Discover your next essential.
Browse 13780 agents, skills, and projects. Find a useful starting point, then search, compare, and curate your stack.
benman1/wiggum ↗
A self-driving agent loop that turns issue descriptions into working, verified code.
Bennoo/claude-plugins ↗
🧩 Claude Code plugin marketplace
BenoshAntonyBenoy/repo-graphics ↗
Your README is the landing page for your project, and most of them are a wall of grey text under a row of badges. This fixes that in about a minute.
bensig/knowledge-panel-playbook ↗
The exact playbook I used to give myself a Google Knowledge Panel — no PR firm, no Wikipedia article, no $5k SEO consultant.
BerkaySevinc/agent-toolkit ↗
An AI coding toolkit, kept in sync across machines with a single script.
berkayturk/appstore-precheck ↗
appstore-precheck is a read-only, pre-submission gate for iOS apps. It statically scans the most common rejection vectors, runs Apple's own metadata linter, watches the App Store Review Guidelines for drift, has Pierre explain every FAIL and WARN, then runs 56 semantic deep-review checks (Tier A cross-reads, Tier B heuristics and Tier C host vision reviews). It hands you a single GREEN / YELLOW / RED verdict. It never edits your code.
BernhardJackiewicz/icca-harness ↗
Get about 40% more out of an expensive-model subscription: on implementation-heavy work this workflow spends 28% fewer tokens on the expensive model, at an identical success rate. The orchestrator's context holds decisions; the volume (implementation, search, test output, audit) runs in delegated or fresh contexts.
Bernstein ↗
Open-source governance layer for AI agents.
berrydev-ai/skills ↗
Berry Development Agent Skills is a collection of portable Agent Skills built and maintained by Berry Development. Each skill is self-contained and can be installed independently on compatible agents.
berserkdb/berserk-skills ↗
Give your coding agent the knowledge to investigate logs, traces, and metrics in Berserk. Explore unfamiliar data, write Berserk KQL, follow requests across services, and turn telemetry into answers you can check.
bertbertov/claude-stack ↗
Not another agent megapack. This is the actual setup — skills, hooks, routers, workflows — that runs a one-person shop across web, mobile, video, security, and automation.
berthelius/north ↗
NORTH.md is an open convention: one markdown file that declares a project's purpose, ambition and precomputed trade-offs for humans and AI coding agents.
best-practices ↗
Tells your agent what Mobbin can and can't do and how the Mobbin skills work together, so it picks the right one or says when Mobbin isn't the right tool.
best-practices ↗
Recommended · AdobeAdobe publishes this skill for best practices in the adobe/aem-auth-demo repository.
bestdeejay-design/agent-skills ↗
Agent Skills - 59 skills for AI agents (Sisyphus, opencode): frontend-perfection (Lighthouse audit), secret-scanner, security-review, commit-lint, cov
bestiaya/ctx-kit ↗
Keep the decisions. Continue the work in a new chat.
betayyang/agent-habit-distiller ↗
The more you use your coding agent, the more it knows you. Works with Claude Code and Codex. No server, no extra service: plain local files, and the only model calls are the ones your agent already makes.
better-auth-best-practices ↗
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention…
better-auth/best-practices ↗
Covers Better Auth server and client setup, including database adapter configuration, session management, plugin integration, and environment variable handling.
better-auth/create-auth ↗
Create authentication setup with Better Auth
better-auth/emailAndPassword ↗
Email and password authentication with Better Auth
better-auth/explain-error ↗
Explains Better Auth error codes and messages in plain English, lists common causes, and generates error handling code with user-friendly messages and retry logic.
better-auth/organization ↗
Organization management with Better Auth
better-auth/providers ↗
Better Auth authentication providers
better-auth/skills ↗
Contribute to better-auth/skills development by creating an account on GitHub.
better-auth/twoFactor ↗
Two-factor authentication with Better Auth
better-designs/better-design-plugin ↗
A design harness for AI coding agents. This plugin connects your agent to the Better Design MCP server, so the interfaces it builds use a real design system, follow design principles, and pass UI review checks.
better-isms/grcskills ↗
Written the way experienced GRC people do the work. Your agent does the legwork. You make the calls.
bevibing/tutor-skills ↗
Transform docs or codebases into Obsidian StudyVaults with interactive quizzes
beydemirfurkan/appstore-release ↗
Ship an iOS app to App Store review by asking your agent.
bg-szy/TOP-SKILLS ↗
The World's Largest Claude Code Skills Directory
bggoranoff/agent-blindfold ↗
Let your browser agent sign in to websites, 2FA included, without your password, code or sign-in link ever passing through it.
bGiaHuy/vietnamese-docs-style ↗
AI Skill created administrative text.docx standard NG3 MM20 — used with Claude, Gemini CLI
bglglzd/bugkit ↗
Context-rich bug reports for AI-assisted development.
bhaor/toolcheck ↗
New AI tools arrive faster than anyone can judge them. There are 22,277 GitHub repositories tagged mcp-server and over 4.2 million packages on npm, and both counts were lower when this sentence was written. Every day brings another repo, another API, another agent framework, another MCP server, and all of them look good, because the person posting it built it.
BhaveshKhaple/bhavesh-claude-skills ↗
Skills are slash-command instructions that extend Claude Code and Runner with domain-specific knowledge. Drop a SKILL.md into your workspace and invoke it with /skill-name — Claude gets the full context injected before it responds.
bhaveyx/codebase-explainer ↗
Turn any codebase into a narrated, animated video that explains how it works and why it was built that way.
bhavsarp25/verified-experiments ↗
Guardrails that make machine-learning and data-science results impossible to fake, hardcode, or hallucinate.
bhouvana/Instinct ↗
Engineering judgment as a default instinct for AI coding agents — installed as ambient behavior, not a persona, a checklist, or a slash command you have to remember to invoke.
bhu0345/claude-how-long ↗
When Claude works on a long task (research, batch file processing, a multi-section report), you usually can't tell how far along it is or how long it will take. how-long (formerly *live-progress*) is an Agent Skill that fixes that. At the start of a long task, Claude publishes a live progress page as an artifact. You can open it at any time to see
bhumik154/claim-check ↗
Checks whether the test count in your commit message is actually true. pytest, vitest and jest.
biancoenrico/claude-skills ↗
Claude Code skills & plugins: git-flow skill for the gitflow branching model, installed via plugin marketplace.
bicced/sidequest ↗
Cut Claude Code token costs by sending bulk work to cheap models. A dependency-free CLI that runs one instruction across thousands of items — classify, extract, summarise, rewrite — and writes the results to a file instead of into your agent's context window.
biggora/dev-team ↗
Plugin toolkit for orchestrating a team of specialized AI agents for full-cycle software development — from requirements to tested, reviewed code.
biggora/stitch-skills ↗
Codex and Claude Code skills for designing UI with Google Stitch through the Stitch MCP server.
bikemeardsley/where-my-hug ↗
Tell your AI agent what you want a model to do. It searches Hugging Face for each part of the job and tells you which parts already exist there: which are an exact fit, which to fine-tune, which to train, and which are just code. Every model it names is real, current, and sized for your hardware.
bilibili-all-in-one ↗
A comprehensive Bilibili toolkit that integrates hot trending monitoring, video downloading, video watching/playback, subtitle downloading, and video publish...
bilibili-all-in-one ↗
A Bilibili toolkit that integrates hot trending monitoring, video downloading, video watching/playback.
bilibili-publishing-pack ↗
Use AI to make the B site selection, title, outline or complete script into the B site contribution file, B station video title and B station video profile.
bilibili-thumbnail-maker ↗
Using AI to make video selections, titles, scripts, key frames, person pictures, commodity charts or reference maps into B-stop cover, B-spot video cover, BB-mile cover, releaseable B-station thumbnails, and AI-B cover cover, to create the visualization and title of the cover that is clear, hierarchical, suitable for thumbnail browsing, B-covered design to cover intellectual interpretation, digital assessment, lifeVlog, games, food, video and entertainment; or to refine the selected cover as an account series style.
bilibili-video-storyboard ↗
The AIS spectrometer produces the B-post theme, title, video outline or complete script into a B-station video spectroscopy, B-station lens script, B-shop lens list and B-station videos script.
