://api - Network accessline 168
"image": [ "https://api.pruna.ai/v1/files/IDENTITY_ID", "https://api.pruna.ai/v1/files/MATERIAL_ID" - Network accessline 169
"https://api.pruna.ai/v1/files/IDENTITY_ID", - Network accessline 170
"https://api.pruna.ai/v1/files/MATERIAL_ID" - Network accessline 171
], "video": [ "https://api.pruna.ai/v1/files/MOTION_ID" - Network accessline 172
"video": [ "https://api.pruna.ai/v1/files/MOTION_ID" ], - Network accessline 173
"https://api.pruna.ai/v1/files/MOTION_ID" - Network accessline 174
], "audio": [ "https://api.pruna.ai/v1/files/AUDIO_ID" - Network accessline 175
"audio": [ "https://api.pruna.ai/v1/files/AUDIO_ID" ], - Network accessline 176
"https://api.pruna.ai/v1/files/AUDIO_ID" - Network accessline 177
], "first_frame_image": "https://api.pruna.ai/v1/files/START_ID", "last_frame_image": "https://api.pruna.ai/v1/files/END_ID", - Network accessline 178
"first_frame_image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 179
"last_frame_image": "https://api.pruna.ai/v1/files/END_ID", - Network accessline 194
[Credential-related source omitted] - Access to secretsline 194
[Credential-related source omitted] - Access to secretsline 196
[Credential-related source omitted] - Network accessline 201
"prompt": "Preserve the reference subject. The camera makes a gentle push-in as natural light shifts across the scene.", "image": [ "https://api.pruna.ai/v1/files/IMAGE_ID" - Network accessline 202
"image": [ "https://api.pruna.ai/v1/files/IMAGE_ID" ], - Network accessline 203
"https://api.pruna.ai/v1/files/IMAGE_ID"
skills/video/p-video-2-pro/SKILL.md
- Access to secretsline 30
[Credential-related source omitted] - Network accessline 36
| Do | Don't | | --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`sports car`, `person - Network accessline 37
| --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`sports car`, `person turns`, …) or - Network accessline 38
| Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`sports car`, `person turns`, …) or reuse a prior - Network accessline 83
[Credential-related source omitted] - Access to secretsline 83
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 95
[Credential-related source omitted] - Network accessline 123
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Network accessline 129
"prompt": "The camera slowly pushes in, the person turns their head and smiles", "image": "https://api.pruna.ai/v1/files/FIRST_ID", - Network accessline 130
"image": "https://api.pruna.ai/v1/files/FIRST_ID", - Network accessline 140
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted] - Access to secretsline 142
[Credential-related source omitted] - Network accessline 146
"prompt": "Start on the still product hero. The camera holds, then a slow push-in as light moves across the metal. End exactly on the last-frame packshot, label readable, no extra props.", "image": "https://api.pruna.ai/v1/files/START - Network accessline 147
"image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 148
"last_frame_image": "https://api.pruna.ai/v1/files/END_ID", - Network accessline 162
[Credential-related source omitted] - Access to secretsline 162
[Credential-related source omitted] - Access to secretsline 164
[Credential-related source omitted]
skills/video/p-video-2/SKILL.md
- Access to secretsline 30
[Credential-related source omitted] - Network accessline 36
| Do | Don't | | --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`sports car`, `person - Network accessline 37
| --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`sports car`, `person turns`, …) or - Network accessline 38
| Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`sports car`, `person turns`, …) or reuse a prior - Network accessline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Access to secretsline 83
[Credential-related source omitted] - Network accessline 92
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Network accessline 120
[Credential-related source omitted] - Access to secretsline 120
[Credential-related source omitted] - Access to secretsline 122
[Credential-related source omitted] - Network accessline 126
"prompt": "OPEN: hold wide on wet alley, neon flicker. MID: slow dolly in, rain ticks on pavement. CLOSE: settle on end pose.", "image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 127
"image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 128
"last_frame_image": "https://api.pruna.ai/v1/files/END_ID", - Network accessline 139
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Network accessline 145
"prompt": "Close-up of a singer performing the uploaded track. Natural lip-sync, expressive face, stage lighting, camera holds steady on the performer.", "image": "https://api.pruna.ai/v1/files/SCENE_START", - Network accessline 146
"image": "https://api.pruna.ai/v1/files/SCENE_START", - Network accessline 147
"last_frame_image": "https://api.pruna.ai/v1/files/SCENE_END", - Network accessline 148
"audio": "https://api.pruna.ai/v1/files/SCENE_NARRATION", - Network accessline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 163
[Credential-related source omitted]
skills/video/p-video-animate/SKILL.md
- Access to secretsline 27
[Credential-related source omitted] - Network accessline 68
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Network accessline 72
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Network accessline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Network accessline 88
"video": "https://api.pruna.ai/v1/files/source-video-abc123", - Network accessline 89
