html-diagram-artifact
Skill16 starsChanged 5 months agoMITView on GitHub
Create a self-contained HTML artifact for architecture, stack, and system-flow explanation using SVG-first diagrams and minimal prose. Use when the user needs a standalone visual deliverable that makes a system, request path, ownership map, or execution flow click quickly.
In this repository94 other files it gives its agents.
- agent-friction-ledgerSkill
- agent-learning-layer-triageSkill
- agent-operations-contractSkill
- agents-best-practicesSkill
- agent-tool-contract-reviewSkill
- anti-slop-reviewSkill
- architecture-deepening-reviewSkill
- assumption-excavationSkill
- authorized-security-routerSkill
- book-to-skillSkill
- bounded-evaluationSkill
- bounded-growth-loopSkill
- bounded-orchestration-contractSkill
- brief-first-executionSkill
- browser-verificationSkill
- bug-evidence-protocolSkill
- codex-review-loopSkill
- compaction-survivalSkill
- complexity-optimizerSkill
- confidence-fragility-reviewSkill
- context-degradation-reviewSkill
- corporate-surfaceSkill
- delivery-baseline-auditSkill
- delivery-preflight-gateSkill
- design-critique-polishSkill
- designmd-brand-kitSkill
- design-register-bootstrapSkill
- diagnoseSkill
- doc-grounded-grillingSkill
- doc-to-lora-evaluatorSkill
- durable-context-maintenanceSkill
- dynamic-workflow-packetsSkill
- editorial-surfaceSkill
- evidence-ledger-researchSkill
- filesystem-context-disciplineSkill
- fluid-interaction-reviewSkill
- frontend-product-builderSkill
- frontend-taste-layerSkill
- git-native-context-contractSkill
- goal-loop-designerSkill
- graph-guided-code-readingSkill
- handoffSkill
- happy-handoffSkill
- html-brief-artifactSkill
- hypothesis-diversificationSkill
- idea-to-ship-gatesSkill
- knowledge-base-enrichmentSkill
- lean-context-layoutSkill
- local-inference-tuningSkill
- loop-hardening-contractSkill
- loopops-protocolSkill
- loop-readiness-reviewSkill
- lottie-motion-builderSkill
- minimal-diff-builderSkill
- motion-review-gateSkill
- overengineering-reviewSkill
- personal-workspace-routerSkill
- phase-spec-executionSkill
- pipeline-readiness-gateSkill
- plan-to-issuesSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 13 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈13
Distinctive · estimate
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
- Very specific: line 38
Create one self-contained .html file that:
- Distinctive: line 52
Keep prose light: title, framing line, labels, and optional detail panel.
- Distinctive: line 53
Prefer 1-2 dominant flows over showing every possible edge.
- Distinctive: line 56
Use interaction only when it helps explain sequence, causality, or scope.
- Distinctive: line 61
Use a restrained palette with one accent family.
- Distinctive: line 62
Use hierarchy through typography, spacing, and contrast.
- Distinctive: line 63
Keep labels short and scannable.
- Distinctive: line 64
Avoid dashboard chrome, fake browser frames, and decorative card spam.
- Distinctive: line 65
If serif headings help, use them sparingly.
- Distinctive: line 72
Check desktop and mobile layouts.
- Distinctive: line 73
Check there is no horizontal overflow.
- Distinctive: line 74
Check the theme toggle works and persists.
- Distinctive: line 75
Check SVG text remains legible in both themes.
- Distinctive: line 76
Check interactive highlighting if present.
≈ “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
HTML Diagram Artifact
Produce a standalone HTML deliverable, not a production app surface.
Review:
references/architecture-example.htmlreferences/style-notes.md
Best Fit
- architecture overviews;
- request or event flows;
- stack explainers;
- system boundary maps;
- component relationship diagrams;
- interactive walkthroughs where flow highlighting genuinely improves understanding.
Not The Best Fit
- full product frontends;
- landing pages;
- dense prose reports;
- diagrams that would be clearer as Mermaid or a static image;
- speculative visual polish without a concrete explanation job.
Output Contract
Create one self-contained .html file that:
- works without a build step;
- uses semantic HTML plus inline CSS and JS only when needed;
- includes a dark mode toggle;
- persists theme via
localStorage; - applies theme before paint in
<head>; - uses SVG as the primary diagram surface;
- drives SVG colors from CSS variables rather than hard-coded values inside the SVG;
- remains usable on desktop and mobile widths.
Diagram Rules
- Lead with structure first, decoration second.
- Keep prose light: title, framing line, labels, and optional detail panel.
- Prefer 1-2 dominant flows over showing every possible edge.
- Group by zones, boundaries, or ownership domains.
- Make important nodes distinct through role, not random styling.
- Use interaction only when it helps explain sequence, causality, or scope.
- Respect reduced-motion preferences.
Visual Rules
- Use a restrained palette with one accent family.
- Use hierarchy through typography, spacing, and contrast.
- Keep labels short and scannable.
- Avoid dashboard chrome, fake browser frames, and decorative card spam.
- If serif headings help, use them sparingly.
Verification
Before finishing:
- Open the artifact in a browser.
- Check desktop and mobile layouts.
- Check there is no horizontal overflow.
- Check the theme toggle works and persists.
- Check SVG text remains legible in both themes.
- Check interactive highlighting if present.
- Report limitations honestly.
Pair with browser-verification when browser tooling is available.
Final Report
Include:
- output file path;
- artifact type;
- flows or areas covered;
- browser checks run;
- known omissions or simplifications.
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.

