using-lightpanda
Skill0 starsChanged 7 months agoCC-BY-SA-4.0View on GitHub
Operates Lightpanda, a Zig-based headless browser with no rendering pipeline, as an AI agent's browser tool via native MCP or CDP. Covers MCP tool selection (goto, markdown, semantic_tree, interactiveElements, structuredData, click, fill), output mode strategy, the observe-decide-act loop, actions grounded in node IDs, token-efficient page reading, and Chrome fallback triggers. Use when tasks require interactive or stateful web navigation on JS-heavy sites (multi-step flows, form fill/click actions, DOM-aware extraction by node ID), or when the user explicitly asks to use Lightpanda.
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
In this repository42 other files it gives its agents.
- applying-composition-over-inheritanceSkill
- applying-practical-typographySkill
- applying-vertical-slice-architectureSkill
- arazzo-specificationSkill
- assessing-platform-scalabilitySkill
- auto-improving-agents-mdSkill
- balancing-couplingSkill
- benchmarking-with-hyperfineSkill
- building-tuning-panelsSkill
- commenting-codeSkill
- creating-c4-diagramsSkill
- designing-backend-error-messagesSkill
- designing-deep-modulesSkill
- designing-rest-apisSkill
- explaining-code-changesSkill
- humanizing-proseSkill
- kotlin-functional-programmingSkill
- making-invalid-states-unrepresentableSkill
- markdown-section-summarizerSkill
- mermaid-sequence-diagramsSkill
- obsidian-best-practicesSkill
- property-based-testing-with-kotestSkill
- quizzing-before-approvingSkill
- rendering-clean-diagramsSkill
- reviewing-pull-requestsSkill
- searching-and-extracting-web-with-parallel-cliSkill
- slicing-pbisSkill
- specifying-by-exampleSkill
- tdd-with-llm-agentsSkill
- threat-modelingSkill
- toon-formatSkill
- tweet-reviewSkill
- using-git-notes-for-ai-contextSkill
- using-markitSkill
- writing-agent-skillsSkill
- writing-anki-cardsSkill
- writing-checklist-communicationsSkill
- writing-git-commit-messagesSkill
- writing-okrsSkill
- writing-persuasive-documentsSkill
- writing-project-status-reportsSkill
- writing-wiki-contentSkill
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.