html-artifacts
Use when asked to create, generate, visualize, or convert material into a standalone HTML artifact, single-file self-contained .html report, interactive…
Skill by TheCheepeer
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thecheepeer-html-artifacts
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, presentations, frontend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/html-artifacts
What's inside
- Skill name
html-artifacts- Description
- Use when asked to create, generate, visualize, or convert material into a standalone HTML artifact, single-file self-contained .html report, interactive visual explanation, visual walkthrough, or HTML slide deck. Ideal for explaining code architecture, features, PR/diff reviews, incident timelines, or decision comparisons. Not for building production web applications or HTML emails.
- License
- Apache-2.0
- Instructions
- 77 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (8)
- README.md
- SKILL.md
- artifact-components.css · assets/
- component-contracts.md · references/
- content-patterns.md · references/
- quality-and-validation.md · references/
- research-basis.md · references/
- inline-components.py · scripts/
SKILL.md (first lines)
# Visual HTML Artifacts (HTML Artifacts) Generate visual documents that justify the use of HTML: the output must be easier to analyze, compare, or navigate than plain text. The default format is a local, self-contained `.html` file. ## Non-Negotiable Core Guidelines - **Ground in code first:** Read source files and trace real behavior before designing the interface. - **Default to document mode:** The document must be complete and legible for asynchronous reading. Use presentation/slide mode only when explicitly requested. - **Complete static narrative:** Interactivity deepens understanding, but the reader should never have to click to discover the main takeaway. - **Question-driven interactivity:** Every interactive control must answer a specific reader question: question -> interaction -> immediate visible feedback. - **100% offline single-file:** Inline all CSS, vanilla JavaScript, SVGs, and data within the file itself. Never depend on external CDNs, remote web fonts, or live server endpoints. - **Keep it local:** The file may expose internal repository architecture or data. Never deploy externally without explicit permission. - **Validate the output:** Ensure the HTML loads cleanly without JavaScript errors in the browser console. ## Presentation Modes | Mode | Purpose | Structure | | ----------------------- | --------------------------------------------------------- | ------------------------------------------------------------------------------------------ | | **Document** (Default) | Codebase explanation, PR review, incident, or research | Continuous reading, stable anchors, complete text, responsive layout, print-friendly | | **Explorable Document** | Causal mechanisms, parameter simulations, and comparisons | Complete default state paired with interactive controls to simulate scenarios in real time | | **Presentation** | Guided walkthrough for meetings or live demos | One concept per slide, keyboard navigation, and presenter notes | ## Workflow ### 1. Define Scope - Who will read this artifact, and what core question must it answer? - What repository, branch, or commit serves as the baseline? - Is this a temporary scratch artifact or intended for project documentation? ### 2. Map Evidence - Identify key files and line numbers. - Distinguish rigorously between: facts **observed in code**, conclusions **inferred**, and **proposed** improvements. - Document uncertainties rather than smoothing them over. ### 3. Structure the Reading Flow 1. Lead immediately with the primary answer or core finding. 2. Provide minimal necessary context. 3. Present the central visual model (diagram, state flow, topology, comparison, or timeline). 4. Demonstrate a concrete end-to-end trace. 5. Highlight trade-offs, risks, limitations, and decision forks. 6. Conclude with source index and recommended next actions. ### 4. Restrained Technical Visual Style Avoid visual clutter and AI design clichés: - No exaggerated gradients or decorative glassmorphism. - No unprompted animations or blinking elements lacking explanatory value. - No massive, tangled diagrams: break into a high-level map followed by focused detail views. - Use color strictly for functional meaning, never for generic decoration. ### 5. Technical Implementation - Use semantic HTML5, clean structured CSS, and inline SVGs. - Ensure accessibility: adequate contrast, visible keyboard focus indicators, and `prefers-reduced-motion` compliance. - Include print styles (`@media print`) for clean PDF export. - Sanitize code strings to prevent script injection or broken markup. ### 6. User Delivery After generating and validating the artifact, open it or provide the command to open: - On Windows: `Start-Process "path\to\artifact.html"` - On Linux/macOS: `xdg-open /path/to/artifact.html` In chat, share the absolute file path, presentation mode, and primary findings. Do not dump the entire raw HTML payload into the chat window. ## Supporting Documents - [references/content-patterns.md](references/content-patterns.md) — Content blueprints for PRs, systems flows, and decision comparisons. - [references/component-contracts.md](references/component-contracts.md) — Specifications for reusable UI components and canonical CSS. - [references/quality-and-validation.md](references/quality-and-validation.md) — Polish and accessibility verification checklist.
