Discover your next essential.
Browse 13780 agents, skills, and projects. Find a useful starting point, then search, compare, and curate your stack.
blindlove200/sub-agents-skills ↗
🤖 Define and execute task-specific AI agents in markdown across various platforms with the Sub-Agents Skills for integration and portability
BlinkingSun/github-web-skill ↗
Put your GitHub stats on your own website, and let your coding agent keep them current on a schedule. Contribution heatmap, streaks and activity stats, a public/private repository split bar, and your pinned repo cards with live star and fork counts.
blisspixel/primr ↗
Company name + website → evidence-grounded, long-form strategic reports. Built for agent hosts and the CLI: structured research, strategic insight, confidence labels, and durable Word and Markdown artifacts, not a free-form chat essay.
blitzsicht/falzmarke ↗
Checked to the millimetre, not only claimed: DIN-5008 letters from Markdown, set as PDF/A. Skill for AI agents and CLI.
blkdynamite/Gio-prompt-optimizer ↗
Your vibe-coding sidekick. Lean, clean, and easy on the planet.
block-collection-and-party ↗
Recommended · AdobeAdobe publishes this skill for block collection and party in the adobe/skills repository.
block-inventory ↗
Recommended · AdobeAdobe publishes this skill for block inventory in the adobe/helix-website repository.
block-inventory ↗
Recommended · AdobeAdobe publishes this skill for block inventory in the adobe/skills repository.
BlockAGI ↗
BlockAGI conducts iterative, domain-specific research, and outputs detailed narrative reports to showcase its findings
blockdancez/PreviewShip ↗
Version delivery records: 2.0.1 — background content review and automatic remediation.
blocking-io-guard ↗
Recommended · ByteDanceByteDance publishes this skill for blocking io guard in the bytedance/deer-flow repository.
blog-writing-guide ↗
Recommended · SentrySentry publishes this skill for blog writing guide in the getsentry/skills repository.
blogwatcher ↗
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
blonderoofrat/pet-freedom ↗
Map a pet species' legal status across jurisdictions worldwide — and publish it as an honest, source‑cited resource. A Claude Code skill.
bloom ↗
Recommended · SnowflakeSnowflake publishes this skill for bloom in the Snowflake-Labs/cocoplus repository.
bloom-crystallize ↗
Recommended · SnowflakeSnowflake publishes this skill for bloom crystallize in the Snowflake-Labs/cocoplus repository.
bloom-skip ↗
Recommended · SnowflakeSnowflake publishes this skill for bloom skip in the Snowflake-Labs/cocoplus repository.
Blucli ↗
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Blucli ↗
BluOS CLI (blu) for discovery, playback, grouping, and volume.
blueaisecurity/claude-skills ↗
Free Claude skills: yt-notes turns long YouTube videos into short study PDFs, and skill-audit checks a skill for security risks before you install it.
blueclover22/mw_agent_kit ↗
Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.
BlueprintOS/analysis-to-delivery ↗
Generic demand to develop design workflows — 26 stand-alone skills, cross-industry (medicine/SaaS/mobile), 3 full examples.
bluerock-io/claude-plugins ↗
The BlueRock plugin marketplace for Claude Code. One plugin, bluerock: the run-as-is core for your agentic project.
blur3hq/codebase-vault-docs ↗
The skill is a SKILL.md with the workflow, two reference files with the writing rules, and three small Python scripts that verify the output. They follow the Agent Skills layout, so any agent that reads skill folders loads them as-is. Any other LLM works too: paste both files into the conversation and ask.
blyatiful1/ultraweb ↗
A Claude Code plugin that builds production Next.js 16 + Tailwind CSS v4 websites through a guided design session. You describe the site in one sentence, answer a few scoping questions, pick one of three mockups, and the pipeline builds, tests, and ships the rest: design system, components, copy, motion, backend, SEO, and seven quality gates verified with a real browser.
bmad ↗
Answers BMad questions and recommends the next skill from what is installed. Use when the user asks bmad for help, what to do next or where to start; to set…
bmad-advanced-elicitation ↗
Push the LLM to reconsider, refine, and improve its recent output.
bmad-agent-analyst ↗
Business analyst for market research, competitive analysis, and requirements. Use when the user asks to talk to Mary or requests the business analyst
bmad-agent-architect ↗
System architect and technical design leader.
bmad-agent-dev ↗
Senior software engineer who implements stories and code changes.
bmad-agent-pm ↗
Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager
bmad-agent-po ↗
Sofia, the Product Owner: turns any input.
bmad-agent-ux-designer ↗
UX designer and UI specialist.
bmad-architecture ↗
Work out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document. Creates, updates, or…
bmad-brainstorming ↗
Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'
bmad-build ↗
Turns implementation work into working code, reviewed and verified. Use when the user delegates a feature, story, bug fix, or meaningful change; a bare story…
bmad-build-auto ↗
One iteration of an unattended development loop.
