Discover your next essential.

Browse 11303 agents, skills, and projects. Find a useful starting point, then search, compare, and curate your stack.

Browser Use ↗

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

browser-act ↗

Browser automation CLI for AI agents. NEVER run browser-act commands directly via Bash — always invoke this skill first. Use browser-act when a user mentions…

browser-act-skill-forge ↗

Forges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-exploration later.

browser-act/browser-act ↗

Automate authenticated browsers with extraction and human handoff

browser-act/skills ↗

BrowserAct enables AI agents and teams to perform real-browser automation, web data extraction, and account-based workflows.

browser-cdp ↗

Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug…

browser-fingerprint-audit ↗

Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes,…

browser-mcp-agent ↗

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device…

browser-testing-with-devtools ↗

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture…

Python web-agent harness: natural-language goals become browser actions, driven directly over the Chrome DevTools Protocol (it dropped Playwright in August 2025). The biggest community in the browser-agent category.

browser-use ↗

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI…

browser-use ↗

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with w...

browser-use ↗

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

browser-use/video-use ↗

Introducing video-use — edit videos with Claude Code. 100% open source.

browserbase/browser ↗

Automate web browser interactions through natural language CLI commands

browserbase/browserbase-cli ↗

A CLI wrapper around the Browserbase platform.

browserbase/cookie-sync ↗

Exports cookies from your local Chrome browser into a Browserbase persistent context.

browserbase/fetch ↗

Fetches HTML, JSON, headers, and status codes from URLs through the Browserbase API without spinning up a full browser session.

browserbase/functions ↗

Deploy browser automation scripts as serverless cloud functions

browserbase/search ↗

Search the web via the Browserbase API with structured results

browserbase/ui-test ↗

Run adversarial UI tests by analyzing git diffs in a real browser

browserwing ↗

Control and automate browser actions via HTTP API, including navigation, element interaction.

browsh ↗

A modern text-based browser. Renders web pages in the terminal using headless Firefox.

brquatti/readme-style ↗

Keep every README on your GitHub profile in the same visual style, with no effort

BruceFloyd/claude-skill-speaker-page ↗

A Claude Code skill for adding a person's profile page to an event or conference website — a speaker, panelist, instructor, board member — and wiring it into every place the site lists people.

brunob54/superpowers-orchestrator ↗

Superpowers is a plugin for coding agents (Claude Code and GitHub Copilot CLI, which are the two it has been used with — Copilot CLI only up to v7.13.0, so later releases are untested there; Cursor and OpenCode integrations exist but are untested, and Codex is no longer supported — see Platform status) that adds a disciplined development workflow: a design specification first, then a task plan, then test-driven implementation with staged code reviews. The workflow is implemented as *skills* (instruction files the agent follows) and *hooks* (scripts that run automatically at session events).

brunoflma/jusmanizer ↗

Legal Tech · Review of legal style in Portuguese. Skill with 33 standards, practical examples and prompts for the routine of advocacy.

Brxerq/claude-cockpit ↗

Zero-token progress bars and a cache-aware model and effort router for Claude Code

BryanBenner/de-ai-gate ↗

A read-only content-honesty gate for AI-assisted writing. Catches the typographic and lexical tells of machine-generated prose before it ships - em-dashes, curly quotes, invisible unicode, and high-precision AI phrase tells - with a hard pass/fail exit code. Deterministic regex, no network, no credentials.

BryanBenner/no-fabricate-gate ↗

A read-only fact-honesty gate for AI-assisted writing. Every statistic in your published copy must trace to a cited source. Anything that doesn't fails the build.

bryanG2518/paper-grader-skill ↗

An Agent Skill that grades an academic paper the way a professor in that specific field will. It reads the paper, works out which of 50 academic disciplines it belongs to, applies that field's standards, and hands back a PDF: a current grade, a projected grade if the fixes are made, findings tied to specific passages, and, for group projects, a per-person task list.

bryankwandou/rangka ↗

Skeletons first, new writing, open skills for Claude and other AI models.

BryceEWatson/claude-global-skills ↗

A curated collection of Claude Code skills: a multi-agent code-review loop, exhaustive local chat-history search, an evidence-grounded session end/resume pair, Gemini image generation, and rigorous transcript retrospectives. They run machine-wide with nothing but python and node. There's no per-project install: drop a skill into ~/.claude/skills/ and invoke it as a slash command in any session.

