Skip to content

avibebuilder/claude-prime / .claude/skills/media-processor

media-processor

Verified

Specialized visual and multimedia processing tools. Use this skill whenever a task involves complex visual content — UI mockups, dense screenshots, design images, charts, artwork — where precise details like spacing, hex colors, font sizes, and component hierarchy need to be extracted accurately. Also use for: reviewing or auditing existing UI against designs, comparing screenshots for visual regressions, transcribing audio/video, extracting data from PDFs with complex layouts, and generating images. Trigger whenever the user wants to implement from a design, review or compare UI screenshots, analyze visual details precisely, describe artwork or aesthetic content, or process any media file (audio, video, PDF).

references/model-routing.md

View on GitHub
# Model Routing

Task-based model selection for media-processor. Model IDs change frequently — check the [official models page](https://ai.google.dev/gemini-api/docs/models) for latest.

## Default Routing

| Task | Default Model | Rationale |
|------|--------------|-----------|
| `transcribe` | `gemini-3-flash-preview` | Multimodal audio input, best quality/cost balance |
| `analyze` | `gemini-3-flash-preview` | Best quality/cost balance for general analysis |
| `extract` | `gemini-3-flash-preview` | Fast multimodal extraction |
| `generate` | `gemini-3.1-flash-image-preview` | High-efficiency image generation — **paid plan required** |
| `generate-hq` | `gemini-3-pro-image-preview` | 4K output, commercial grade — **paid plan required** |
| document conversion | `gemini-3-flash-preview` | Document-to-markdown via vision |

Override any default with `--model <model-id>`.

## Model Tiers

### Gemini 3.x (Current)

| Model | Best for |
|-------|---------|
| `gemini-3.1-pro-preview` | Complex reasoning, detailed analysis |
| `gemini-3-flash-preview` | General-purpose multimodal, cost-effective |
| `gemini-3.1-flash-lite-preview` | Budget batch jobs, simple tasks |
| `gemini-3.1-flash-image-preview` | Standard image generation |
| `gemini-3-pro-image-preview` | High-quality image gen, 4K, 14 reference images |

### Gemini 2.5 (Legacy — still available)

| Model | Best for |
|-------|---------|
| `gemini-2.5-pro` | Advanced reasoning (if 3.x preview isn't stable enough) |
| `gemini-2.5-flash` | Production stability when preview models aren't suitable |
| `gemini-2.5-flash-lite` | Cheapest option for simple tasks |

## When to Override

- Complex image analysis (dense UI, charts): `--model gemini-3.1-pro-preview`
- Production stability over latest features: `--model gemini-2.5-flash`
- Minimum cost batch jobs: `--model gemini-3.1-flash-lite-preview`

rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall