菜单
Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | chrome-cdp |
| description | Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome) |
Lightweight Chrome DevTools Protocol CLI. Connects directly via WebSocket — no Puppeteer, works with 100+ tabs, instant connection.
chrome://inspect/#remote-debugging and toggle the switchAll commands use scripts/cdp.mjs. The <target> is a unique targetId prefix from list; copy the full prefix shown in the list output (for example 6BE827FA). The CLI rejects ambiguous prefixes.
scripts/cdp.mjs list
scripts/cdp.mjs shot <target> [file] # default: /tmp/screenshot.png
Captures the viewport only. Scroll first with eval if you need content below the fold. Output includes the page's DPR and coordinate conversion hint (see Coordinates below).
scripts/cdp.mjs snap <target>
scripts/cdp.mjs eval <target> <expr>
Watch out: avoid index-based selection (
querySelectorAll(...)[i]) across multipleevalcalls when the DOM can change between them (e.g. after clicking Ignore, card indices shift). Collect all data in oneevalor use stable selectors.
scripts/cdp.mjs html <target> [selector] # full page or element HTML
scripts/cdp.mjs nav <target> <url> # navigate and wait for load
scripts/cdp.mjs net <target> # resource timing entries
scripts/cdp.mjs click <target> <selector> # click element by CSS selector
scripts/cdp.mjs clickxy <target> <x> <y> # click at CSS pixel coords
scripts/cdp.mjs type <target> <text> # Input.insertText at current focus; works in cross-origin iframes unlike eval
scripts/cdp.mjs loadall <target> <selector> [ms] # click "load more" until gone (default 1500ms between clicks)
scripts/cdp.mjs evalraw <target> <method> [json] # raw CDP command passthrough
scripts/cdp.mjs stop [target] # stop daemon(s)
shot saves an image at native resolution: image pixels = CSS pixels × DPR. CDP Input events (clickxy etc.) take CSS pixels.
CSS px = screenshot image px / DPR
shot prints the DPR for the current page. Typical Retina (DPR=2): divide screenshot coords by 2.
snap --compact over html for page structure.type (not eval) to enter text in cross-origin iframes — click/clickxy to focus first, then type.orchestrate multiple amp agents with bidirectional tmux communication. use for multi-hour autonomous runs with INDEPENDENT parallel tasks. NOT for review courts or generating opinions to reconcile.
systematic investigation and debugging methodology. hypothesis-driven analysis with verification agents. use for incident response, codebase archaeology, dependency mapping, root cause analysis, or any investigation requiring verified findings.
apply documentation philosophy — explain why, not what. use for jsdocs, READMEs, inline comments.
git workflows for agents: ship (stage → commit → push), worktree (parallel branches), hunks (selective staging). never force push, never git add -A, conventional commits. triggers on: commit, push, stage, ship, git add, worktree, hunks, selective staging.
structured investigation-to-PR workflow for linear issues. hypothesis-driven debugging with browser validation and counterfactual proof. use when investigating a linear ticket, fixing a UI bug, or shipping a fix with evidence. triggers on: investigate issue, fix bug, nexus-fix, AXM-, linear issue.
record context that would help in future sessions. use after learning something, discovering a gotcha, or making a decision worth preserving. test: would a future agent starting fresh benefit from knowing this?