Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add prasad-vennam/Awesome-Android-AI-Agent-Skills --skill android-media-and-image-expertgit clone --depth 1 https://github.com/prasad-vennam/Awesome-Android-AI-Agent-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/prasad-vennam/awesome-android-ai-agent-skills/android-media-and-image-expert)<a href="https://agentmods.dev/skills/prasad-vennam/awesome-android-ai-agent-skills/android-media-and-image-expert"><img src="https://agentmods.dev/badge/skills/prasad-vennam/awesome-android-ai-agent-skills/android-media-and-image-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/prasad-vennam/awesome-android-ai-agent-skills/android-media-and-image-expert"><img src="https://agentmods.dev/badge/skills/prasad-vennam/awesome-android-ai-agent-skills/android-media-and-image-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00877 |
| Opus 5.5 | $0.00014 | $0.00351 |
| Sonnet 5.5 | $0.00007 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
android-media-and-image-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Media & Image Excellence 🎞️🖼️
Professional strategies for high-performance image loading, video streaming, and media management in modern Android applications.
⚡ When to Use
- Image Loading: Performance-first loading with Coil (Compose-native).
- Video Playback: Streaming using ExoPlayer or the new Media3 library.
- Media Management: Displaying local media (Photos/Videos) with proper metadata.
- Image Optimization: Sizing, Caching, and format support (WebP, AVIF).
- Audio Playback: Playing background music or voice notes.
🖼️ Image Loading with Coil (The Android Standard)
- Rule: ALWAYS use Coil for Compose. It's lightweight, efficient, and uses Coroutines.
- Rule: NEVER load the full image if displayed in a small box. Use
size(Size.ORIGINAL)or explicitsize().
1. The AsyncImage Composable
AsyncImage(
model = ImageRequest.Builder(LocalContext.current)
.data(url)
.crossfade(true)
.placeholder(R.drawable.loading)
.error(R.drawable.error)
.build(),
contentDescription = null,
modifier = Modifier.clip(CircleShape)
)
2. Best Practices
- Disk Caching: Ensure
ImageLoaderis configured to cache properly. - Memory Caching: Control cache size for apps with many images.
- SVGs: Use
SvgDecoderfor sharp, vector-based illustrations.
🎥 Video Playback (Media3 / ExoPlayer)
- Rule: Use the Media3 library as the modern wrapper for ExoPlayer.
- Lifecycle: Ensure the player is released in
onDisposeto avoid memory leaks and battery drain.
1. Basic Player Setup
val exoPlayer = remember {
ExoPlayer.Builder(context).build().apply {
setMediaItem(MediaItem.fromUri(url))
prepare()
}
}
AndroidView(
factory = { ctx ->
PlayerView(ctx).apply {
player = exoPlayer
}
},
update = { _ -> },
modifier = Modifier.fillMaxWidth()
)
🚀 Media Optimization Checklist
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 101 lines · 35 tokens per session scan A 9a186ff1a294
android-media-and-image-expert is a skill published in the GitHub repository prasad-vennam/Awesome-Android-AI-Agent-Skills (11 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 877 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
android-media-and-image-expert compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| android-media-and-image-expertprasad-vennam/Awesome-Android-AI-Agent-Skills | Skill | 11 | 7mo ago | MIT | A | 35 | Claude Code, Codex |
| apple-designbillythekidz/apple-design-skill | Skill | 5 | 2mo ago | MIT | A | 55 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 34 | Claude Code |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |