Discover your next essential.

Browse 11291 agents, skills, and projects. Find a useful starting point, then search, compare, and curate your stack.

aaddrick/scripting-blender-scenes ↗

Your coding agent can't see Blender's viewport. It works through bpy scripts and headless renders, so it calls a fix done because the script ran, the spec says so, or the rest pose looks right. Then the character's foot sinks through the floor on frame 140.

aahl/skills ↗

AAHL's Agent Skills.

aahlijia/dekko ↗

Ever watched your coding agent grep blind through a repo, open three files it didn't need, and burn fifteen thousand tokens just to answer "who calls this function"? That's the problem dekko exists to fix.

aakashdhar/vibe-skill ↗

Built by Aakash Dhar at BetaCraft for production AI-assisted development workflows.

aantenore/mpsf ↗

Agents are fast. The problem is everything around the diff: a chat that scrolls away, an assumption nobody confirmed, a file outside the agreed scope, a "tests pass" that was never run. Code review sees the result, not the reasoning or the boundary.

aariz51/promo-video-skill ↗

Turn a reference promo video + your app's screenshots into an original launch film.

aaron-he-zhu/aaron-marketing-skills ↗

69 marketing skills across SEO/GEO, influencer, paid ads, and email on one shared contract, with 5 benchmark-driven auditor gates (CORE-EEAT, CITE, C³, ROAS, SEND) and keyless data connectors

aaron-he-zhu/seo-geo-claude-skills ↗

16 skills covering research → build → optimize → monitor, gated by CORE-EEAT (content quality) and CITE (domain authority). Entrypoint command: /aaron-marketing:seo-geo.

aaron4605/context-optimizer ↗

Reduce Claude token consumption by using local manifests to index and summarize project files for efficient context management.

aaronartistzhang-afk/DailyWork ↗

Author: Aaron Zhang (@aaronartistzhang-afk)

aaronjmars/agent-credit ↗

Give your AI agent a credit line: it borrows and repays on Aave V3 via credit delegation, within limits you set.

aarontzeng/dev-lead ↗

Cross-family delegation & adversarial review for CLI coding agents *Independence of training, not just of context.*

aarshsharma2803-stack/optimusprime ↗

The session state protocol for AI coding.

Aarvion-AI/stackwise-skills ↗

End-to-end development skills for Claude Code - frontend, backend, mobile, infra, and QA - one plugin install.

aashishvasu/dev-team-claude ↗

A Claude Code plugin for projects you need to come back to.

aashutosh396/mindpalace-skill ↗

A resource-first knowledge vault your AI agent can actually maintain.

aatmik-panse/clone-site-skill ↗

A Claude Code skill that rebuilds a target URL in real code, from measurements taken off the running page — computed styles, CSSOM rules and keyframes, document.fonts, getBoundingClientRect, getAnimations(), the network log.

Abdallah-Abdelazim/mobile-pr-review-skill ↗

An agent skill that reviews Android, iOS and Kotlin Multiplatform (KMP) pull requests. By default it saves every finding as a pending (draft) GitHub review, which nobody else sees until you submit it. Pass --live, or ask for it, to post immediately instead. It runs without stopping to ask questions.

abdazez01/own-it ↗

A Claude Code skill that turns your codebase into games.

abduelhamit/hungrai-skill ↗

Unofficial Claude Code port of the SNICKERS HUNGR.AI campaign: hand Claude a digital candy bar when its last answer was off, get a blunter second atte

Abdulaziz-almoshen/orbit ↗

You give it a goal. It sizes the work, dispatches a small team of subagents through hard quality gates, keeps a live board in your terminal, and refuses to call the work done until the gates have evidence.

abdulazizsapra/marie-kondo-skill ↗

An anti-clutter design skill for coding agents.