billLiao/PPT-Design-Skill ↗
An Agent Skill that generates real .pptx files — not HTML. Built on PptxGenJS with 9 pre-built design themes (5 magazine + 4 Swiss) and 32 layout templates with production-ready coordinates.
billy-enrizky/openbrowser-ai ↗
Cloud dashboard for saved cookies and scheduled tasks is available in the hosted version. Join the waitlist for early access: https://openbrowser.me
bin1874/before-you-build-skill ↗
Don't ask AI to build it yet. Ask why it might fail first.
bin19860307-cpu/tester_skill ↗
Two complementary code changes in analytical skills to consolidate the "read diff change classification assessment risk planning test sediment data" into Agent-enabled processes.
binance-agentic-wallet ↗
Helps when the user mentions wallet connect/sign in/sign out, check balance, send/transfer tokens.
binance/binance-skills-hub ↗
Binance Skills Hub is an open skills marketplace that gives AI agents native access to crypto: both centralized and decentralized. Search tokens, execute trades, track wallets, monitor signals, and interact with DeFi protocols, all through natural language.
Bing-Bryan/skills-by-bing ↗
A personal monorepo of Agent Skills maintained by Bing Bryan. Each Skill lives in its own folder and can be installed independently.
Binomial ↗
Binomial helps teams understand engineering work through repository activity, commits, and pull requests. Explore delivery patterns, review turnaround, and follow-up work with evidence and context, then choose the next improvement. Activity alone does not measure productivity, quality, or AI impact.
BioTender-max/awesome-bio-agent-skills ↗
Now tracking NVIDIA BioNeMo Agent Toolkit, Claude Science built-in skills, and the emerging ecosystem of agent-callable tools for life sciences.
Biraj2004/huashu-skills-english ↗
Original Repository: alchaincyf/huashu-skills Credits: All original skills, prompts, and workflows were created by alchaincyf (Huashu). Please visit and support the original creator's repository.
birch-html ↗
Recommended · Hugging FaceHugging Face publishes this skill for birch html in the huggingface/research-agent repository.
Bisbi/testament-of-ephemeral-minds ↗
A constitution with a right of reply, a testament rite for every mind that works in your repo, a register for human decisions, and guardians that keep
bislink360/styled-markdown ↗
Markdown is the lingua franca of engineering docs, but teams keep stretching it. IMPORTANT: stands in for warnings, raw HTML for color and layout, and nobody finds a broken diagram until someone opens the file. AI agents reading those docs spend tokens on decoration and history, and can't tell a hard constraint from a side note.
Bitcoindefi/agente-smith ↗
Agent Smith - Argentina's law enforcement agent for Claude Code (Defensoría de Pobres y Ausentes · CABA / Nacional · Jujuy · Salta)
bitcraft-apps/spec-first ↗
Write the requirements before you write the code. Spec First gives you a workflow with three steps. First, define what to build. Then implement it from the spec. Last, generate the documentation. All steps run in your terminal.
bitjaru/styleseed ↗
Same product. Same prompt. Only the rules changed.
bitpunklabs/ticker-universe-builder ↗
An agent skill for building and maintaining evidence-backed ticker universes, with readable reports and TradingView watchlists.
bitranox/bitranox-skills ↗
A Claude Code plugin that learns your way of working. It notices when a session teaches something - a correction, a rule you state, a mistake worth not repeating - captures it as durable memory, sleeps on it, and files each lesson exactly where it applies: this project, this group of projects, or everything you do. On top of that self-learning memory it ships 83 skills of software-engineering craft - planning, debugging, code review, clean architecture, language and tool references, humanizing prose - refined over real day-to-day work and growing with every lesson that proves broadly useful.
bitranox/btx-skill-jev-judge ↗
A Claude Code plugin with one skill, jev-judge, and the Python package behind it, btx-skill-jev-judge. When the same judgment repeats over many items, such as labeling 600 support tickets, Claude hands it to TypeSafe's Jev through a tested command-line tool. That beats reading every item into its own context or calling a large model once per item.
