lexmount

Use when the user asks for web research, search, recommendations, comparison, evidence gathering, website inspection, browser automation, page interaction, form filling, login-gated browsing, screenshots, scraping/extraction, or operating a remote browser with Lexmount Browser.

仓库会话入口 skill。仓库会话第一轮、续修 PR、处理反馈、调整协作规则，或判断 specs、plans、topics、验证证据承载位时使用。

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when the user provides structured or semi-structured data (CSV, Excel, JSON, pasted tables, or metric snippets) and asks for a polished executive-style deliverable — an HTML report, an infographic image, or both.

Use when the user asks for GitHub daily, weekly, project, repository, team, organization, or personal activity reports based on issues, pull requests, reviews, commits, or GitHub Projects v2.

Use when a user provides Notion page links and asks to read page content, recursively read child pages, or verify Notion API access using official Notion API endpoints. This skill is read-only by default and portable across repositories.

Use when creating or updating GitHub pull request titles and bodies, especially when the current PR text is empty, vague, commit-driven, or inconsistent with the established PR structure

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Create and integrate new modular agents for browseruse-bench (BaseAgent in browseruse_bench/agents/, registry import in __init__.py, entry in configs/agent_registry.yaml, runtime config in root config.yaml agents section). Use when a user asks to add/register a new agent, scaffold a custom agent, or implement a new agent based on external docs.

Generate and maintain PR review checklists from GitHub review threads for the current branch PR or a specified PR. Use when you need reviewer comments with exact code locations, nearby code snippets, and raw thread chat logs, and when you want continuously updated .pr/<pr_number>/review_checklist.md and .pr/<pr_number>/unresolved_checklist.md.

Use this skill whenever the user describes a benchmark experiment using any combination of these parameters — agent (e.g. browser-use, skyvern), model (e.g. deepseek, minimax, claude, gemini, gpt), data/benchmark (e.g. LexBench-Browser), browser (e.g. Chrome-Local, lexmount), and tasks (specific IDs or "all"). Trigger phrases include "跑实验 agent=xxx model=xxx", "跑实验 agent xxx model xxx", "run [model] on [tasks]", "eval [model] results", "re-run [model]", or any request that specifies an agent + model + task set to execute or evaluate. Also triggers on requests to chain run→eval pipelines, check experiment progress, or read final results.

Create GitHub pull requests for browseruse-bench with clear conventional-commit style titles and a review-ready body.

Update Mintlify documentation in docs/ for browseruse-bench, including adding new pages, enforcing .mdx files, and keeping English/Chinese navigation parity. Use when adding or editing docs pages, fixing missing/incorrect language variants, or updating docs/docs.json navigation.

Draft and track fixes for unresolved PR review threads. Use when you need to generate a solution draft markdown for the latest/current PR unresolved threads and keep `.pr/<pr_number>/review_checklist.md` plus `.pr/<pr_number>/unresolved_checklist.md` checkbox states synchronized as issues are fixed.

Operate Lexmount remote browsers with browser-cli. Use when Codex or another agent needs to create, list, inspect, keep alive, or close browser sessions; manage persistent contexts, pick reusable contexts, or detect locked contexts; guide authentication with auth status/scopes/token-info/refresh/logout/clear-credentials/connect-requirements/export-env/login; verify installation, environment, and API connectivity with doctor; discover installed commands/workflows; read packaged references with reference list/get; inspect packaged playbooks and case examples with example list/get; validate/run JSON/YAML browser case files; open pages, read page info, wait for selectors/states/roles/URLs/load/network/text/forms/dialogs/frames/console/fetch-XHR, act/click/type/fill/select/check/hover/press/scroll, inspect interactive/accessibility/page diagnostics, manage storage/cookies, navigate, screenshot, eval, snapshot, or verify credentials without custom Playwright.

Operate Lexmount remote browsers with browser-cli. Use when Codex or another agent needs to create, list, inspect, keep alive, or close browser sessions; manage persistent contexts, pick reusable contexts, or detect locked contexts; guide authentication with auth status/scopes/token-info/refresh/logout/clear-credentials/connect-requirements/export-env/login; verify installation, environment, and API connectivity with doctor; discover installed commands/workflows; read packaged references with reference list/get; inspect packaged playbooks and case examples with example list/get; validate/run JSON/YAML browser case files; open pages, read page info, wait for selectors/states/roles/URLs/load/network/text/forms/dialogs/frames/console/fetch-XHR, act/click/type/fill/select/check/hover/press/scroll, inspect interactive/accessibility/page diagnostics, manage storage/cookies, navigate, screenshot, eval, snapshot, or verify credentials without custom Playwright.

Use Lexmount WebFetch through webfetch-cli for lightweight public page extraction and DOM dump tasks. Prefer this skill when the task needs structured extraction or rendered HTML capture without creating a live remote browser session.

Use Lexmount WebFetch through webfetch-cli for lightweight public page extraction and DOM dump tasks. Prefer this skill when the task needs structured extraction or rendered HTML capture without creating a live remote browser session.