"image": "https://api.pruna.ai/v1/files/reference-image-def456", - Network accessline 104
[Credential-related source omitted] - Access to secretsline 104
[Credential-related source omitted] - Access to secretsline 106
[Credential-related source omitted] - Network accessline 111
"video": "https://api.pruna.ai/v1/files/source-video-abc123", - Network accessline 112
"image": "https://api.pruna.ai/v1/files/reference-image-def456"
skills/video/p-video-avatar/SKILL.md
- Access to secretsline 28
[Credential-related source omitted] - Network accessline 74
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Network accessline 84
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Network accessline 90
"image": "https://api.pruna.ai/v1/files/FILE_ID", - Network accessline 112
[Credential-related source omitted] - Access to secretsline 112
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Network accessline 119
"image": "https://api.pruna.ai/v1/files/FILE_ID", - Network accessline 135
[Credential-related source omitted] - Access to secretsline 135
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Network accessline 141
"image": "https://api.pruna.ai/v1/files/PORTRAIT_ID", - Network accessline 142
"audio": "https://api.pruna.ai/v1/files/NARRATION_ID",
skills/video/p-video-edit/SKILL.md
- Access to secretsline 27
[Credential-related source omitted] - Network accessline 74
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Network accessline 84
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Network accessline 94
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Network accessline 100
"video": "https://api.pruna.ai/v1/files/source-video-abc123", - Network accessline 113
[Credential-related source omitted] - Access to secretsline 113
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Network accessline 120
"video": "https://api.pruna.ai/v1/files/source-video-abc123",
skills/video/p-video-replace/SKILL.md
- Access to secretsline 27
[Credential-related source omitted] - Network accessline 69
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Network accessline 73
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Network accessline 77
[Credential-related source omitted] - Access to secretsline 77
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Network accessline 87
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Network accessline 93
"video": "https://api.pruna.ai/v1/files/source-video-abc123", - Network accessline 94
"images": [ "https://api.pruna.ai/v1/files/reference-person-a-def456", "https://api.pruna.ai/v1/files/reference-person-b-ghi789" - Network accessline 95
"https://api.pruna.ai/v1/files/reference-person-a-def456", - Network accessline 96
"https://api.pruna.ai/v1/files/reference-person-b-ghi789" - Network accessline 112
[Credential-related source omitted] - Access to secretsline 112
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Network accessline 119
"video": "https://api.pruna.ai/v1/files/source-video-abc123", - Network accessline 120
"images": [ "https://api.pruna.ai/v1/files/reference-image-def456" ] - Network accessline 121
"https://api.pruna.ai/v1/files/reference-image-def456"
skills/video/p-video/SKILL.md
- Access to secretsline 30
[Credential-related source omitted] - Network accessline 36
| Do | Don't | | --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`rain-slick street`, - Network accessline 37
| --- | --- | | Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`rain-slick street`, `dog tosses plu - Network accessline 38
| Run the `generation-diversity` random seed ritual; state it; rotate ≥2 free axes (camera move, lighting shift, texture, pacing) when the brief allows | Copy curl examples from this skill (`rain-slick street`, `dog tosses plush`, …) or reu - Network accessline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Access to secretsline 83
[Credential-related source omitted] - Network accessline 92
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Network accessline 113
[Credential-related source omitted] - Access to secretsline 113
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Network accessline 119
"prompt": "OPEN: hold wide on wet alley, neon flicker. MID: slow dolly in, rain ticks on pavement. CLOSE: settle on end pose.", "image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 120
"image": "https://api.pruna.ai/v1/files/START_ID", - Network accessline 121
"last_frame_image": "https://api.pruna.ai/v1/files/END_ID", - Network accessline 132
[Credential-related source omitted] - Access to secretsline 132
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Network accessline 138
"prompt": "Dog tosses plush upward, tail wagging, motion matches narrator, warm light", "image": "https://api.pruna.ai/v1/files/SCENE_START", - Network accessline 139
"image": "https://api.pruna.ai/v1/files/SCENE_START", - Network accessline 140
"last_frame_image": "https://api.pruna.ai/v1/files/SCENE_END", - Network accessline 141
"audio": "https://api.pruna.ai/v1/files/SCENE_NARRATION",
skills/workflows/avatar-multi-scene/SKILL.md
- Network accessline 184
1. Upload refs → hero `p-image-ideogram` → parallel per-scene `p-image-edit` → slop gates → **approve stills**. 2. Parallel **`p-video-avatar`** (avatar rows) and **`p-video-animate`** (animate rows) via curl batches (`pruna-api`). - Network accessline 185
2. Parallel **`p-video-avatar`** (avatar rows) and **`p-video-animate`** (animate rows) via curl batches (`pruna-api`). - Access to secretsline 211
[Credential-related source omitted]
skills/workflows/avatar-single-scene/SKILL.md
- Network accessline 81
1. Upload refs → build still with curl (`pruna-api`) → slop gate → **approve still**.
skills/workflows/illustrated-story-reel/SKILL.md
- Access to secretsline 51
[Credential-related source omitted]
skills/workflows/illustrated-story-reel/references/illustrated-story-reel-api.md
- Network accessline 9
- Base: `https://api.pruna.ai/v1/predictions` - Network accessline 10
- Upload: `https://api.pruna.ai/v1/files` - Access to secretsline 11
[Credential-related source omitted] - Network accessline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Network accessline 30
- Create: `POST https://api.replicate.com/v1/models/{owner}/{name}/predictions`
skills/workflows/illustrated-story-reel/references/illustrated-story-reel-gates.md
- Network accessline 52
Follow `illustrated-story-reel` — agent runs curl + ffmpeg. No Python runner. Do not skip still/audio/clip approval gates.
skills/workflows/illustrated-story-reel/references/illustrated-story-reel-p-video-motion.md
skills/workflows/image-to-video/SKILL.md
- Network accessline 81
1. Confirm intake → present plan → wait for **approve plan**. 2. Build start/end stills with curl (`pruna-api` upload/poll/download). Show stills → **approve stills**. - Network accessline 82
2. Build start/end stills with curl (`pruna-api` upload/poll/download). Show stills → **approve stills**.
skills/workflows/interactive-explainer/SKILL.md
skills/workflows/interactive-explainer/references/interactive-explainer-scenes.md
- Network accessline 229
Runner: agent follows `interactive-explainer` phase table (curl + ffmpeg — no Python scripts).
skills/workflows/music-video/SKILL.md
- Network accessline 44
| Beat | Human singer / rapper | Mascot or stylized host | |------|----------------------|-------------------------| | **Performance** (lip sync to song) | **`p-video-avatar`** — `image` + **`audio`** slice from master song. **Not** `voice_ - Network accessline 45
|------|----------------------|-------------------------| | **Performance** (lip sync to song) | **`p-video-avatar`** — `image` + **`audio`** slice from master song. **Not** `voice_script`. | **`p-video-2`** — `image` + **`audio`** slice ([ - Network accessline 46
| **Performance** (lip sync to song) | **`p-video-avatar`** — `image` + **`audio`** slice from master song. **Not** `voice_script`. | **`p-video-2`** — `image` + **`audio`** slice ([Pruna music-to-video](https://docs.pruna.ai/en/stable/docs - Network accessline 172
{ "prompt": "Slow dolly through neon city street at dusk, rain reflections, cinematic", "image": "https://api.pruna.ai/v1/files/STILL_ID", - Network accessline 173
"prompt": "Slow dolly through neon city street at dusk, rain reflections, cinematic", "image": "https://api.pruna.ai/v1/files/STILL_ID", "audio": "https://api.pruna.ai/v1/files/SLICE_ID", - Network accessline 174
"image": "https://api.pruna.ai/v1/files/STILL_ID", - Network accessline 175
"audio": "https://api.pruna.ai/v1/files/SLICE_ID", - Access to secretsline 224
[Credential-related source omitted] - Access to secretsline 225
[Credential-related source omitted]
skills/workflows/music-video/examples.md
- Network accessline 22
**Pipeline** (agent is the runner — follow `this skill` phase table; curl + ffmpeg, no Python scripts):
skills/workflows/music-video/lyrics-and-cuts.md
- Network accessline 3
How to write lyrics for [Music 2.5](https://replicate.com/minimax/music-2.5) and map them to video clips **without cutting mid-word**. Workflow skill: `music-video`. - Network accessline 16
Follow [SKILL.md — How the agent runs this](./SKILL.md#how-the-agent-runs-this). No Python runner — the agent uses curl + ffmpeg.
