explainer
Skill0 starsChanged 34 days agoMITView on GitHub
Turn a dense result, system, error or architecture into a custom artifact the user can actually process. The default artifact is a high-quality interactive single-file HTML page (self-contained, no CDN, no build step); diagrams (Mermaid, ASCII) only where HTML cannot render; controlled plain English (ASD-STE100 spirit) for chat answers; an explainer video on explicit request. Use when the user asks to explain, summarize, visualize or show something, says they do not understand, re-asks, or asks for a page, a diagram, a demo or an explainer. A markdown file is never the deliverable when a page is possible.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- AJschoons/robowrighttheir own version, first seen Nov 8, 2026
- akachandan1/video-studiotheir own version, first seen Nov 8, 2026
- alandaitch/explainer-skilltheir own version, first seen Nov 8, 2026
- overment/skillstheir own version, first seen Nov 8, 2026
- agentic-community/mcp-gateway-registrytheir own version, first seen Nov 6, 2026
- artemnovitckii/claude-editing-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use ugc-ads.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AdviblySkillugc-ads
Generate complete multi-shot UGC video ads end to end with the Advibly MCP tools. Takes a brand plus an ad angle and produces a realistic AI creator image (gpt-image-2), a 5-shot direct response script, a user-approved storyboard of start frames, and one video clip per shot animated from its frame (Gemini Omni Flash with native spoken dialogue), then assembles the clips into a finished vertical ad. Use whenever the user wants a UGC ad, a creator-style video ad, a product-in-hand testimonial video, or asks to turn a product into a TikTok/Reels-style ad. Also trigger on phrases like "UGC video," "creator ad," "testimonial ad," or "make an ad for my product" when the Advibly MCP is connected.
Also in 3 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- agentic-community/mcp-gateway-registry★ 1ksame name
- marswaveai/skills★ 82same name
- Pika-Labs/Pika-Plugins★ 40same name
- codetesla51/skills★ 32same name
- overment/skills★ 31same name
- artemnovitckii/claude-editing-skills★ 12same name
- alandaitch/explainer-skill★ 8same name
- akachandan1/video-studio★ 2same name
- barisgit/explainer-skill★ 2same name
- ofoxai/skills★ 2same name
10 more not listed
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 repository58 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agySkill
- animate-expoSkill
- animateSkill
- animation-performanceSkill
- animation-vocabularySkill
- apple-designSkill
- ask-sonnerSkill
- break-uiSkill
- docs-fishingSkill
- emil-design-engSkill
- explainerSkill
- ffmpeg-skillSkill
- find-animation-opportunitiesSkill
- frontend-designSkill
- good-cssSkill
- improve-animationsSkill
- minimal-change-engineerSkill
- mobile-nativeSkill
- moli-webfetchSkill
- pick-ui-librarySkill
- project-dashboardSkill
- prototypeSkill
- reality-checkerSkill
- review-animationsSkill
- rust-refactoringSkill
- skill-creatorSkill
- using-superpowersSkill
- voice-ai-engineeringSkill
- write-swiftSkill
- agySkill
- animate-expoSkill
- animateSkill
- animation-performanceSkill
- animation-vocabularySkill
- apple-designSkill
- ask-sonnerSkill
- break-uiSkill
- docs-fishingSkill
- emil-design-engSkill
- ffmpeg-skillSkill
- find-animation-opportunitiesSkill
- frontend-designSkill
- good-cssSkill
- improve-animationsSkill
- minimal-change-engineerSkill
- mobile-nativeSkill
- moli-webfetchSkill
- pick-ui-librarySkill
- project-dashboardSkill
- prototypeSkill
- reality-checkerSkill
- review-animationsSkill
- rust-refactoringSkill
- skill-creatorSkill
- using-superpowersSkill
- voice-ai-engineeringSkill
- write-swiftSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
1
Distinctive
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 46
Start at the highest rung the surface allows: the page by default, a diagram only where a page cannot live, prose for short chat replies.
“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Explainer
As agents do more work on their own, the human job moves up to supervising and understanding what came back. Raw prose is the most expensive format to process, and models are now strong at frontend: when something deserves more than a chat answer, build a small custom artifact - disposable, made for one question, a real page rather than a wall of text.
The ladder
- Controlled English - simplified technical English in the spirit of ASD-STE100 (apply "80% of the way" when the full spec reads too stiff): short sentences, one topic per sentence, active voice, plain verbs, no idiom, measured numbers over adjectives. This is the voice of EVERY answer, chat included; prose alone is fine only for short replies.
- Diagram - for surfaces that cannot render a page: terminal output, diffs, PR comments, doc embeds. Mermaid where a forge renders it, ASCII in a terminal. A diagram is a bonus inside a chat answer, never the deliverable when a page is possible.
- Interactive single-file HTML page - the default artifact. Whenever the request deserves an artifact, build a real page: deliberate layout, real typography, color, and interaction (hover detail, filters, tabs, step-through). Self-contained: inline CSS and JS, no CDN, no network, no build step - it opens directly in a browser on any machine. A throwaway artifact, never a maintained app. A markdown or plain text file is never an acceptable substitute.
- Explainer video, on explicit request only - storyboard first (scenes, narration text, what appears when) and the user approves it before any render. Local path first: animated HTML canvas plus capture, or the pipeline the repository already has; narration through a local TTS when available. An external API (voice, video) only on explicit user instruction - the key comes from an environment variable and never lands in code, logs or the artifact itself.
Quality bar
- Design it, do not dump it: a page with no styling decisions (default HTML look, no spacing system, no hierarchy) is not done. Rebuild it.
- Inspect before delivering: screenshot the rendered page and look at it. The artifact ships only after visual inspection - verified means seen.
- Start at the highest rung the surface allows: the page by default, a diagram only where a page cannot live, prose for short chat replies.
- "Make it better", a re-ask or "I do not understand" means ONE rung up, not a polish of the same rung.
Rules
- The artifact speaks the reader's language: write it in the chat language the repository declares for replies to the user, whatever the repository content language is. It is a deliverable to a person, not repository content.
- Artifacts are disposable: write them under
scratch/or the location the repository declares; never wire them into the build or the docs unless asked. - The artifact accompanies the chat, it does not replace it: deliver it with a short summary in controlled English and the path to the file.
- Numbers shown in an artifact are measured or read from the source material, never invented to make the picture nicer.
- A reusable insight goes to the project state files (dated entry) like any other finding.
Outputs
- the artifact under
scratch/(or the declared location): by default the interactive HTML page; a diagram where no page can live; a video on explicit request - a screenshot kept as evidence of the visual inspection
- a short chat summary plus the artifact path
- one rung kept in reserve: the next format to try if the user is still lost
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.

