media-processor

Name: media-processor
Author: avibebuilder

109stars17forks

How to install media-processor?

avibebuilder/claude-prime/media-processor

$npx -y skills add avibebuilder/claude-prime --skill media-processor

Installs into the current project.

Summary

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 extr

Files · 1

View on GitHub

SKILL.md

1	# Media Processor
2
3	Specialized tools for extracting precise visual details (exact colors, spacing, hierarchy), processing audio/video, and generating images.
4
5	## Tools
6
7	All scripts live in `scripts/` relative to this skill's directory. They auto-select the best model per task and handle retries, large file uploads, and error reporting.
8
9	\| Script \| Purpose \|
10	\|--------\|---------\|
11	\| `gemini_batch_process.py` \| Analyze images, transcribe audio/video, extract data from PDFs \|
12	\| `image_gen.py` \| Generate and edit images (paid plan required) \|
13	\| `document_converter.py` \| Convert PDF, DOCX, XLSX, PPTX to Markdown; extract page ranges and images \|
14
15	Requires `GEMINI_API_KEY` in environment or `.env` in this skill's directory. Run any script with `--help` for setup details and available parameters.
16
17	Quick start — image analysis:
18	```bash
19	python <skill-dir>/scripts/gemini_batch_process.py \
20	--files <image-path> \
21	--task analyze \
22	--prompt "<tailored prompt>" \
23	--output <output-path>.md
24	```
25
26	## Prompt Quality Matters
27
28	The prompt sent to the processing model is the single biggest factor in output quality. Tailor prompts to what the task actually needs — generic prompts produce generic results.
29
30	What makes a good analysis prompt:
31	- Ask for the specific details the task requires (hex colors, spacing in px, component hierarchy) rather than "describe this image"
32	- Structure the ask as a numbered list — the model mirrors the structure back, making output easy to parse
33	- Name the desired output format ("as a markdown table", "as JSON", "as a component tree")
34	- Include implementation context when relevant ("for React with Tailwind") so the model emphasizes useful details
35
36	Example prompt patterns:
37
38	UI implementation: "Extract component hierarchy, layout type, exact hex colors, typography (sizes/weights), spacing in px, interactive states, icons and decorative elements"
39
40	Chart data: "Extract chart type, axes with units, every data point with exact values, legend entries with colors. Output as a markdown table"
41
42	Design review: "Compare this screenshot against the design. Flag differences in spacing, colors, alignment, missing elements, and visual inconsistencies. Note exact values for each discrepancy"
43
44	## Pasted Images
45
46	When a user pastes images in chat, they are auto-saved to:
47	```
48	$CLAUDE_DIR/image-cache/<current_session_id>/<image_number>.png
49	```
50	Use `ls "$CLAUDE_DIR/image-cache/"` to discover the session ID, then list its contents to find available images.
51
52	## Model Overrides
53
54	Scripts auto-select models per task (see [model-routing.md](./references/model-routing.md)). Override with `--model <model-id>` when the default isn't enough — for example, `--model gemini-3.1-pro-preview` for complex visual analysis where the pro model catches more detail than flash.
55
56	## References
57
58	\| Reference \| When to read \|
59	\|-----------\|-------------\|
60	\| [api-gotchas.md](./references/api-gotchas.md) \| Before using image generation, video processing, or raw API calls — prevents common failures \|
61	\| [model-routing.md](./references/model-routing.md) \| When choosing or overriding the default model for a task \|
62	\| [media-optimization.md](./references/media-optimization.md) \| When files are too large to upload — ffmpeg compression recipes \|
63
64	## Gotchas
65
66	- Rate limits — scripts retry up to 3 times with backoff. If still rate-limited after retries, stop and ask the user to check their API key quota or provide a new key.
67	- Model IDs change — Google frequently rotates preview model IDs. If you get a 404, the model was likely superseded — check the [models page](https://ai.google.dev/gemini-api/docs/models) for current IDs.
68	- Safety filters — the API may refuse some content. Report clearly to the user rather than retrying.
69	- Large files auto-upload — files >20MB automatically use the File API (2GB max, 48h retention). No action needed.