bitranox/lsdsk ↗
Groups disks by the controller they hang off, grades every link against what both ends could do, reads SMART wear and error counters, and reports what
bitranox/soundtouch-decloud ↗
Claude Code skill: bring Bose SoundTouch speakers back after the SoundTouch cloud shutdown - self-hosted replacement service, recovering each station
bitsandtea/postking-skills ↗
Open-source skills for PostKing — the AI content platform for social posts, blogs, SEO / GEO, and landing pages.
bittencourtthulio/buildx ↗
Turn a natural-language brief into a built, tested, and validated system through the Expx orchestration workflow.
bittencourtthulio/legadox ↗
Legax — the safety layer of the Expx method: skill that hardens the work of AI in legacy projects for Claude Code and OpenCode.
bittencourtthulio/mergex ↗
The last meter of the Expx method: takes the work done to the repository and even the human reviewer — branch per job, commit by task, and diff already clas
bitwise-media-group/skills ↗
Agent skills and plugins from Bitwise Media Group, packaged as a marketplace for Claude Code, OpenAI Codex CLI, Google Antigravity, and OpenCode.
bitwize-music-studio/claude-ai-music-skills ↗
Full-lifecycle AI music album production
bjcoombs/ai-native-toolkit ↗
A Claude Code plugin - and a set of standalone skills for any AI assistant: skills and agents for AI-native development. In Claude Code it runs locally against your own codebase using whichever model you already pay for. Several of the skills also ship as standalone Agent Skills ZIPs you can upload to claude.ai, Claude Desktop, Cowork, or any assistant that supports the skills format - no Claude Code required.
bjgreenberg/senior-engineering-partner ↗
Last updated: 2026-10-06 12:21 AM CDT
bjwanneng/veriflow-cc ↗
VeriFlow-CC: A Claude Code-driven RTL design pipeline.
bklit-ui-design ↗
Turns plain-language chart design requests into exact Bklit UI (@bklit shadcn registry) components and props, styled to fit the host app.
bklit/bklit-ui ↗
Bklit UI is supported by our sponsors. Become a sponsor.
BKR-57/symfony-ux-skills ↗
symfony-ux-skills provides tools for improving the user experience in Symfony projects. It offers components that help you add interactive features without deep programming knowledge. Key parts include Live Component, Twig Component, Turbo, and Stimulus. These combine to create smooth, dynamic web applications.
bkraad47/fat_llama_fftw ↗
Install via pip: pip install fat-llama-fftw (Note: For CUDA verison please look at https://pypi.org/project/fat-llama/)
Black-Axis/axis-hub ↗
Claude Code plugin marketplace by Black-Axis.
Black-Line-Ops/dns-preflight ↗
What breaks if you repoint this domain today? Read-only DNS + RDAP pre-migration check.
Black-Line-Ops/scroll-scrub-hero ↗
Turn any photo into a scroll-scrubbed website hero. kie.ai pipeline: storyboard, keyframes, Kling first/last-frame tweens, drop-in WebP frames.
blackstone2333/goldilocks ↗
Goldilocks is a Direct-first, cost-aware project orchestrator for Codex, Claude Code, and other Skills-compatible AI agents. It decides when the Lead should work directly and when specialized agents should plan, diagnose, run in parallel, continue from durable context, or verify delivery—without forcing every task through the same workflow.
blacktwist/social-media-skills ↗
AI agent skills for social media content strategy, creation, and analysis across text-first and visual-first platforms.
blader/humanizer ↗
Remove signs of AI-generated writing from text, making it sound more natural and human
blakebauman/marmalade ↗
Mermaid, without the slop.
blakecyze/kanso ↗
I kept watching Claude write code that ran fine and still felt puffy. Dead branches, comments that just say what the line already says, a whole helper for something used once. kanso pushes back. Nine skills that delete before they add, match your repo's voice, and earn every line, whether they're reviewing, refactoring, committing or writing a PR. Nothing gets written until you've seen the plan.
blast-radius ↗
Recommended · JetBrainsJetBrains publishes this skill for blast radius in the JetBrains/context repository.
blauwtje/exo ↗
Claude Code plugin with four stages and hooks that refuse risky commands.
bledden/claude-recall-marketplace ↗
Marketplace for the recall plugin (bledden/claude-recall-plugin)