Chrome Extensions · For developers

Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login…

mxyhi/ok-skills

Write or rewrite a Voyager pull request description. An agent skill from voyager-crew/voyager.

voyager-crew/voyager

Control a real browser via CDP — navigate, click, type, screenshot, and extract web content.

AgenticMatrix/coderix

A skill your agent uses when the user asks to create a release, bump version, tag, or publish a new version of the Slopless browser extension.

alexeyfv/slopless

Create, review, or update Harness Anything preset-manifest/v3 packages, including profiles, completion gates, template selections, output shapes, script entrypoints, capability declarations, package…

FairladyZ625/harness-anything

Control and inspect the user's real Google Chrome through byob's local MCP tools.

wxtsky/byob

Release ZenUML web-sequence to production (app.zenuml.com) by publishing a GitHub release, wait for deploy-prod CI + @smoke, then run a release-delta spot check (spot-check skill Step 5.5).

ZenUml/web-sequence

Diagnoses why the Claude in Chrome MCP tools report the browser extension as not connected, with macOS-specific checks and a fix for the Claude.app native host conflict.

trailofbits/skills

Diagnose extension-caused memory leaks, freezes, and CPU storms on live third-party sites via controlled attribution experiments, CDP metrics, heap snapshots, and browser-process trace profiling…

mengxi-ream/read-frog

Epupp architecture, development patterns, and system contracts.

PEZ/epupp

Drive the PenguinHarness agent browser — the desktop app's built-in browser or the user's own Chrome — from the shell with penguin browser: open pages, read them as simplified HTML or text, act with…

Prism-Shadow/penguin-harness

Extract structured data from websites into CSV or JSON. An agent skill from hanzili/hanzi-browse.

hanzili/hanzi-browse

Create new Cebian skills, edit or improve existing ones, scaffold multi-file skill packages, and validate them against the agentskills.io specification.

maotoumao/Cebian

A skill your agent uses when working on Trilium's browser extension, the web clipper (apps/web-clipper, built with WXT for Chrome MV3 and Firefox MV2) — its background script, content script…

TriliumNext/Trilium

Trust Wallet open-source libraries — Wallet Core (HD wallets, address derivation, tx signing in Swift/Kotlin/TypeScript/Go for 140+ chains), Web3 Provider (dApp connection for…

trustwallet/tw-agent-skills

Launches Chrome with an unpacked extension over CDP, opens its sidepanel, popup or options page, and hands over to cdp-connect for clicks, typing and screenshots.

adobe/skills

Test a web app like a QA person — open it in a real browser, click through flows, and report what's broken with screenshots and code references.

hanzili/hanzi-browse

面向没有编程经验的用户，把想法做成可试用的浏览器插件，并完成检查、商店材料、审核提交和上线验证；也用于继续已有插件、排错和发布新版。用户说“帮我做个插件”“把插件上架”“继续我的插件”时使用。普通网站开发、仅查询插件知识不触发。

davepoon/buildwithclaude

已有功能的需求变更闭环（门禁式七步）。触发硬条件：要改的功能已经实现并跑起来了。当用户说"改需求""需求变更""调整交互""改功能""重构流程"，或改动容易散到多个文件、碰到鉴权/存储/配置/权限、需要可靠验证 + 回滚方案时使用。流程：锁 scope 写 change brief → 从代码确认当前行为（不靠记忆和假设）→ 影响面与风险评估 + 回滚计划 →…

yunshu0909/yunshu_skillshub

Master specialized skill for building 2025/2026-grade browser extensions.

xenitV1/claude-code-maestro

Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions.

davila7/claude-code-templates

Controls the user's Chrome through Qwen Code's Node REPL and Browser SDK, with the Qwen Code Chrome extension, profile binding and tab ownership handling.

QwenLM/qwen-code

审计自上次发版以来的提交，把遗漏的「用户可见变更」补进 CHANGELOG.md 的 [Unreleased]；可选地把 [Unreleased] 收口成正式版本节

maotoumao/Cebian

Expert guidelines for Chrome extension development with Manifest V3, covering security, performance, and best practices.

Mindrally/skills

Main application building orchestrator. An agent skill from xenitV1/Antigravity-Workflows.

xenitV1/Antigravity-Workflows

Apply to jobs from your real browser. An agent skill from hanzili/hanzi-browse.

hanzili/hanzi-browse

调研 package.json 所有依赖的最新版本，交叉验证版本差异，给出可升级到最新版的结论. An agent skill from maotoumao/Cebian.

maotoumao/Cebian

Chrome Extension auth with @clerk/chrome-extension -- popup/sidepanel setup, syncHost for OAuth/SAML via web app, createClerkClient for service workers and headless extensions, stable CRX ID.

geekskai/blog

Expert in building Chrome Extensions using Manifest V3. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Find people on LinkedIn and send personalized connection requests.

hanzili/hanzi-browse

Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions.

sickn33/agentic-awesome-skills

Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.

maotoumao/Cebian

Builds, tests, packages, and prepares Chrome extensions for store launch from a plain-language idea; use for new extensions, fixes, releases, and submission recovery.

sickn33/agentic-awesome-skills

Authorized reverse engineering of Chrome/Firefox extensions: manifest analysis, background workers, content scripts, and extension-based credential or data-exposure research.

sickn33/agentic-awesome-skills

Post content across social platforms from your real signed-in browser.

hanzili/hanzi-browse

Identify and name Chrome instances connected to the Claude-in-Chrome extension under the current Claude account, and persist a stable deviceId - name mapping to a local file outside the repo.

hmislk/hmis

Create PostHog error tracking suppression rules to drop high-volume, low-value errors at ingestion.

PostHog/posthog

CRXJS Chrome extension development — true HMR for popup, options, content scripts, side panels, manifest-driven builds, dynamic content script imports (?script, ?script&module), and defineManifest…

samber/cc-skills

"Comprehensive guide for building Chrome extensions with Manifest V3.

LeoYeAI/openclaw-master-skills

Truthful answers about what the Vellum client apps can and cannot do on the user's device.

vellum-ai/vellum-assistant

Integrate TwinMind meeting transcription workflows into CI/CD pipelines for automated meeting documentation and action item tracking.

jeremylongshore/tons-of-skills-marketplace

Optimize TwinMind costs across Free, Pro ($10/mo), and Enterprise tiers with usage monitoring and tier selection guidance.

jeremylongshore/tons-of-skills-marketplace

Deploy TwinMind integrations to production environments with Chrome extension deployment, mobile app configuration, and API access setup.

jeremylongshore/tons-of-skills-marketplace

Configure TwinMind Enterprise with on-premise deployment, custom AI models, SSO integration, and team-wide transcript sharing.

jeremylongshore/tons-of-skills-marketplace

Optimize TwinMind transcription accuracy and speed with Ear-3 model configuration, audio quality tuning, and caching strategies.

jeremylongshore/tons-of-skills-marketplace

Production architecture for meeting AI systems using TwinMind: transcription pipeline, memory vault, action item workflow, and calendar integration.

jeremylongshore/tons-of-skills-marketplace

Security best practices for TwinMind: on-device audio processing, encrypted cloud backups, microphone permissions, and data privacy controls.

jeremylongshore/tons-of-skills-marketplace

Handle TwinMind meeting events including transcription completion, action item extraction, and calendar sync notifications.

jeremylongshore/tons-of-skills-marketplace