Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
47,966 skills from 2,309 repositories · updated 16 hours ago
47,966 skills
- finta-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Finta plan selection and feature usage. Trigger with phrases like "finta cost", "finta pricing", "finta plan selection".PlanningNo warnings★ 2.9K↓ —
- clade-load-scalejeremylongshore/tons-of-skills-marketplaceScale Claude usage for high-throughput applications — batches, queues, Use when working with load-scale patterns. concurrency control, and tier upgrades. Trigger with "anthropic scale", "claude high volume", "anthropic throughput", "scale claude api", "anthropic concurrent requests".EngineeringNo warnings★ 2.9K↓ —
- tao-train-bevfusionNVIDIA/skillsBEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for robust 3D perception. Use when training, evaluating, or running inference for a TAO BEVFusion model. Trigger phrases include "train BEVFusion", "LiDAR + camera fusion", "BEV 3D detection", "multi-sensor 3D perception".OtherNo warnings★ 3.8K↓ —
- figma-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect Figma API diagnostic evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Figma API problems. Trigger with phrases like "figma debug", "figma support bundle", "collect figma logs", "figma diagnostic".DesignNo warnings★ 2.9K↓ —
- canva-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement endpoint- and user-scoped Canva throttling with bounded backoff and reconciliation. Use when handling HTTP 429, sizing concurrency, or preventing duplicate asynchronous jobs. Trigger with: "Canva rate limit", "Canva 429", "throttle Canva requests".OtherNo warnings★ 2.9K↓ —
- doca-bare-metal-deploymentNVIDIA/skillsRunning a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField Arm. Use this skill for launching and supervising it (direct, tmux, systemd), and when it "exits 1 right after launch", "systemd keeps restarting it", reports "no matching device on the BF", or the BlueField itself is unhealthy: "bfb-install exited 0 but DPU is dead", "ping 192.168.100.2 works but ssh fails", "host PFs aren't showing netdevs". Refuse service containers under kubelet (doca-container-deployment). Covers PCI/NUMA/CPU/IRQ binding, co-tenant isolation (cgroup-v2/netns/numactl), a seven-layer error taxonomy, platform lifecycle (BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery) and a six-state BlueField lifecycle classifier. Destructive firmware burn / mlxconfig set requires explicit confirmation via doca-hardware-safety; library APIs, env prep, and build use other skills.DevOpsNo warnings★ 3.8K↓ —
- token-integration-analyzertrailofbits/skillsToken integration and implementation analyzer based on Trail of Bits' token integration checklist. Analyzes token implementations for ERC20/ERC721 conformity, checks for 20+ weird token patterns, assesses contract composition and owner privileges, performs on-chain scarcity analysis, and evaluates how protocols handle non-standard tokens. Use when integrating or accepting arbitrary ERC20/ERC721 tokens, auditing a token implementation for standards conformity, or assessing risk from weird tokens such as fee-on-transfer, rebasing, missing return values, or blocklists.LegalNo warnings★ 7.9K↓ —
- kiro-spec-requirementsgotalab/cc-sddGenerate comprehensive requirements for a specificationPlanningNo warnings★ 3.7K↓ —
- hive.terminal-tools-pty-sessionsaden-hive/hiveUse when you need state across calls — building env vars, navigating with cd, driving REPLs (python -i, mysql, psql, node), or responding to interactive prompts (sudo password, ssh host-key confirmation, mysql connection). Teaches the prompt-sentinel exec pattern (default mode), raw I/O for REPLs (raw_send=True then read_only=True), the one-in-flight-per-session rule, and the close-or-leak-against-the-cap discipline. Bash on macOS — never zsh; explicit shell=/bin/zsh is rejected. Read before calling terminal_pty_open.DataNo warnings★ 11.1K↓ —
- clerkclerk/skillsClerk authentication router. Use when user asks about Clerk CLI operations, adding authentication, setting up Clerk, custom sign-in flows, Swift or native iOS auth, native Android auth, Next.js patterns, React patterns, Vue patterns, Nuxt patterns, Astro patterns, TanStack Start patterns, Expo patterns, React Router patterns, Chrome Extension patterns, organizations, billing, subscriptions, payments, pricing, plans, seat-based pricing, feature entitlements, syncing users, testing, impersonating a user, or testing webhooks locally. Automatically routes to the specific skill based on their task.OfficialTestingNo warnings★ 89↓ —
- send-experiment-designeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "design an email A/B test", "set up a multivariate subject/CTA test", "run a send-time test", "build a hold-out group", or "is this email result statistically and practically material?"; produces a falsifiable hypothesis, one-variable-per-cell matrix, sample-size/MDE/duration/power plan, and an effect/uncertainty read from own ESP data. Applies only a precommitted owner-approved action rule; the helper never chooses a business action. Not for EQS/vetoes or writing the email. 邮件AB测试设计/多变量测试/发送时间测试/留出组/显著性判定TestingNo warnings★ 3K↓ —
- rag-blueprintNVIDIA/skillsNVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).DevOpsNo warnings★ 3.8K↓ —
- programmatic-seonowork-studio/notfair-pluginProgrammatic SEO planning and audit: building or evaluating large sets of template-generated pages that target long-tail query patterns (e.g. "[service] in [city]", "[product] vs [product]", "[tool] for [use-case]"). Covers data-source and template design, thin/duplicate-content and doorway-page risks, per-page uniqueness and value thresholds, internal linking and hubs, indexation management (publish vs. noindex), and scaling without a manual action. Use whenever the user wants to generate many pages from a template/dataset, build location/comparison/use-case pages at scale, or asks why generated pages aren't indexing. Trigger on: "programmatic SEO", "pSEO", "generate pages at scale", "templated pages", "location pages at scale", "comparison pages", "[city] pages", "my generated pages aren't indexed", "doorway pages", "scale content". For one-off content use /content-writer; for keyword discovery use /keyword-research.MarketingNo warnings★ 4.1K↓ —
- howmichael-denyer/pstack-claudeUse for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.PlanningNo warnings★ 3.7K↓ —
- doca-gpunetioNVIDIA/skillsUse this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.EngineeringNo warnings★ 3.8K↓ —
- paperclippaperclipai/paperclipUse for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.PlanningNo warnings★ 108.9K↓ —
- kiro-spec-requirementsgotalab/cc-sddGenerate comprehensive requirements for a specificationPlanningNo warnings★ 3.7K↓ —Also in 5 other repos
- doca-perftestNewNVIDIA/skillsUse this skill when the user is running DOCA Perftest (doca_perftest), the RDMA benchmark that measures bandwidth, message rate and latency for RDMA verbs, point-to-point or across a cluster, with an optional DOCA Verbs backend (-r dv) or GPUNetIO engine (--engine gpunetio). Trigger even when the user does not say "DOCA Perftest" — implicit phrasings include "how do I benchmark RDMA write bandwidth with DOCA", "run ib_write_bw but across 8 nodes", "perftest says the device is busy", "my latency numbers differ between client and server", "launch the server over SSH", or "run an all-to-all RDMA test from a JSON scenario". Refuse and route elsewhere for DOCA install (doca-setup), DOCA Bench (doca-bench), and application-level throughput.TestingNo warnings★ 3.8K↓ —
- groq-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect Groq debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Groq problems. Trigger with phrases like "groq debug", "groq support bundle", "collect groq logs", "groq diagnostic".EngineeringNo warnings★ 2.9K↓ —
- groq-common-errorsjeremylongshore/tons-of-skills-marketplaceDiagnose and fix Groq API errors with real error codes and solutions. Use when encountering Groq errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "groq error", "fix groq", "groq not working", "debug groq", "groq 429".EngineeringNo warnings★ 2.9K↓ —
- kiro-validate-designgotalab/cc-sddInteractive technical design quality review and validationDesignNo warnings★ 3.7K↓ —
- skill-publish-checklistZJU-REAL/Easel发布前完整性检查：逐项检查标题、封面、标签、格式、合规标记、链接、CTA 是否齐全， 确保内容没有遗漏就能发布。当用户说"检查一下能不能发"、"发布前检查"、"checklist"、 "查漏补缺"、"发之前看一眼"、"发布清单"、"漏了什么没"、"能发了吗"时触发。 和 skill-quality-gate 的区别：quality-gate 做深度合规审核和质量评分， publish-checklist 只做"有没有漏东西"的快速完整性检查。OtherNo warnings★ 4.2K↓ —
- skill-account-diagnosisZJU-REAL/Easel账号诊断/起号体检：读取已完善的画像 Profile + 近期内容数据，诊断垂直度、定位清晰度、限流降权信号、流量池阶段，给出病因→证据→处方式的起号意见与发布建议。当用户说账号诊断/起号体检/为什么没流量/是不是被限流了/账号定位诊断/起号建议/怎么起号时使用OtherNo warnings★ 4.2K↓ —
- tao-train-mask-auto-labelNVIDIA/skillsMAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Trigger phrases include "train MAL", "Mask Auto-Label", "weakly-supervised segmentation", "box-prompted segmentation", "minimal-annotation mask prediction".OtherNo warnings★ 3.8K↓ —
core
vercel-labs/agent-browser
OfficialTestingUpdated 23 hours ago
From the author
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.
Install
npx skills add vercel-labs/agent-browser --skill core -a claude-code
Installs to .claude/skills/core/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Runs bundled scriptsUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 90
Security85
Provenance100
Maintenance100
Licence100
Adoption72
Files (14)
- SKILL.md
- references/authentication.md
- references/commands.md
- references/profiling.md
- references/proxy-support.md
- references/session-management.md
- references/snapshot-refs.md
- references/streaming.md
- references/trust-boundaries.md
- references/video-recording.md
- references/webgpu.md
- templates/authenticated-session.sh
- +2 more