BryceEWatson/honestweek ↗

See where your Claude Code and Codex sessions went wrong, open the exact steps behind each problem, and check every count yourself. The page runs on your machine with fixed rules and sends nothing to an AI unless you turn that on.

brycewang-stanford/AER-Skills ↗

Agent skills that help you publish in the AER faster — identification-first empirics, AEA-compliant replication, Keith-Head intros, R&R rebuttals for

brycewang-stanford/lit-review-agent-tools ↗

Curated tools that help AI agents handle the whole loop of a literature review: search, screen, extract, read, synthesize, verify citations, and write.

brycewang-stanford/many-ppt-skills ↗

Every AI slide-deck skill worth knowing, on one page — both the HTML and native-PPTX routes, compared on what actually decides the choice rather than

bsmi021/google-notebook-plugin ↗

A Claude Code plugin that teaches Claude how to operate Google NotebookLM through the nlm command-line interface. It ships the notebooklm-cli skill: complete command and option coverage for nlm 0.8.9, profile-aware authentication, machine-readable output, bounded polling for asynchronous jobs, verified IDs, and explicit approval gates for every consequential write.

bsromero/graph_pec ↗

A Claude Skill for building native, editable Excel charts that follow a fixed house style — line and bar charts with specific colors, fonts, axes, gridlines, and data-label rules.

btmoriarty/algol ↗

A project-controlled policy, routing, and governance layer that sits above code-review engines rather than being one. Algol reviews nothing itself. It reads the project's versioned review standards, decides which engine handles a given change, reconciles every engine's findings into one record, never upgrading a heuristic to verified without notice, and preserves each human decision with the conditions that would reopen it. Category: ReviewOps for Claude Code.

btmoriarty/kochab ↗

*A personalized job search assistant.*

btmoriarty/pherkad ↗

A Claude skill that helps you review whether a draft still sounds like you.

bufferBrew/craftsman ↗

craftsman makes engineering discipline the default in Claude Code: the smallest correct change, no fix without a root cause, and an honest report of what was actually verified. It bundles fifteen agents, eight skills, seven slash commands, and a cross-platform hook system — installable in two commands.

build-dashboard ↗

Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a…

build-tam ↗

Build a Total Addressable Market list: size the audience, source companies from ICP filters, then find contacts at those companies at scale.

build-zoom-bot ↗

Build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining…

build-zoom-contact-center-app ↗

Reference skill for Zoom Contact Center.

build-zoom-video-sdk-app ↗

Reference skill for Zoom Video SDK.

building-tests ↗

Builds and runs an app's committed tests, written from the user's expectations rather than per platform — segments (one actor's intent on one surface, from a…

buildproven/agent-kit ↗

Archived

A Claude Code + Codex toolkit whose quality gate reads your diff, scores its risk, and scales its own review depth to match.

BuildThingsThatBuildthings/content-foundry ↗

A brand-locked, compliance-gated content engine for real estate — built as a Claude Code skill.

Bullseye-Francophone/bfr-claude-plugins ↗

Claude Code plugin marketplace by Bullseye Francophone (BFR) for DCS World mission makers

buluslan/amazon-listing-doctor ↗

AmazonListing + Rating Skill Amazon listening heart-check & scring (CDQ/A9/COSMO/Alexa)

buluslan/bulus-amazon-skill ↗

13 hints running from zero to one to the whole Amazon operating process (market/competing/Listing/advertising/reverse), data-based neutrality

buluslan/seedance-video-script ↗

Seedance 2.5 Generate a video skill for Agent transfer commercial intent + material to direct video scripts + assets into ready-to-use Seedance 2.5 store files f

buminduyasith/la-peace ↗

A single-file markdown design-doc reviewer. It renders Mermaid diagrams, lets you pin a comment to an exact sentence, a whole table, a code block, a diagram or a single node inside one, then exports every note as structured feedback an AI agent can act on without you explaining where anything is.

bunderlog/claude-plugins ↗

Claude Code plugin marketplace with baloo: skills, an agent that verifies changes against the project's decisions, guidelines, checks, an output style

bunhine0452/Ocul-PM ↗

Build and revise software, using the coding workflow described by the publisher.

bunlongheng/repo-audit ↗

Reverse-engineer any repo through 10 audit lenses into one clean HTML report.

burakCokyildirim/clawde-plugin ↗

The Claude Code hook that reports session status to Clawde

BurakErdemci/codex-delegate ↗

Delegate implementation work to a Codex worker while Claude stays the architect and reviewer.

burythehammer/claude-code-plugins ↗

A Claude Code plugin marketplace with skills for Terraform provider development, project wiki maintenance, CLAUDE.md housekeeping, and copy-editing.

