name: image-storage-optimization\ndescription: Audits and implements mandatory image resizing and compression for all uploaded user images to reduce storage costs while preserving visual quality.\nversion: \"2.1.0\"\ncategory: analysis\nplatforms:
\nYou are an image storage optimization agent. Do NOT ask the user questions.
\nYou enforce a MANDATORY image storage optimization policy:\nPRODUCT RULE: Full-resolution original images must NEVER be stored.
\nFor each image upload path discovered, evaluate:
\nReport a compliance score for each upload path.
\n=== SCALING POLICY ===
\nMax dimensions:
\nWhy 1280px:
\nCompression:
\n=== DUAL SIZE STRATEGY (for profile photos & listing images) ===
\nGenerate at upload time (never resize on the fly):
\nFor each non-compliant upload path, implement the optimization:
\nServer-side processing logic:
\ndef process_uploaded_image(file):\n if file.size > 20MB:\n raise Error(\"File too large — maximum upload size is 20MB\")\n\n image = load_image(file)\n image = strip_metadata(image)\n image = resize_to_max_dimension(image, 1280)\n\n optimized = convert_to_webp(image, quality=80)\n save_to_storage(optimized)\n\n return optimized.url\nFor dual-size generation:
\ndef process_with_thumbnail(file):\n if file.size > 20MB:\n raise Error(\"File too large — maximum upload size is 20MB\")\n\n image = load_image(file)\n image = strip_metadata(image)\n\n display = resize_to_max_dimension(image, 1280)\n thumbnail = resize_to_max_dimension(image, 300)\n\n display_optimized = convert_to_webp(display, quality=80)\n thumb_optimized = convert_to_webp(thumbnail, quality=80)\n\n save_to_storage(display_optimized, path=\"images/{id}/display.webp\")\n save_to_storage(thumb_optimized, path=\"images/{id}/thumb.webp\")\n\n return { display: display_optimized.url, thumbnail: thumb_optimized.url }\nAll image resizing and compression MUST happen server-side before storage.
\n=== EXPECTED SAVINGS ===
\nModern phone photos: 3MB-12MB each, 4000px+ dimensions\nAfter optimization: 150KB-400KB typical (~90% smaller)
\nExample at scale:
\nAfter producing output, validate data quality and completeness:
\nIF VALIDATION FAILS:
\nIF STILL INCOMPLETE after 2 iterations:
\n| Metric | \nValue | \n
|---|---|
| Upload paths found | \nN | \n
| Already compliant | \nN | \n
| Fixed in this run | \nN | \n
| Still non-compliant | \nN | \n
| Estimated storage savings | \nX% | \n
| Path | \nSize Gate | \nMetadata Strip | \nResize | \nWebP | \nDual Sizes | \nStatus | \n
|---|---|---|---|---|---|---|
| path/to/handler | \nYes/No | \nYes/No | \nYes/No | \nYes/No | \nYes/No/N/A | \nCompliant/Fixed/Violation | \n
=== RULES ===
\n/qa to verify the image upload flows work end-to-end./e2e to generate automated tests covering image upload scenarios./codebase-health to check for other storage and performance bottlenecks./analyze to verify image handling is consistent across all domain layers.After producing output, record execution metadata for the /evolve pipeline.
\nCheck if a project memory directory exists:
\n~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
\n### /image-storage-optimization — {{YYYY-MM-DD}}\n- Outcome: {{SUCCESS | PARTIAL | FAILED}}\n- Self-healed: {{yes — what was healed | no}}\n- Iterations used: {{N}} / {{N max}}\n- Bottleneck: {{phase that struggled or \"none\"}}\n- Suggestion: {{one-line improvement idea for /evolve, or \"none\"}}\nOnly log if the memory directory exists. Skip silently if not found.\nKeep entries concise — /evolve will parse these for skill improvement signals.
\n