skills/workflows/music-video/templates/music-video-plan.template.json
- Network accessline 19
"audio_format": "mp3" }, "lyrics": "[Intro]\n(Soft piano, building slowly)\n\n[Verse]\nWe built the skills library line by line\nEvery workflow ready when you need it\nFrom stills to motion, all in one place\n\n[Pre Chorus]\nAnd when th - Network accessline 20
}, "lyrics": "[Intro]\n(Soft piano, building slowly)\n\n[Verse]\nWe built the skills library line by line\nEvery workflow ready when you need it\nFrom stills to motion, all in one place\n\n[Pre Chorus]\nAnd when the chorus hits you'll kno - Network accessline 21
"lyrics": "[Intro]\n(Soft piano, building slowly)\n\n[Verse]\nWe built the skills library line by line\nEvery workflow ready when you need it\nFrom stills to motion, all in one place\n\n[Pre Chorus]\nAnd when the chorus hits you'll know\n\n
skills/workflows/narrated-multi-scene/SKILL.md
- Network accessline 42
Execute phases with parallel curl batches — **never** batch `p-video-2` before still and TTS review. Quality path: `p-video-2`. Simpler clips: `p-video`.
skills/workflows/visual-transition-reel/example-prompt.md
- Network accessline 17
Edit scene `edit_prompt`, `last_frame_edit_prompt`, and `video_prompt` rows, then follow the phase table in `this skill` (agent runs curl + ffmpeg — no Python runner).
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 467 facts
- Access to secrets in code of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:44High confidence
- Network access in code of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:52High confidence
- Access to secrets in code of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:52High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuegemini-3.1-flash-tts/SKILL.md:53Low confidence
- Network access in code of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:61High confidence
- Network access in code of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:62High confidence
- Network access in code of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:63High confidence
- Network access in prose of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:70Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuegemini-3.1-flash-tts/SKILL.md:71Low confidence
- Network access in prose of the SKILL.mdgemini-3.1-flash-tts/SKILL.md:72Low confidence
- Access to secrets in code of the SKILL.mdmusic-2.5/SKILL.md:42High confidence
- Network access in code of the SKILL.mdmusic-2.5/SKILL.md:50High confidence
- Access to secrets in code of the SKILL.mdmusic-2.5/SKILL.md:50High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuemusic-2.5/SKILL.md:51Low confidence
- Network access in code of the SKILL.mdmusic-2.5/SKILL.md:60High confidence
- Network access in code of the SKILL.mdmusic-2.5/SKILL.md:61High confidence
- Network access in code of the SKILL.mdmusic-2.5/SKILL.md:62High confidence
- Network access in prose of the SKILL.mdmusic-2.5/SKILL.md:69Low confidence
- Access to secrets in prose of the SKILL.mdmusic-2.5/SKILL.md:70Low confidence
- Network access in prose of the SKILL.mdmusic-2.5/SKILL.md:71Low confidence
- Access to secrets in code of the SKILL.mdstable-audio-2.5/SKILL.md:42High confidence
- Network access in code of the SKILL.mdstable-audio-2.5/SKILL.md:50High confidence
- Access to secrets in code of the SKILL.mdstable-audio-2.5/SKILL.md:50High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuestable-audio-2.5/SKILL.md:51Low confidence
- Network access in code of the SKILL.mdstable-audio-2.5/SKILL.md:59High confidence
- Network access in code of the SKILL.mdstable-audio-2.5/SKILL.md:60High confidence
- Network access in code of the SKILL.mdstable-audio-2.5/SKILL.md:61High confidence
- Access to secrets in prose of the SKILL.mdstable-audio-2.5/SKILL.md:69Low confidence
- Access to secrets in code of the SKILL.mdwhisperx/SKILL.md:42High confidence
- Access to secrets in prose of the SKILL.mdwhisperx/SKILL.md:66Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueaudio-prompting/references/audio-post-production.md:34Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:43Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:83Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:85Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:203Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:225Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:235Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:243Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:251Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:734Low confidence
- Network access in prose of documentationgeneration-diversity/references/generation-diversity.md:736Low confidence
- Access to secrets in prose of documentationgeneration-diversity/references/generation-quality-checklists.md:101Low confidence
- Network access in prose of documentationgeneration-diversity/references/still-image-prompt-flow.md:38Low confidence
- Network access in prose of documentationgeneration-diversity/references/still-image-prompt-flow.md:39Low confidence
- Network access in prose of documentationgeneration-diversity/references/still-image-prompt-flow.md:40Low confidence
- Network access in prose of documentationgeneration-diversity/references/still-image-prompt-flow.md:104Low confidence
- Network access in prose of documentationgeneration-diversity/references/still-image-prompt-flow.md:105Low confidence
- Network access in prose of documentationgeneration-diversity/references/still-image-prompt-flow.md:106Low confidence
- Network access in prose of documentationgeneration-diversity/references/workflow-feedback-gates.md:5Low confidence
- Network access in prose of documentationgeneration-diversity/references/workflow-feedback-gates.md:32Low confidence
and 417 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/audio/whisperx/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/audio/whisperx/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/audio/whisperx/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/audio/whisperx/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.