generate_release_image
Skill3 starsChanged 2 months agoMITView on GitHub
create or edit promotional images for releases, adding version numbers, feature highlights, and modern styling.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- krishnakanthb13/antigravity_global_skillsedited, first seen Jul 4, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- krishnakanthb13/antigravity_global_skills★ 50100% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- agy-customizationsSkill
- antigravity-guideSkill
- api-and-interface-designSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code_reviewSkill
- code-simplificationSkill
- context-engineeringSkill
- create_launcherSkill
- create_skillSkill
- daily_logSkill
- debugging-and-error-recoverySkill
- debug_issueSkill
- deprecation-and-migrationSkill
- document_apiSkill
- documentation-and-adrsSkill
- enhance_uiSkill
- frontend_designSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- idea-refineSkill
- idea_to_actionSkill
- impeccableSkill
- incremental-implementationSkill
- list_featuresSkill
- open_source_prepSkill
- optimize_codebaseSkill
- performance-optimizationSkill
- permissioned-githubSkill
- planning-and-task-breakdownSkill
- release_helperSkill
- repo_infographicSkill
- scaffold_testsSkill
- security-and-hardeningSkill
- security_auditSkill
- shipping-and-launchSkill
- software_architectureSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- test_runnerSkill
- ui_ux_pro_maxSkill
- update_docsSkill
- using-agent-skillsSkill
- using-ui-stackSkill
- web_performance_optimizationSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Use generate_image to create or edit the asset.
- Very specific: line 32
Action: Use the generate_image tool, passing the user's file path in ImagePaths.
- Very specific: line 42
Action: Use the generate_image tool to create a new asset.
- Very specific: line 51
Ensure Directory: Check if an assets/ folder exists in the project root.
- Very specific: line 52
Save: Call generate_image with the constructed prompt.
- Distinctive: line 58
If text is malformed (common in AI image gen), offer to regenerate or suggest using a dedicated design tool for the final text overlay.
- Distinctive: line 62
When creating release assets, follow these professional standards:
- Distinctive: line 66
Focus: Keep the text minimal. The image should tease the release, not document it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Generate Release Image
This skill helps create visually stunning assets to announce a new software release.
Inputs
- Version Number: e.g. v1.0.0.
- Key Features: List of highlights.
- Source Image: (Optional) Path to existing image.
Tooling Strategy
- Use
generate_imageto create or edit the asset.
Workflow
1. Gather Inputs
- Version Number: e.g., v2.0.1
- Key Features: 2-3 main highlights to feature on the image.
- Source Image (Optional): Does the user have a screenshot or existing asset to modify?
2. Prompt Strategy (generate_image)
Option A: User provides an image (Edit Mode)
- Action: Use the
generate_imagetool, passing the user's file path inImagePaths. - Prompt Construction:
- "Edit this image to add a premium, modern overlay."
- "Add the text '[Version Number]' prominently."
- "Add a sleek list or callout bubbles highlighting: [Feature 1], [Feature 2]."
- "Style: Glassmorphism, dynamic lighting, professional tech aesthetic."
- "Ensure text is legible and integrated into the design."
Option B: No image provided (Creation Mode)
- Action: Use the
generate_imagetool to create a new asset. - Prompt Construction:
- "A modern, high-tech promotional image for a software release version [Version Number]."
- "Visual style: [Choose based on context, e.g., Dark mode, Neon, Minimalist, Corporate]."
- "Include visual representations or text overlays for these features: [Feature List]."
- "Composition: Hero header style, plenty of negative space for text."
3. Execution
- Ensure Directory: Check if an
assets/folder exists in the project root. If not, create it. - Save: Call
generate_imagewith the constructed prompt. - Filename: Save the image specifically to
assets/release_[version].png.
4. Review
- Show the generated image to the user.
- If text is malformed (common in AI image gen), offer to regenerate or suggest using a dedicated design tool for the final text overlay.
Advanced Release Image Patterns
When creating release assets, follow these professional standards:
- Brand Consistency: Explicitly prompt for the brand's primary colors (e.g., "#0F172A and #3B82F6") and design language if available in
DESIGN_PHILOSOPHY.md. - Platform Optimization: Specify the aspect ratio based on where it will be posted (e.g., 16:9 for LinkedIn/X, 1:1 for generic announcements).
- Focus: Keep the text minimal. The image should tease the release, not document it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