From TheCheepeer/omni-agents, Apache-2.0.
More from TheCheepeer/omni-agents
- 0.570score
strategic-roadmap
TheCheepeer
Use when the user asks "what should I work on in this repository?", "what is worth doing next?", requests a repository audit, technical debt priorities…
SkillAFreshness: AClaude Code +9 - 0.570score
writing-error-messages
TheCheepeer
Use when writing, reviewing, or rewriting human-facing error messages, form validation errors, empty states, authentication failures, error notifications…
SkillAFreshness: AClaude Code +9 - 0.570score
frontend-design-principles
TheCheepeer
Use when building or reviewing frontend user interfaces (UI) — dashboards, admin panels, landing pages, marketing sites, and web applications.
SkillAFreshness: AClaude Code +9 - 0.570score
coding-standards
TheCheepeer
Use when reviewing code quality, evaluating whether a refactoring or design is sound, identifying code smells, or judging architectural trade-offs.
SkillAFreshness: AClaude Code +9 - 0.570score
reducing-entropy
TheCheepeer
Use when evaluating architectures, reviewing code, or planning refactorings — measures success by total code volume in the end state rather than immediate…
SkillAFreshness: AClaude Code +9 - 0.570score
researching-codebases
TheCheepeer
Use when answering complex questions about a codebase that require exploring multiple modules or tracing flow across components.
SkillAFreshness: AClaude Code +9 - 0.570score
improving-prompts
TheCheepeer
Use when optimizing GEMINI.md, AGENTS.md, system prompts, custom slash commands, or skill files.
SkillAFreshness: AClaude Code +9 - 0.570score
skill-authoring
TheCheepeer
Use when creating, authoring, refining, or debugging skills for AI agents.
SkillAFreshness: AClaude Code +9 - 0.570score
writing-cli-skills
TheCheepeer
Use when authoring an agent skill that wraps a command-line interface (CLI) tool or terminal binary.
SkillAFreshness: AClaude Code +9 - 0.570score
crafting-effective-readmes
TheCheepeer
Use when drafting, structuring, or improving README.md files.
SkillAFreshness: AClaude Code +9 - 0.570score
diataxis
TheCheepeer
Structure, classify, and author technical documentation using the Diátaxis framework.
SkillAFreshness: AClaude Code +9 - 0.570score
feature-planning-artifacts
TheCheepeer
Use when creating or iterating staged planning artifacts for complex features: design discussions, structure outlines, final execution plans, or exploratory…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/TheCheepeer/omni-agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TheCheepeer
- 0.570score
writing-error-messages
TheCheepeer
Use when writing, reviewing, or rewriting human-facing error messages, form validation errors, empty states, authentication failures, error notifications…
SkillAFreshness: AClaude Code +9 - 0.570score
frontend-design-principles
TheCheepeer
Use when building or reviewing frontend user interfaces (UI) — dashboards, admin panels, landing pages, marketing sites, and web applications.
SkillAFreshness: AClaude Code +9 - 0.570score
coding-standards
TheCheepeer
Use when reviewing code quality, evaluating whether a refactoring or design is sound, identifying code smells, or judging architectural trade-offs.
SkillAFreshness: AClaude Code +9 - 0.570score
reducing-entropy
TheCheepeer
Use when evaluating architectures, reviewing code, or planning refactorings — measures success by total code volume in the end state rather than immediate…
SkillAFreshness: AClaude Code +9 - 0.570score
researching-codebases
TheCheepeer
Use when answering complex questions about a codebase that require exploring multiple modules or tracing flow across components.
SkillAFreshness: AClaude Code +9 - 0.570score
writing
TheCheepeer
Prose and writing guidelines for human-facing technical communication — clear, concrete, and free from prefabricated AI clichés.
SkillAFreshness: AClaude Code +9
Cite this page
html-artifacts skill. Agent Mart. https://agentmart.dev/skills/thecheepeer-html-artifacts (last updated 2026-10-24)