commentdrop
Skill4 starsChanged yesterdayMITView on GitHub
Add simulated social-media comment overlays to a still image in the floating comment-drop style used in video editing. Use when the user invokes /commentdrop or asks for a comment-drop effect on an image.
In this repository58 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- anywidget-generatorSkill
- brandkitSkill
- design-taste-frontendSkill
- diagram-designSkill
- docxSkill
- frontend-designSkill
- full-output-enforcementSkill
- gpt-tasteSkill
- grill-meSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- impeccableSkill
- implement-paper-autoSkill
- implement-paperSkill
- industrial-brutalist-uiSkill
- jupyter-to-marimoSkill
- marimo-notebookSkill
- minimalist-uiSkill
- pdfSkill
- postrboardSkill
- pptxSkill
- redesign-existing-projectsSkill
- skill-creatorSkill
- stitch-design-tasteSkill
- streamlit-to-marimoSkill
- xlsxSkill
- brandkitSkill
- design-taste-frontendSkill
- full-output-enforcementSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- impeccableSkill
- industrial-brutalist-uiSkill
- minimalist-uiSkill
- redesign-existing-projectsSkill
- stitch-design-tasteSkill
- network-flowSkill
- create-lib-docsSkill
- artwallbgSkill
- newsletter-aiSkill
- prodigySkill
- scrolls-explainerSkill
- scrolls-helpSkill
- scrolls-hideSkill
- scrolls-removeSkill
- scrolls-restoreSkill
- scrolls-setupSkill
- scrolls-unhideSkill
- scrolls-updateSkill
- stata-recipesSkill
- dynamic-promo-videoSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Use supplied comments faithfully, including usernames and other details when given.
≈ “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
Comment drop
Interpret /commentdrop {{ image + sampleComments | default="auto-generate" }} as a request to edit an image with floating comment cards. Use the supplied image or, when clearly referenced, the most recent relevant image in the conversation. If no target image is available, ask for one. A separately supplied reference image may guide card styling; do not confuse it with the target.
Use supplied comments faithfully, including usernames and other details when given. Otherwise invent a few short, context-appropriate reactions and fictional handles. Comments are simulated, not evidence of real engagement. Respect any specified number, wording, platform, placement, or style.
By default, add a small set of staggered, floating social-style cards: rounded light rectangles, soft shadows, circular avatars, bold usernames, subtle timestamps, readable comment text, and small heart icons. Make them look like overlay graphics captured from a video edit, not paint on the image. Balance the layout and keep the main subject and important visual features visible; preserve the source image, aspect ratio, and overall composition. Adapt colors and density to the scene or user's preferences.
Use the available image-editing tool to produce and display the edited image. Include the source image and any style reference as inputs. If exact text is important, preserve it as accurately as the tool allows; do not claim verbatim accuracy without verification. Do not present a description alone as the completed result.
See assets/EXAMPLE.md for example /commentdrop prompts and their outputs.
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.

