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.
48,168 skills from 2,325 repositories · updated 6 hours ago
48,168 skills
- rag-perfNVIDIA/skillsPerformance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).TestingNo warnings★ 3.8K↓ —
- doca-rdmaNVIDIA/skillsRDMA data movement on NVIDIA BlueField/ConnectX NICs (RoCE/InfiniBand) with DOCA RDMA, instead of hand-written libibverbs/rdma_cm. Use when the user moves data between processes or hosts over the NIC, or hits "one-sided read returns permission denied", "completions never arrive after submit", "connection callback never fires", atomic compare-and-swap over RoCE, or DOCA_ERROR_FULL on the send queue under burst, even without naming DOCA RDMA. Covers bringing up an RDMA context on a doca_dev, connection methods (RDMA CM, bridge/OOB, or gRPC exchange of doca_rdma_export()), the eleven task types (Send/Receive/Send-Imm, Read/Write/Write-Imm, Atomic CmpSwap/FetchAdd, Get/Set/Add Remote Sync Event), matching mmap + RDMA permissions, queue and connection sizing, doca_rdma_cap_* queries, and DOCA_ERROR_* from RDMA calls. Raw QP/verbs control belongs to doca-verbs. Refuse and route elsewhere for general RDMA / ibverbs theory (queue pairs, MRs, RoCE vs IB), installing DOCA itself, or non-RDMA DOCA libraries.WritingNo warnings★ 3.8K↓ —
- i4h-workflow-scene-editNVIDIA/skillsEdit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success rules; do not use to create a new workflow.WritingNo warnings★ 3.8K↓ —
- nvflare-diagnose-jobNVIDIA/skillsUse when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with EXECUTION_EXCEPTION, or produced suspicious errors. Diagnose in simulation, POC, or production by collecting bounded evidence and mapping failure patterns to recovery actions.OtherNo warnings★ 3.8K↓ —
- clerk-expoclerk/skillsAdd Clerk authentication to Expo and React Native apps using @clerk/expo. Use for Expo setup, prebuilt native components (AuthView, UserButton), custom sign-in/sign-up flows (email, password, SMS/phone OTP, MFA), OAuth/SSO, native Google/Apple sign-in, Expo Router protected routes, biometrics, and push notifications. Do not use for native Swift/iOS, native Android/Kotlin, or web-only framework projects.OfficialEngineeringNo warnings★ 89↓ —
- ramp-sdk-patternsjeremylongshore/tons-of-skills-marketplaceBuild a small typed Ramp Developer API adapter with secure token management, pagination, structured errors, rate control, idempotency, and schema drift checks. Use when replacing scattered raw requests in application code. Trigger with "Ramp API client" or "Ramp SDK patterns".EngineeringNo warnings★ 2.9K↓ —
- hex-install-authjeremylongshore/tons-of-skills-marketplaceInstall and configure Hex SDK/CLI authentication. Use when setting up a new Hex integration, configuring API keys, or initializing Hex in your project. Trigger with phrases like "install hex", "setup hex", "hex auth", "configure hex API key".EngineeringNo warnings★ 2.9K↓ —
- impeccableUpdatedpbakaus/impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or otherwise improve a frontend interface: websites, landing pages, dashboards, product UI, components, forms, settings, onboarding, empty states, and native iOS or Android screens. Handles UX review, hierarchy, layout, typography, color, motion, UX copy, accessibility, responsive behavior, edge cases, and capturing or documenting design systems (DESIGN.md, tokens). Also for making bland UI bolder, loud UI quieter, or ambitious visual effects. Not for backend-only or non-UI tasks.DesignNo warnings★ 97.8K↓ —
- hyperplancode-yeongyu/oh-my-openagentAdversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', 'adversarial plan', 'hostile planning', 'cross-critique plan', '하이퍼플랜', '적대적 계획', '교차 비평'.PlanningNo warnings★ 70.5K↓ —
- nemo-rl-session-memoryNVIDIA/skillsManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.ProductivityNo warnings★ 3.8K↓ —
- gsd:new-milestonedavepoon/buildwithclaudeStart a new milestone cycle — update PROJECT.md and route to requirementsPlanningNo warnings★ 3.7K↓ —
- gsd:complete-milestonedavepoon/buildwithclaudeArchive completed milestone and prepare for next versionOtherNo warnings★ 3.7K↓ —
- narrative-quality-auditoraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "audit our brand narrative" or "is this message on-canon"; runs separate typed TALE truth, system, or effectiveness profiles and never averages them into one composite. Checks differentiation, canon, landing consistency, and evidence integrity. Not for launch readiness — use launch-readiness-auditor; not for social operations — use social-quality-auditor. 品牌叙事分层审计/发布前一致性放行OtherNo warnings★ 3K↓ —
