adobe-create-social-variations
Resize, crop, or export any image or video into platform-ready social media assets using Adobe Creative Cloud tools. Use this skill when a user wants to prepare a photo, image, or video for one or more social platforms — Instagram, TikTok, LinkedIn, Facebook, YouTube, Snapchat, Pinterest, Threads, or X/Twitter. Triggers on: "prepare my image for Instagram", "resize for TikTok", "get this ready to post", "make versions for all platforms", "social media sizes", "crop for stories", "export for LinkedIn", "resize my video for social", "make social media assets", or any request to adapt a photo or video for specific platforms. Handles subject-aware cropping, AI canvas expansion, test previews before full runs, and same-ratio video resizing.
90
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific concrete actions, comprehensive trigger terms covering natural user language, explicit 'Use when' guidance with enumerated example phrases, and a clearly distinctive niche combining social media asset preparation with Adobe Creative Cloud tools. The description is thorough without being padded, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: resize, crop, export, subject-aware cropping, AI canvas expansion, test previews, same-ratio video resizing. Very detailed about what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (resize, crop, export images/videos into platform-ready social media assets) and 'when' (explicit 'Use this skill when...' clause plus a detailed 'Triggers on:' list with specific example phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'resize for TikTok', 'get this ready to post', 'make versions for all platforms', 'social media sizes', 'crop for stories'. Also lists all major platform names which are strong natural keywords. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: social media asset preparation using Adobe Creative Cloud tools. The combination of platform-specific resizing/cropping with Adobe tools creates a clear, unique identity unlikely to conflict with general image editing or generic social media skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with excellent workflow clarity, clear validation checkpoints, and comprehensive error handling. Its main weakness is length — the document is quite long with some redundancy between sections (tool reference vs. entitlement check, platform specs vs. step 5 table), and the lack of bundle files means all detail is inline rather than progressively disclosed. Despite the verbosity concern, nearly every line serves a purpose for this complex multi-tool, multi-platform workflow.
Suggestions
Extract the Platform Specs table and Error Handling table into separate reference files (e.g., PLATFORM_SPECS.md, ERROR_HANDLING.md) to reduce the main skill's token footprint and improve progressive disclosure.
Remove the Tool Reference table (redundant with the Entitlement Check section) or consolidate them into a single location to eliminate duplication.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive and mostly efficient for its complexity, but there is notable redundancy — the Tool Reference table largely duplicates information already in the Entitlement Check section, and the Platform Specs table repeats information from the Step 5 per-platform variants table. Some sections could be tightened without losing clarity. | 2 / 3 |
Actionability | Highly actionable throughout: specific tool names, exact JSON payloads, precise dimensions, quality values, file naming conventions, exact user-facing messages to output, and clear decision tables for every conditional branch. Claude can execute this workflow without guessing. | 3 / 3 |
Workflow Clarity | Excellent multi-step sequencing with explicit validation checkpoints: the test preview step (Step 4) serves as a validation gate before the full batch run, error handling covers every failure mode with specific fallback actions, and the conditional flow (runTestPreview flag) is clearly defined. The feedback loop of 'preview → approve → generate' catches framing issues early. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but it's a monolithic document (~350+ lines) with no references to external files. The Platform Specs table, Video Workflow, and Error Handling could reasonably be split into separate reference files to reduce the main skill's token footprint. No bundle files are provided to offload detail. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- adobe/skills
- Commit
5bb2150
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.