Abed-Zahed/claude-skills-kit ↗

A set of 8 Claude Code skills covering engineering, research, and decision-making workflows. Each skill is useful on its own. Seven of them are zero-config and portable, the eighth (/video-review) is included as a worked example of a more involved, personal-infrastructure-dependent skill, see its own note below before expecting it to run as-is.

abgne/line-dev ↗

AI agent skills for LINE platform development. Build bots, login flows, LIFF apps, MINI Apps, notification messages, and LINE stickers/emoji/themes with up-to-date API references.

abhaymettu/writing-from-dated-sources ↗

A Claude skill for one specific failure: it copies a stale document's present tense into new prose.

AbhiiGatty/cld-flare-maxxing ↗

Talk to Cloudflare from any project. This plugin gives Claude Code or Codex a read-first Cloudflare control center. It snapshots your account, flags misconfigurations, explains what changed, recommends useful Cloudflare products, and runs only the changes you approve.

abhimanyusingh-gh/Arkon ↗

Arkon publishes craft, a skill for Claude Code: engineering guidance for building, changing and reviewing production applications. It defines acceptance criteria, designs boundaries, implements complete slices, reviews behavior, verifies the real application and prepares a recoverable release, on any stack. Each rule is traced to review evidence or labelled as judgment. The skill was built for and is tested in Claude Code. The engineering principles do not depend on Claude Code, but they have not been tested anywhere else. The project-binding discovery script also runs on its own and works with any IDE.

abm9111/vigil ↗

Codebase quality and compliance audit skill for Claude Code.

Abner-Machado/agent-layer ↗

Ferramentas pequenas para a camada de agentes de IA: detecta skill envenenada e da validade temporal a base RAG.

abouchard11/midnight-seo-skills ↗

Claude Code skill suite for running SEO operations across a portfolio of local-service and niche sites: auditing, topical mapping, link acquisition, local pack strategy, analytics wiring, rapid indexing, and AI-search citation/answer work (GEO + AEO).

Aboudjem/aws-cost-audit-skill ↗

It is a skill for Claude Code: a Markdown instruction file, six reference documents it loads only when it needs them, and ten bash helper scripts. Claude picks it up when you ask about AWS spend.

Aboudjem/goalify ↗

Come back to proof it's done, not a promise that it is.

Aboudjem/humanizer-skill ↗

AI writing has a fingerprint. Sentences all run about the same length, the same safe words keep coming back, and filler like "in today's landscape" pads the gaps. Humanizer names 55 of those habits, finds the ones in your text, and rewrites it in a voice you pick. The CLI scores the text 0 to 100 from four measurable signals, not from a count of the 55.

Aboudjem/ui-ux-suite ↗

Most design review tells you to improve your contrast. This tells you that .hero-subtitle on line 14 of src/styles.css is #fbfbfb on #ffffff, which measures 1.03 to 1, and that #767676 would pass. Same shape as a linter error, applied to design.

AboutRSS/rsshub-route-authoring-skill ↗

Agent skill for authoring PR-ready RSSHub routes, distilled from 2000+ PR reviews

abs1294/fulin-claude-plugins ↗

Claude Code Toolset marktplace: webwright driven QA test frame + schedule schedule plugin

ABTdomain/domainkits-plugins ↗

DomainKits turns domain data into answers. It does the search, retrieval, and correlation across registration pipelines (new / expired / deleted / aged), nameserver indexes, keyword registration trends, WHOIS/DNS, backlink and market datasets. Claude does the analysis.

abtindaa/checklist-audit ↗

A security audit skill for vibe-coded projects. A Claude Code skill that checks your project against more than 200 built-in security items, focused on the issues that most often affect AI-assisted codebases. It checks the actual code, not general knowledge, and every covered item comes with a file:line citation.

abualnassr/interactive-workflow ↗

An agent skill for Claude Code, OpenAI Codex, Cursor, OpenCode, Hermes Agent, OpenClaw and other agents that read SKILL.md. It turns a process description into a self-contained, clickable HTML diagram: cards on a fixed grid, labelled orthogonal arrows, exception routes you can switch off, a context panel on the right, search, deep links, four colour themes (one dark), and a PNG for slides. One file, no dependencies, works offline, opens in any browser.

AbubakrChan/product-launch-motion ↗

Already installed it? Get the latest version with npx skills update.

abullard1/claude-bionify ↗

It only changes how text looks on screen. What gets saved to the transcript and what Claude reads stays the original, unbolded text, which you can reopen any time with the Ctrl+O transcript view.

Abwor9658/social-media-skills ↗

Choose the latest release for Windows, then download the file that matches your device.

abxn4r/archon-skills ↗

subgraph CouncilSub ["High-Stakes Multi-Discipline Dilemmas"] Seneca & Dijkstra & Saltzer & Aperture & Caples & Berners & Orwell --> Council["Archon Consensus Council"] Council --> Matrix["Consensus & Disagreements Matrix"] end

aby-studio-works/garelier ↗

Turn Claude Code (or Codex CLI) into an 11-role dev team with review gates, a merge pipeline, and machine-enforced command rails — all local, all git-native, and fully removable.

Ac-Hanxin/sixteen-personality-fun-test ↗

Based on OJTS 2.1, the 16th type personality test in Chinese: 48 Questions, local certainty scores, shared reports, or as Agent Skyll.

academic-pre-review-committee ↗

Draft and review academic writing, with attention to structure, clarity, and supporting evidence.

academic-research-hub ↗

Use this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly information. Triggers include: requests to "find papers on", "search rese…

accelerated-computing-cudf ↗

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

accessibility ↗

Audit and improve web accessibility following WCAG 2.2 guidelines.

accessibility-review ↗

Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design…

acchuang/zh-tw-humanizer ↗

Edit writing to reduce formulaic AI phrasing and make it read more naturally.

ace-step ↗

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the runcomfy CLI. ACE Step is StepFun-AI's open-weights music foundation model —…

AceDataCloud/fish-audio ↗

Generate speech and clone voices with Fish Audio

Acendas/shipyard ↗

You're copy-pasting requirements into chat windows. You're re-explaining context every session. You're manually checking if the AI actually built what you asked for. You're debugging code that passed the AI's own "tests." You're losing work when sessions crash. You're starting from scratch every Monday.

AceyAdapter/knap ↗

Claude Code workflows for shaping AI-built software — flintknapping for code.

AcKeskin/contexture ↗

The setup I use to work with AI. A rule corpus that loads itself before I write code, a review pass that checks against it after, safety hooks, and a memory store.

acoz-labs/quickstop ↗

A little convenience store for your agents: useful plugins and practical workflows you can make your own.

acquire-codebase-knowledge ↗

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document…

Actionbook ↗

Parallel Action CLI for AI agents. Run 50 actions across 20 sites at once.

activeloopai/hivemind ↗

Hivemind turns your traces into reusable skills across agents

acuity-scheduling ↗

Acuity Scheduling API integration with managed OAuth. Manage appointments, calendars, clients, and availability.

Acuminate-conventionality909/aibti ↗

Aibti analyzes your history with coding assistants like Claude Code, Cursor, and Codex. It determines which of the 16 personality types best matches your unique prompt style. Your data stays on your machine. This tool respects your privacy.

acus9345/haiku-delegate ↗

A Claude Code skill that hands the purely mechanical steps of a bigger task to Haiku subagents, runs them in parallel, and verifies their results. Design, debugging, naming, writing and judgment calls stay on the main model.

ad-account-diagnostic ↗

Diagnose the root cause of an underperforming paid ad account - why the ads stopped working, why CPA went up.

ad-attribution-gap ↗

Quantify and explain the discrepancy between ad platform reporting, an analytics tool, and the source of truth (CRM or order system), classifying every unit of…

ad-audience-targeting ↗

Turn a business's ICP and buying signals into a layered ad audience targeting plan - cold/broad prospecting, interest and in-market behavioural segments,…

ad-bidding-strategy ↗

Choose the bidding policy per platform and goal - manual vs automated, cost-goal vs value/return-goal, when to switch, and how to set and move the target -…

ad-budget-pacing ↗

Track daily and weekly spend against a single campaign or account budget and flag under-pacing or over-pacing before it hurts results.

ad-buyer-group-mapper ↗

Map the likely buying committee for an offer, deal size, and industry.

ad-campaign-consolidation ↗

Evaluate a fragmented paid-ads account and recommend which campaigns and ad sets to merge, which splits to preserve, and how to migrate without resetting…

ad-conversion-tracking ↗

Verify that conversion events are correctly configured, firing once, and deduplicated before a paid campaign launches.

ad-copy-variants ↗

Turn one core value proposition into genuinely distinct ad copy variants - headline, primary text, description.

ad-creative-brief ↗

Turn a campaign goal and an audience insight into a structured creative brief a designer, video editor, or UGC creator can execute - messaging angle, hook…

ad-creative-fatigue ↗

Decide whether a running ad creative is genuinely wearing out, or whether a confounder - budget change, learning-phase reset, audience saturation, auction CPM…

ad-creative-test-plan ↗

Design a pre-launch ad creative test plan - falsifiable hypothesis, isolation level, test cells with per-cell budgets, required sample, spend and duration, and…

ad-format-fit ↗

Flag ad formats that are a poor fit or commonly misused for a given objective and platform - formats the objective does not even expose.

ad-hook-analyzer ↗

Score and force-rank the openings of candidate video ads - from a script, transcript, storyboard.

ad-manager ↗

The ads consultant that becomes an ads agent. Reads paid-ad performance natively through the TikTok Ads connector, or via a build-connector Zapier connection…

ad-negative-keywords ↗

Build and maintain negative keyword lists from search term reports to cut wasted ad spend in paid search - n-gram query mining to surface irrelevant search…

ad-platform-selection ↗

Decide which paid channel families fit a business's economics, audience, funnel stage, and budget at campaign setup - paid search, paid social, short-form…

ad-spend-allocation ↗

Split a fixed total paid-media budget across campaigns, platforms, funnel stages.

ad-spend-guardrails ↗

Set the organisation's top-level paid-media spend guardrails as written policy - maximum allowable CAC, minimum ROAS/MER floor, kill-switch thresholds.

ad-swipe-file ↗

Build and maintain a competitor swipe file - competitors' currently-running ads collected into a categorised, queryable library classified by format, hook…

adam-s-k-i/super-backlog ↗

Supercharge your backlog. Watch it live.

adamczhang/CLI-MODE ↗

Every AI coding subscription you pay for, from inside Claude Code. CLI-MODE is a Claude Code plugin that runs Antigravity, Claude Code, Grok Build, Cursor, GitHub Copilot and Codex CLI as your agents: you send them work from the chat, or let Claude hand it over, and their answers come back into the conversation you were already in.

adamjali/claude-skills ↗

A marketplace of practical Claude Code skills, packaged as installable plugins: research & competitor teardowns, web build/deploy, image search, repo auditing, macOS disk cleanup, prospecting & cold outreach, email broadcasts, and a skill generator. Each skill is its own plugin, so you install only what you want.

adamjali/research-poster-skill ↗

A Claude Code skill that turns a PDF abstract into a polished, fully-editable scientific conference poster (a native PowerPoint .pptx plus a PDF and a preview image) with honest charts, verified citations, big readable typography, and a render-and-QA loop. It can match an existing poster's house style, and it runs interactively or fully autonomously.

adamlinscott/claude-skills ↗

Each skill lives under skills//SKILL.md, and each agent under agents//.md. These are the single source of truth: an install script links them into ~/.claude/skills/ and ~/.claude/agents/ so Claude loads them in every session, on every machine.

adamradek-ux/claude-code-personal-pack ↗

A personal assistant pack for Claude Code, extracted from a real single-user setup: lifestyle agents, discipline skills, guardrail hooks, and the methodology notes behind them.

adamriofc/indonesian-business-agent-skills ↗

*Give AI agents a business brain for Indonesia.*

adapt ↗

Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets.

adaptico/adaptico-os ↗

Plug your project into Claude Code and get a real go-to-market team on the command line. Adaptico OS audits your marketing, sharpens your positioning, fixes your conversion, writes your copy, plans your launch, and tracks your competitors - tuned specifically for early-stage SaaS and AI startup founders.