// 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)
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
Web reading, search, academic research, NLP, screenshots, and PDF extraction via Jina AI mcpcall. TRIGGER when need to read a URL, search the web, find academic papers (arXiv/SSRN), classify text, rerank documents, deduplicate content, capture screenshots, or extract PDF figures.
Guide and template for converting MCP servers into self-contained Claude Code skills with a Python wrapper script. TRIGGER when creating a new MCP skill, wrapping an MCP server as a skill, or need the mcpcall script template.
AI-powered documentation for GitHub repositories via DeepWiki MCP. TRIGGER when need to understand a GitHub repository, read its documentation topics, ask questions about a repo's codebase, architecture, or usage, or explore how an open-source project works.
Search real-world code examples from over a million public GitHub repositories via grep.app MCP. TRIGGER when need to find code usage patterns, see how developers use a library/API in practice, find production examples of a specific function or syntax, or search GitHub code at scale.
Best practices for AI-driven English-to-Chinese translation. This skill should be used when the user asks to "translate to Chinese", "update the Chinese translation", "improve Chinese translation", "fix translation quality", "review Chinese translation", or when translating any English text into Chinese. Also applies when polishing an existing Chinese translation of English content.
| 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.
MUST explicitly ask for user permission before use. Chrome CDP runs in a headful browser in user screen. Start using Chrome CDP without user confirmation is offensive. User refuse: PAUSE IMMEDIATELY.
Use /agent-browser skill instead if you need headless access to web pages.
chrome://inspect/#remote-debugging and toggle the switchDevToolsActivePort is in a non-standard location, set CDP_PORT_FILE to its full pathAll 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: screenshot-<target>.png in runtime dir
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 open [url] # open new tab (each triggers Allow prompt)
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.