Skills for Real Engineers. Straight from my .agents directory.
webperf-core-web-vitals
Agent skill fromnucliweb/webperf-snippets
Intelligent Core Web Vitals analysis with automated workflows and decision trees. Measures LCP, CLS, INP with guided debugging that automatically determines follow-up analysis based on results. Includes workflows for LCP deep dive (5 phases), CLS investigation (loading vs interaction), INP debugging (latency breakdown + attribution), and cross-skill integration with loading, interaction, and media skills. Use when the user asks about Core Web Vitals, LCP optimization, layout shifts, or interaction responsiveness. Compatible with Chrome DevTools MCP.
How to install webperf-core-web-vitals
npx skills add nucliweb/webperf-snippets# or add only this skill to Claude Code: copy the folder
skills/webperf-core-web-vitals/
# into
~/.claude/skills/webperf-core-web-vitals/ (all projects)
.claude/skills/webperf-core-web-vitals/ (one project)
1# WebPerf: Core Web Vitals23JavaScript snippets for measuring web performance in Chrome DevTools.45## Running a script671. Run the script with `mcp__chrome-devtools__evaluate_script`, passing the file instead of its code: `sourcePath` with the absolute path of `scripts/<Name>.js` in this skill, and `format: "script"`, since a script runs by itself and is not a function. Read the object it returns. The scripts have no console output, so the returned object is the result: `script`, `status` and the metric data (`value`, `rating`, `details`, `items`, `issues`), as described in `references/schema.md`.82. When `status` is `"tracking"`, the script keeps observing the page. After the interactions, call the function named in `getDataFn` with another `mcp__chrome-devtools__evaluate_script` call, as an arrow function in `function`, for example `() => getINP()`, and read the object it returns.93. When `status` is `"error"` or `"unsupported"`, read `error`: the page may not have loaded yet, or the browser lacks the API.10…
Excerpt shown under the repository's MIT license.
More skills in webperf-snippets
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