- wiki-digestAr9av/obsidian-wikiProduce a day/week/month knowledge digest summarizing what was learned, updated, and connected in the wiki. Use for readable recent-learning summaries; wiki-status reports source and ingestion state instead.ProductivityNo warnings★ 3.6K↓ —
- navan-debug-bundlejeremylongshore/tons-of-skills-marketplaceAssemble a content-free Navan integration support bundle for operators or vendor escalation. Use when triage needs reproducible evidence. Trigger with "collect Navan diagnostics", "Navan support bundle", or "sanitize Navan logs".EngineeringNo warnings★ 2.9K↓ —
- abridge-cost-tuningjeremylongshore/tons-of-skills-marketplaceEvaluate Abridge adoption, workflow value, and avoidable operational friction without inventing prices or vendor billing meters. Use when reviewing an Abridge rollout or renewal. Trigger with "analyze Abridge value".ProductivityNo warnings★ 2.9K↓ —
- video-reframeZJU-REAL/Easel智能转换视频画幅，支持 9:16/16:9/1:1、模糊背景填充、焦点裁切和人脸居中裁切。当用户说“横竖版互转、改成 9:16、转竖屏、去黑边、适配平台尺寸、人脸居中裁”时使用。通用简单裁切用 video-editing；逐段动态人脸跟随切片用 clipify。MediaNo warnings★ 4.2K↓ —
- impeccableNewpbakaus/impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or otherwise improve a frontend interface: websites, landing pages, dashboards, product UI, components, forms, settings, onboarding, empty states, and native iOS or Android screens. Handles UX review, hierarchy, layout, typography, color, motion, UX copy, accessibility, responsive behavior, edge cases, and capturing or documenting design systems (DESIGN.md, tokens). Also for making bland UI bolder, loud UI quieter, or ambitious visual effects. Not for backend-only or non-UI tasks.DesignNo warnings★ 97.8K↓ —
- i4h-workflow-dataset-mimicNVIDIA/skillsExpand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data, alter state directly, or generate new images.ProductivityNo warnings★ 3.8K↓ —
- skill-xhs-comment-replyZJU-REAL/Easel小红书评论互动运营：列出我的笔记、抓取某条笔记下的评论、按画像语气逐条回复、以及删除评论 （含自己发的回复）。基于 Playwright + 持久化登录态，headless 即可运行，与 skill-xhs-publisher 共用同一登录态。评论抓取走接口响应拦截（稳）；回复/删除走 DOM 文本定位（无坐标）+ 逐字符输入反检测； 带已回复去重、逐条间隔防风控、dry-run 预演。用 notes 列笔记或 fetch --url 贴链接，免手动拆 token。 触发：抓小红书评论 / 回复评论 / 删除评论 / 删评 / 维护评论区 / 看我某条笔记的评论。TestingNo warnings★ 4.2K↓ —
- 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↓ —
- offensive-wpsSnailSploit/Claude-RedWPS (Wi-Fi Protected Setup) PIN attack methodology — Pixie Dust offline attack against vulnerable chipsets (Ralink, Realtek, Broadcom, MediaTek), online PIN brute-force with reaver/bully, lockout handling, time-of-day evasion, WPS push-button vulnerability windows, and PIN-to-PSK derivation. Use when a target SOHO router exposes WPS — common on consumer ISP gear, often left enabled by default even when WPS attacks have been known for over a decade.SecurityNo warnings★ 10K↓ —
- jetson-set-targetNVIDIA/skillsSwitch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles — use jetson-init-target instead.OtherNo warnings★ 3.8K↓ —
- excel-dcf-modelerjeremylongshore/tons-of-skills-marketplaceBuild discounted cash flow (DCF) valuation models in Excel. Use when creating DCF models, calculating enterprise value, or valuing companies. Trigger with phrases like 'excel dcf', 'build dcf model', 'calculate enterprise value'.DocumentsNo warnings★ 2.9K↓ —
tao-finetune-video-clip
NVIDIA/skills
MediaUpdated yesterday
From the author
InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine-tune IV2CLIP", "run video_clip train/evaluate/inference/export", "build a Video-CLIP TensorRT engine", "InternVideo2-CLIP on KPI chunks", or "TAO video_clip on vadr1_chunks JSON".
Install
npx skills add NVIDIA/skills --skill tao-finetune-video-clip -a claude-code
Installs to .claude/skills/tao-finetune-video-clip/ · 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
Instructions onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance83
Maintenance100
Licence100
Adoption57
Files (17)
- BENCHMARK.md
- SKILL.md
- config/skillspector-baseline.yaml
- eval.config
- evals/evals.json
- references/skill_info.yaml
- references/spec_template_deploy_evaluate.yaml
- references/spec_template_deploy_inference.yaml
- references/spec_template_evaluate.yaml
- references/spec_template_export.yaml
- references/spec_template_gen_trt_engine.yaml
- references/spec_template_inference.yaml
- +5 more