People who liked this also viewed

6 picks

Type

media-processor

109stars17forks

View on GitHub

How to install media-processor?

avibebuilder/claude-prime/media-processor

$npx -y skills add avibebuilder/claude-prime --skill media-processor

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Media Processor
2
3	Specialized tools for extracting precise visual details (exact colors, spacing, hierarchy), processing audio/video, and generating images.
4
5	## Tools
6
7	All scripts live in `scripts/` relative to this skill's directory. They auto-select the best model per task and handle retries, large file uploads, and error reporting.
8
9	\| Script \| Purpose \|
10	\|--------\|---------\|
11	\| `gemini_batch_process.py` \| Analyze images, transcribe audio/video, extract data from PDFs \|
12	\| `image_gen.py` \| Generate and edit images (paid plan required) \|
13	\| `document_converter.py` \| Convert PDF, DOCX, XLSX, PPTX to Markdown; extract page ranges and images \|
14
15	Requires `GEMINI_API_KEY` in environment or `.env` in this skill's directory. Run any script with `--help` for setup details and available parameters.
16
17	Quick start — image analysis:
18	```bash
19	python <skill-dir>/scripts/gemini_batch_process.py \
20	--files <image-path> \
21	--task analyze \
22	--prompt "<tailored prompt>" \
23	--output <output-path>.md
24	```
25
26	## Prompt Quality Matters
27
28	The prompt sent to the processing model is the single biggest factor in output quality. Tailor prompts to what the task actually needs — generic prompts produce generic results.
29
30	What makes a good analysis prompt:
31	- Ask for the specific details the task requires (hex colors, spacing in px, component hierarchy) rather than "describe this image"
32	- Structure the ask as a numbered list — the model mirrors the structure back, making output easy to parse
33	- Name the desired output format ("as a markdown table", "as JSON", "as a component tree")
34	- Include implementation context when relevant ("for React with Tailwind") so the model emphasizes useful details
35
36	Example prompt patterns:
37
38	UI implementation: "Extract component hierarchy, layout type, exact hex colors, typography (sizes/weights), spacing in px, interactive states, icons and decorative elements"
39
40	Chart data: "Extract chart type, axes with units, every data point with exact values, legend entries with colors. Output as a markdown table"
41
42	Design review: "Compare this screenshot against the design. Flag differences in spacing, colors, alignment, missing elements, and visual inconsistencies. Note exact values for each discrepancy"
43
44	## Pasted Images
45
46	When a user pastes images in chat, they are auto-saved to:
47	```
48	$CLAUDE_DIR/image-cache/<current_session_id>/<image_number>.png
49	```
50	Use `ls "$CLAUDE_DIR/image-cache/"` to discover the session ID, then list its contents to find available images.
51
52	## Model Overrides
53
54	Scripts auto-select models per task (see [model-routing.md](./references/model-routing.md)). Override with `--model <model-id>` when the default isn't enough — for example, `--model gemini-3.1-pro-preview` for complex visual analysis where the pro model catches more detail than flash.
55
56	## References
57
58	\| Reference \| When to read \|
59	\|-----------\|-------------\|
60	\| [api-gotchas.md](./references/api-gotchas.md) \| Before using image generation, video processing, or raw API calls — prevents common failures \|
61	\| [model-routing.md](./references/model-routing.md) \| When choosing or overriding the default model for a task \|
62	\| [media-optimization.md](./references/media-optimization.md) \| When files are too large to upload — ffmpeg compression recipes \|
63
64	## Gotchas
65
66	- Rate limits — scripts retry up to 3 times with backoff. If still rate-limited after retries, stop and ask the user to check their API key quota or provide a new key.
67	- Model IDs change — Google frequently rotates preview model IDs. If you get a 404, the model was likely superseded — check the [models page](https://ai.google.dev/gemini-api/docs/models) for current IDs.
68	- Safety filters — the API may refuse some content. Report clearly to the user rather than retrying.
69	- Large files auto-upload — files >20MB automatically use the File API (2GB max, 48h retention). No action needed.

People who liked this also viewed

6 picks

Type