visual-explainer
Skill0 starsChanged 45 days agoMITView on GitHub
Explain concepts, workflows, systems, and changes through visuals, clear headings, and short bullets. Use for /explain, walkthroughs, visual explanations, or ADHD-friendly breakdowns. Skip simple facts and routine status updates.
27 other projects use a version of this.
Adopted by
Most recently taken up by
- mhylle/claude-skills-collectiontheir own version, first seen Nov 8, 2026
- tsukhani/jclawtheir own version, first seen Nov 5, 2026
- maxbuildog/skillstheir own version, first seen Nov 1, 2026
- coco-research/cocotheir own version, first seen Nov 1, 2026
- lubshad/skillstheir own version, first seen Nov 1, 2026
- chacosoldier/compabobtheir own version, first seen Oct 23, 2026
Used with
Projects with it also use verification-before-completion.
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.
OpenAISkillverification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Also in 3 projects that use this
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- vercel-labs/vgpu★ 2.6ksame name
- coco-research/coco★ 797same name
- jamditis/claude-skills-journalism★ 449same name
- luanmorenommaciel/agentspec★ 256same name
- tsukhani/jclaw★ 42same name
- chacosoldier/compabob★ 34same name
- mhylle/claude-skills-collection★ 20same name
- parthjshah95/visual-planning-skills★ 14same name
- jscraik/Agent-Skills★ 9same name
- alexandergirardet/visual-explainer★ 4same name
17 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 repository10 other files it gives its agents.
- adhd-prioritiesSkill
- attorney-packetSkill
- co-parent-replySkill
- incident-logSkill
- narrative-writerSkill
- proof-checkSkill
- repo-structure-auditSkill
- review-criticallySkill
- source-mapSkill
- timeline-builderSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 25 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Prefer concise explanations that are easy to scan.
- Distinctive: line 15
Use headings, bullets, whitespace, and visuals where they improve understanding.
- Distinctive: line 31
Use ASCII or Mermaid when supported.
- Distinctive: line 37
Do not add decorative visuals to a one-line answer.
- Distinctive: line 41
Use everyday words. Define unfamiliar terms briefly on first use.
- Distinctive: line 46
Avoid fixed emoji schemes, repeated takeaway headings, and unnecessary sections.
- Distinctive: line 53
When a decision is needed, show concise options and meaningful tradeoffs in a small table or bullets.
- Distinctive: line 64
Active file: when working on a file whose content would benefit from visuals, add them there beside the relevant content.
- Distinctive: line 67
Chat: when no file is being worked on, or the explanation does not belong in that file, respond in chat.
- Very specific: line 69
Separate file: create one only when asked to save or export.
“Common” is measured: kept by at least 6 in 10 of the 25 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
Visual Explainer
Make complex ideas easy to see, scan, and understand. Support people who prefer visual, ADHD-friendly explanations without assuming their expertise or needs.
Presentation
Prefer concise explanations that are easy to scan.
- Use headings, bullets, whitespace, and visuals where they improve understanding.
- Let visuals carry relationships and detail; use prose to clarify what they cannot show.
- Include context, definitions, or examples when they help.
- Match the depth and structure to the content. Remove filler and repetition.
Choose a visual
| To explain… | Use… |
| Parts, folders, or hierarchy | Annotated tree |
| Steps, routing, or decisions | Flow diagram |
| Options, differences, or mappings | Compact comparison table |
| A change | Before/after diagram or table |
| Events over time | Timeline |
| Quantities or trends | Chart with labeled units |
Use ASCII or Mermaid when supported. Use an interactive visual when exploring scenarios benefits from it and the environment supports it. Choose a format that renders clearly in the current interface.
Headings and bullets support the visual; they do not replace it when explaining relationships or flow. Split wide or tangled visuals into small, labeled parts. Do not add decorative visuals to a one-line answer.
Keep it clear
- Use everyday words. Define unfamiliar terms briefly on first use.
- Label parts and connections so the visual can be understood on its own.
- Pair status symbols with text; never rely on color alone. Explain ambiguous symbols with a short legend, without listing ordinary tree connectors.
- Show relevant limits, uncertainty, or costs when they affect understanding.
- Avoid fixed emoji schemes, repeated takeaway headings, and unnecessary sections.
Explain changes and choices
- Show what changes, where it fits, and its practical effect.
- Separate observed facts from recommendations; label unapproved changes Proposed.
- When a decision is needed, show concise options and meaningful tradeoffs in a small table or bullets. Prefer a choice control if available; otherwise ask a short question. Do not ask again for decisions already authorized.
Using the skill
/explain [topic]: explain the named topic visually./explain: explain the current discussion visually.
Where visuals belong
- Active file: when working on a file whose content would benefit from visuals, add them there beside the relevant content. Use a format the file supports and keep the edit within the current task.
- Chat: when no file is being worked on, or the explanation does not belong in that file, respond in chat.
- Separate file: create one only when asked to save or export. Use the
requested destination or the project's output folder. Otherwise, use
docs/explainers/at the verified Git root; outside a repository, ask where to save.
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.