bmad-code-org/BMAD-METHOD ↗
Agile Ai Driven Development — turn an idea or change request into working software without giving up the thinking.
bmad-code-review ↗
Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review…
bmad-deep-recon ↗
Decision-grade research on a topic or this repository. Use when the user says "deep recon", "research this", "draft a research prompt", "process this research…
bmad-eval ↗
Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model.
bmad-forge-idea ↗
Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with…
bmad-party-mode ↗
Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode,…
bmad-prd ↗
Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD
bmad-prfaq ↗
Test a product concept with Amazon's Working Backwards method: write the press release for the finished product first, then answer hard customer and…
bmad-product-brief ↗
Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief
bmad-project-context ↗
Set up, adopt, refresh, or audit a repository's agent instructions (the AGENTS.md block) so AI agents work well in that repo.
bmad-qa-generate-e2e-tests ↗
Add end-to-end and API tests for features that already work, following the project's existing test harness. Use when the user asks for e2e tests, API tests, or…
bmad-review ↗
Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and…
bmad-toolsmith ↗
Smithy the Toolsmith builds and maintains BMad skills, agents and modules. Use when the user asks for Smithy or says "build a skill", "make an agent",…
bmad-ux ↗
Capture the user's UX vision in two documents: DESIGN.md for how the product looks and EXPERIENCE.md for how it behaves. Use when the user says "lets create UX…
bmad-walkthrough ↗
Guide a human review of a commit, PR, file, or directory. Use when invoked by name
bmeunier1974/beautify-md ↗
A Claude Code skill that measures, audits, rewrites and authors markdown — especially READMEs — so humans enjoy reading it. Every rule traces to readability research, and a bundled bash + awk script keeps the numbers honest.
bmod-method ↗
Required bmod metadata. Never invoke this skill.
bmod-toolsmith ↗
Required bmod metadata. Never invoke this skill.
bmurphy201/revenue-messaging-framework ↗
An open methodology and Claude Code skill for auditing and rewriting B2B website copy: messaging, positioning, and value proposition.
board-ops ↗
Recommended · Model Context ProtocolModel Context Protocol publishes this skill for board ops in the modelcontextprotocol/inspector repository.
board-ops ↗
Recommended · Model Context ProtocolModel Context Protocol publishes this skill for board ops in the modelcontextprotocol/servers repository.
bobadilla-tech/requiems-api-skills ↗
Installable AI skills that give your coding agent direct knowledge of Requiems API, authentication, fraud detection, payments intelligence, and global data, all through one unified API.
bobbyhyam/agentics ↗
Modular agentics for Claude Code — skills, subagents, hooks, and CLAUDE.md snippets, each installable individually via the plugin marketplace
bobuel/bloom-taxonomy-quiz-builder-skill ↗
A source-grounded assessment workflow that helps teachers build and review one question at each of Bloom’s six cognitive levels.
boburxd/broom-design ↗
The design skill for AI coding agents. Broom Design collects the most popular design skills into one Agent Skill, together with a working studio's own taste: one set of rules, a checker, a design system generator and six commands. It works in Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, OpenCode and any agent that reads skills, and it removes AI slop from web apps, mobile apps and websites: the generic, machine-made look of default UI. It respects the product's own design system. What your system does on purpose stays, and slop is whatever drifts from it toward generic defaults.
bogaja/moatbreak ↗
Take an existing product apart and plan a better one. Moatbreak is an agent skill for competitor teardowns of apps, SaaS products, websites and online shops: it finds the reference products when you only have a niche, maps what the original does and how it is found, ranks what its customers complain about and why they leave, prices the rebuild, writes the build brief, measures how close the rebuild is, gives sales a sourced battle card, gives the new product an identity that keeps a safe distance, writes its launch pages and store texts, and hands the client one offline HTML report. Built for agencies and founders working in the EU and DACH, with English and German throughout.
bogdankrupin/ask-seranking-api ↗
A Claude Agent Skill that answers questions about the SE Ranking API (Data API and Project API) and the SE Ranking MCP server, and grounds every answer in the official documentation with a direct, verbatim citation to the relevant section of seranking.com/api.html.
bogheorghiu/ex-cog-dev ↗
Mostly skills — with a few MCP servers and hooks — for Claude Cowork and Claude Code. Built for knowledge work — most of it needs no code at all — and honest about what each tool does and doesn't do.
bold-minds/bots ↗
Claude Code plugins by Bold Minds.
bolder ↗
Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.
bolongpa/repopedia ↗
Code is a graph — calls, dependencies, inheritance — but today's AI doc tools pretend it's text. repopedia recovers the structure first (AST → knowledge graph), then grows answers, wikis, and impact analysis from the graph. The graph says what's true (every claim cites file:line); the LLM makes it readable.
bolt-build ↗
Recommended · ByteDanceByteDance publishes this skill for bolt build in the bytedance/bolt repository.
bomsn/grokify ↗
Claude writes the draft. Grok writes the thing you actually send.
