html-export
Installation
SKILL.md
Codex compatibility note:
- Invoke
$skill-name: load the registered.agents/skills/<name>/SKILL.mdand execute it with Codex tools; no separateSkilltool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author.claude/**; mirrors are generated.- Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
- Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agentsubagent(s) for that task.- Preserve protocol order unless the user approves a deviation. Workflows use
$start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.
Quick Summary
Goal: Turn a local HTML file into PNG screenshots with a page-error and blank-capture check, a vector PDF, an MP4 or a GIF, through one entry point that reports the result as an exit code.
Workflow:
- Pick a target —
--to=png(render evidence),--to=pdf(print or slides),--to=mp4/--to=gif(deterministic animation recording) - Check setup — dependencies are opt-in and skill-local; a missing one exits
3with the setup commands - Export —
node .claude/skills/html-export/scripts/export.cjs --to=<target> <input...> [options] - Read the exit code first — then
report.json/frames.json, then the output; a written file is never proof on its own. A reused--outkeeps earlier outputs: only the files this run's manifest names belong to it —report.jsonfiles[](png),report.jsonoutput(pdf),frames.jsonoutput(mp4/gif)
Key Rules: