html-visualization
Build, revise, and evaluate browser-rendered HTML visualizations for concepts, systems, codebases, architectures, workflows, timelines, comparisons, and other…
Skill by ejarmand
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/ejarmand-html-visualization
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: frontend, testing, data
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/html-visualization
What's inside
- Skill name
html-visualization- Description
- Build, revise, and evaluate browser-rendered HTML visualizations for concepts, systems, codebases, architectures, workflows, timelines, comparisons, and other relationship-heavy explanations. Use to create or improve an HTML/CSS/JS diagram, process map, interactive explainer, or visual documentation, validating the rendered result with Playwright CLI screenshots.
- License
- MIT
- Instructions
- 68 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# HTML Visualizations
Build the visualization in code, render it in a real browser, and judge it from screenshots. Prefer pedagogical clarity over marketing polish.
## Plan
- Name the audience and the main questions the visualization must answer. That answer is your stop rule.
- Inspect the source material or code first so the diagram reflects the real implementation.
- Pick the simplest structure that fits the relationships. Identify the content model before adding visual detail.
- Use HTML/CSS for layout; reach for SVG or canvas only when connectors, geometry, or density demand it. Add interaction only when the core explanation can't stand without it.
## Build and render
Prefer a standalone HTML file. Before choosing a browser, inspect the installed
CLI because accepted browser values and installed channels can drift:
```bash
playwright-cli open --help
playwright-cli install-browser --help
```
Start from a value listed by the installed `open --help` (at the pinned review
point: `chrome`, `firefox`, `webkit`, and `msedge`), but treat the error
message as the final authority — a listed value can still fail when its browser
channel is not installed, and an unlisted alias can work (observed: `chromium`
was absent from the help yet accepted, mapping to `chrome-for-testing`, while
`chrome` failed wanting the system Chrome channel). If `open` reports a missing
browser, install the exact bundle named by the error (for example,
`playwright-cli install-browser chrome-for-testing`) and retry with the value
that named it.
Serve the HTML over HTTP because the browser daemon blocks `file://` URLs. Run
this as one shell block so the variables and cleanup trap remain active, after
setting `browser` to the accepted value you selected:
```bash
set -e
viz_dir=/abs/dir/containing/viz
browser=SELECTED_BROWSER
shot_dir="$(mktemp -d -t html-viz-XXXXXX)"
port="$(python3 -c 'import socket; s=socket.socket(); s.bind(("127.0.0.1", 0)); print(s.getsockname()[1]); s.close()')"
python3 -m http.server "$port" --bind 127.0.0.1 --directory "$viz_dir" >/dev/null 2>&1 &
server_pid=$!
trap 'kill "$server_pid" 2>/dev/null' EXIT
url="http://127.0.0.1:$port/viz.html"
curl --retry 5 --retry-connrefused -fsS "$url" -o /dev/null
playwright-cli -s=html-viz open --browser="$browser" "$url"
playwright-cli -s=html-viz resize 1440 900
playwright-cli -s=html-viz screenshot --filename="$shot_dir/viz.png"
echo "$shot_dir/viz.png"
```
View the printed screenshot path. Re-run the block after changes, using the same viewport for comparison.
- Do not assume `chromium` is an accepted alias; use the installed help and
install guidance as the source of truth.
- Use the named session on every command so concurrent browser sessions cannot interfere.
- Check `playwright-cli console` after load and interactions; a missing `/favicon.ico` is expected noise.
- Use `playwright-cli snapshot` when diagnosing layout or DOM structure.
## Critique and iterate
Check accuracy, reading path, clipping or overlap, legibility, scrolling, contrast, and color-independent meaning. Fix the largest defect and re-screenshot. Stop when the visualization answers the target question with no meaningful defect.
When done, close the browser session and remove the printed screenshot directory. Then report the HTML location, what you verified, and any known limitations.From ejarmand/skills, MIT.
More from ejarmand/skills
- 0.592score
cursor-agent
ejarmand
Run Cursor Agent CLI as an independent coding agent for implementation, investigation, planning, or review in a local workspace.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
opencode-agent
ejarmand
Run OpenCode CLI as an independent coding agent across its provider catalog, capture its session, or dispatch its profiled GitHub PR reviewer.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
pr-ping-pong
ejarmand
Drive an issue or pull request through alternating rallies of implementation and cross-provider review until it is review-clean.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
file-pr
ejarmand
Structure GitHub pull requests, issues, and comments.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
code-review
ejarmand
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
improve-codebase-architecture
ejarmand
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
fix-steering
ejarmand
Analyze Codex history for interruptions, corrections, and user steering that indicate agent errors.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
codex-agent
ejarmand
Run Codex CLI as an independent coding worker for implementation, investigation, planning, or review, then monitor and verify its result.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
claude-agent
ejarmand
Run Claude Code CLI headless as an independent coding agent for implementation, investigation, planning, or review in a local workspace.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
codebase-design
ejarmand
Shared vocabulary for designing deep modules, and home of the unified code standard (STANDARD.md).
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
cross-provider-agent
ejarmand
Dispatch a bounded task to a Claude, Codex, Cursor, or OpenCode CLI agent with least authority.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
implement
ejarmand
Implement a prepared spec or set of tickets.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 20
- Last commit (this folder)
- Aug 6, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ejarmand/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ejarmand
- 0.592score
cursor-agent
ejarmand
Run Cursor Agent CLI as an independent coding agent for implementation, investigation, planning, or review in a local workspace.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
opencode-agent
ejarmand
Run OpenCode CLI as an independent coding agent across its provider catalog, capture its session, or dispatch its profiled GitHub PR reviewer.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
pr-ping-pong
ejarmand
Drive an issue or pull request through alternating rallies of implementation and cross-provider review until it is review-clean.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
file-pr
ejarmand
Structure GitHub pull requests, issues, and comments.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
code-review
ejarmand
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
improve-codebase-architecture
ejarmand
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
html-visualization skill. Agent Mart. https://agentmart.dev/skills/ejarmand-html-visualization (last updated 2026-10-24)