Bomx/distribb-skill ↗
SEO articles, keyword research, CMS publishing, high-DR backlink exchange
bootgs/skills ↗
Agent Skills for boot.gs – a NestJS/Spring Boot-style framework for Google Apps Script (decorators, dependency injection, routing, validation) — plus a set of skills for plain Google Apps Script development that don't require boot.gs at all.
bootstrap ↗
Recommended · ByteDanceByteDance publishes this skill for bootstrap in the bytedance/deer-flow repository.
boranesn/agentic-base ↗
The discipline layer for Claude Code — append-only log, deterministic security gates, sensitive spouses and human approval queue (plugin market)
Borda/AI-Rig ↗
Practical agent workflows for Python, ML, and open-source maintenance. AI-Rig turns recurring work—scoping a change, reproducing a bug, reviewing a pull request, running an experiment, or checking release readiness—into explicit workflows with specialist ownership, evidence gates, and reviewable artifacts.
bordumb/recurve ↗
Turn a spec or a README into promises a machine can check — then let an agent loop build until every promise is proven, without ever un-proving one.
borghei/AI-Skills-German-Law ↗
AI skills for German legal practice and EU compliance.
borghei/Claude-Skills ↗
No setup, any AI chat. Browse the skill library, click Try it now on any skill, and paste the prompt into Claude.ai, ChatGPT, or Gemini.
boriskuncer/complicheck-skill ↗
Deterministic sub-10ms cosmetic compliance API for AI agents. Resolves INCI/CAS to EU CosIng regulations via x402 micropayments (0.10 USDC).
Boriwatopal/agent-skill-line-character-studio ↗
A Claude skill that turns a logo or mascot into a full LINE character product line with OpenAI GPT Image: it designs the character in many action poses, then builds upload-ready LINE Creators Market packages for stickers, a complete theme and emoji, each as a validated ZIP with a preview.
borx3a/halka-arz-skills ↗
Exchange Istanbul skill package for Claude Code: ring supply analysis, market view, share scan and KAP/haber analysis
boshu2/agentops ↗
DevOps discipline for AI coding agents.
bosmdavid-gif/dropthehassle-skill ↗
An open Agent Skill that teaches your coding agent to publish a built site or web app with DropTheHassle: a free HTTPS yourname.dropthehassle.app link with no account, card or DNS work, then a real domain when you want one.
bostonaholic/grokbot-skills ↗
When to use this skill, in one or two sentences.
botpress ↗
Visual bot builder and runtime; multi-channel, open-source alternative to commercial bot platforms.
boundlessend/yougile-tracking ↗
Skill for working with YouGile (REST API v2, 70 tools)
bountyoperator/bounty-operator ↗
Make your strongest case before you submit.
bouob/agent-harness ↗
Model-routed multi-agent sprints for Claude Code: a Planner decomposes your spec, Generators implement tasks in parallel (up to 16 concurrent agents inside a background dynamic workflow), and an Evaluator verifies against acceptance criteria — iterating up to 3 times until it passes.
bovinphang/frontend-craft ↗
Frontend-craft is a universal frontend plugin that brings the same opinionated engineering standards to all 15 AI coding assistants.
boweiww/behavior-first-testing ↗
A Claude Code skill (and plugin) for testing business applications. Tests prove business rules, not the code that happens to implement them, and a linter keeps it that way.
bowen31337/comprehension-ladder ↗
A Claude Code skill that explains anything so a human can understand it: as Simplified Technical English prose, a blueprint diagram, an interactive HTML page, or a narrated 3Blue1Brown-style video.
bowenlabs/claude-plugins ↗
A Claude Code plugin marketplace for the Louise / Astroid stack.
bp-high/itr-filing-claude-skill ↗
A Claude Code skill for filing an Indian ITR-2 for AY 2026-27 (FY 2025-26).
bqnhat/claude-local-plugins ↗
Function-hooks plugins ("mods") for Claude Code, built mainly for the Desktop Code tab. The repository is a plugin marketplace named nhat-local.
brackendev/clojurescript-skills ↗
ClojureScript development skills packaged as an APM plugin. One install deploys the full set to every runtime in APM's default target set: Claude Code, Codex, OpenCode, Cursor, Copilot, Gemini, Windsurf, Kiro, and Grok Build. Antigravity is supported by naming it explicitly with --target antigravity.
brackendev/jsp-skills ↗
ArchivedSkills follow the Agent Skills open standard. Two appear as slash commands (/upstream-sync, /deploy-check); the rest activate automatically from conversation context. Argument grammar, scope vocabulary, and the --report convention are documented in CONVENTIONS.md.