Busabase ↗

Local-first database and workspace for AI agents that keeps structured data, durable knowledge, documents, files, skills, and apps in one searchable place. Agents connect through MCP, OpenAPI, CLI, or coding-agent skills, and material writes can remain reviewable ChangeRequests before becoming canonical.

bushrabeg/turkce-humanizer ↗

Claude Skill that cleans artificial intelligence signatures from Turkish texts. The production of AI converts Turkish to natural, human-voiced Turkish.

Business Strategy ↗

Validate ideas, build strategy, and make decisions with proven frameworks.

BUTFL/claude-skills ↗

Claude Code / Codex Skills (12): installation with one key, bilingual Chinese-British documentation, auto-validation before upload

bwfnx/agent-skills ↗

Drop-in skills and plugins that make Claude do one job well, the same way every time.

bx33661/oh-my-vul ↗

Evidence-first vulnerability research for Pi, Codex, and Claude Code.

by-carlos/claude-plugins ↗

Carlos Eng's Claude Code plugin marketplace (carlos-plugins).

by-carlos/daikenja ↗

Not an assistant -- a sage you consult. It knows your work, the work around you, and where to go next.

by-carlos/plan-staged-rollout ↗

Run big projects as many small sessions — not one huge one.

byAbas/design-system ↗

Set up, audit, fix and gate a web project's design system, so AI coding agents stay on it: W3C Design Tokens (DTCG) as the one source of values, a DESIGN.md that holds the rules and no values, and hooks, a pre-commit hook and CI checks that stop an agent the moment it writes a value outside the tokens.

bybit-exchange/svg-diagram ↗

Agent skill that draws architecture, flowchart, sequence, data-flow and lifecycle diagrams as hand-placed SVG, to one linted house style.

byensitmagnus/agent-mission-control ↗

Portable agent orchestration skill for Claude Code, Codex, Cursor, Grok and Kimi: route coding tasks, scope subagents, resume work and report checks a

byensitmagnus/sitesmith ↗

A browser release loop for coding agents that build websites.

bygama/skills ↗

Personal Agent Skills library for Claude Code — methodology skills usable from any repo, installed globally as junction links by the workstation repo's installer.

byjunyoung/claude-product-skills ↗

Most Claude Code plugins are aimed at the codebase. These two are aimed at the work beside it — the Figma file you draw in, and the spec you write next to it. One repository, installed separately.

byte271/mirrorframe ↗

Capture a live webpage's design system, motion, and interaction state machines, then reconstruct it as verified React — with per-node pixel verificati

ByteDance DeerFlow ↗

ByteDance DeerFlow is listed as a framework. Its catalogue topics include information research and software engineering.

ByteDance UI-TARS Desktop ↗

ByteDance UI-TARS Desktop is listed as a project. Its catalogue topics include browser workflows and agent development.

byterover ↗

Archived

You MUST use this for gathering contexts before any work. This is a Knowledge management for AI agents. Use brv to store and retrieve project patterns, dec...

ByteRover ↗

Archived

You MUST use this for gathering contexts before any work. This is a Knowledge management for AI agents.

bytesbrains/cruise-claude-plugin ↗

Put a Cruise key in your environment — a shell profile or a secret manager, not a settings file — and restart Claude Code

BytesFromToby/plumbline ↗

*To build a house well you follow the plans, double-check the work, and keep everything plumb. The plumb line is the builder's reference of truth — here, your spec is that line.*

BYZANTINE26/claude-log ↗

Append-only, token-efficient session logging plugin for Claude Code.

bzsasson/pre-launch-audit-skill ↗

A skill for Claude Code that checks a website before it goes live. It runs 5 sub-audits (technical SEO, AI accessibility, security, performance, and on-page SEO), then tells you what to fix before launch, in priority order.

c-c0rtex/web-qa ↗

Autonomous web-app QA skill for Claude Code: Playwright E2E, visual regression, axe-core accessibility — with test scenarios auto-generated from a git diff or a plain-text task, specs grounded in a real crawled map of your app, and a self-healing loop for failing tests.