CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is adobe-create-social-variations in adobe/skills

SKILL.md
Quality
Evals
Security

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, actionable workflow with clear sequencing and validation gates, but it is a monolithic file with repeated fallback prose that could be tightened or split into reference files. Conciseness and progressive disclosure are the weaker dimensions.

Suggestions

Consolidate the No-widget fallback guidance into one section and reference it from each step instead of repeating the full paragraph in Steps 0, 4, 6, and the video workflow — this directly addresses the conciseness penalty.

Move the Platform Specs table and Error Handling table into reference files under references/ (e.g. PLATFORM_SPECS.md, ERROR_HANDLING.md) and link to them one level deep, improving progressive_disclosure and shortening the main file.

Replace the illustrative `image_generative_expand(sourceURI, { top: 960 }) → tallURI` pseudo-assignments with concrete call examples showing argument structure so the image workflow is as copy-paste-ready as the video one.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no primer on what social platforms are), but the No-widget fallback guidance is repeated verbatim across Steps 0, 4, 6 and the video workflow, and several table cells restate the same entitlement rule — noticeable padding that could be tightened; not 4 because the repetition is more than minor.

3 / 5

Actionability

Provides executable code (`video_resize({ assetId, width, height })`, polling calls), exact dimensions, quality settings, and file-naming conventions; not 5 because the image expand/crop blocks use illustrative `image_generative_expand(sourceURI, { top: 960 }) → tallURI` pseudo-assignments rather than fully copy-paste-ready calls.

4 / 5

Workflow Clarity

Clear numbered sequences for image (Steps 0-7) and video (Steps 0-5) with explicit validation checkpoints — entitlement halt on missing tools, a test-preview approval gate before the full run, and an error-handling table with fix-and-retry feedback loops — satisfying the destructive/batch feedback-loop requirement; not 4 because checkpoints are explicit rather than only mostly present.

5 / 5

Progressive Disclosure

Scored against the actual bundle: references/ and scripts/ are empty and only two icon SVGs exist, so everything lives in a single ~400-line SKILL.md with no one-level-deep references to navigate to; sections are well-organized (some structure) but content that could be split (Platform Specs, Error Handling, Video Workflow) is inlined, matching the anchor-3 example rather than the 4 anchor's mostly-split content.

3 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it states concrete capabilities, lists explicit natural-language triggers across nine named platforms, and clearly separates the what from the when. It is distinguishable from generic image skills and unlikely to fire for the wrong task.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Resize, crop, or export any image or video", plus "subject-aware cropping, AI canvas expansion, test previews before full runs, and same-ratio video resizing" — giving comprehensive coverage; not the 4 anchor because coverage is broad rather than showing only minor gaps.

5 / 5

Completeness

Explicitly answers what (resize/crop/export into platform-ready social assets) and when ("Use this skill when a user wants to prepare a photo... Triggers on: ...") with concrete trigger phrases; the "A missing 'Use when...' clause should cap at 3" rule does not apply because the clause is present, and a clear what+when earns 5.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases ("prepare my image for Instagram", "resize for TikTok", "get this ready to post", "crop for stories", "social media sizes") plus synonyms and platform names; matches the comprehensive-coverage-with-synonyms anchor and exceeds the 4 anchor which allows a few missing terms.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Adobe Creative Cloud social-media variations) with platform-specific triggers (Instagram, TikTok, X/Twitter, etc.) and minimal overlap with other skills; matches the distinct-niche anchor rather than the 4 anchor's minor overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.