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.
48,620 skills from 2,355 repositories · updated 7 minutes ago
48,620 skills
- text-polisherZJU-REAL/Easel文本润色打磨：七轮聚焦扫描（清晰度/语气/价值感/证据/具体性/情感/风险） + 去 AI 感改写（砍填充短语、打破公式化结构、主动语态、变化节奏）。 当用户说"帮我改一下"、"润色"、"文案打磨"、"编辑文案"、 "去 AI 感"、"太像 AI 了"、"改自然"、"校对"、"文案优化"时使用。 合并了原 copy-editing（系统化编辑）和 stop-slop（去 AI 感）的能力。WritingNo warnings★ 4.3K↓ —
- audio-visualizerZJU-REAL/Easel音频可视化视频：把纯音频（播客片段、音乐、口播金句、电台）渲染成带动态波形/频谱的视频，配封面和标题，好发到抖音/B站/视频号等只收视频的平台。当用户说 音频可视化、音频转视频、播客做成视频、音频波形视频、音乐可视化、给音频配画面、声波视频、频谱视频、把音频发到视频平台、电台切片视频 时使用。基于 shared/scripts/audio_viz.py（ffmpeg showwaves/showcqt/showspectrum）。与 audio-mix 区别：那个输出音频，本 SKILL 输出视频；与 slideshow-video 区别：那个用图片，本 SKILL 用音频驱动画面。MediaNo warnings★ 4.3K↓ —
- doca-telemetry-utilsNVIDIA/skillsdoca_telemetry_utils command line on a host with DOCA: discover the diagnostic-counter schema, translate counter names to binary Data IDs and back, and check per-device counter support before committing a DOCA Telemetry exporter config. Use this skill when telemetry counters vanish between the exporter and the collector: "my exporter ships but the collector sees nothing", "this metric silently drops downstream", "which counters does this BlueField expose", "translate this 0x... back to a counter name", "what do node / pcie_index / depth mean here", or "is this counter supported on this device", even without naming the tool. Route exporter or collector code to doca-telemetry-exporter / doca-telemetry, DTS deployment to doca-dts, and DOCA install or repair to doca-setup.DevOpsNo warnings★ 3.8K↓ —
- security-researchcode-yeongyu/oh-my-openagentOmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.SecurityNo warnings★ 70.6K↓ —
- video-strategyZJU-REAL/Easel视频制作策略与工具选型：AI 视频生成模型对比、视频脚本结构设计、制作流程规划，覆盖产品演示/解说/社媒短视频场景。 当用户说"视频怎么做""视频选型""用什么工具做视频""视频制作流程""视频策略""视频系列规划"时使用。 和 video-script 的区别：video-strategy 做内容规划与工具选型，video-script 写具体某条视频的脚本。MediaNo warnings★ 4.3K↓ —
- hyperframesheygen-com/hyperframesRead first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.OfficialMediaNo warnings★ 76.9K↓ —
- voice-cloneZJU-REAL/Easel上传本人语音样本克隆专属音色，再用它合成口播、旁白或带货语音。当用户说“声音克隆、克隆/复刻我的声音、用我的声音配音、定制专属音色”时使用，需要用户自备云端 provider 凭证。使用公共现成音色时改用 tts-voiceover。OtherNo warnings★ 4.3K↓ —
- foundationpose-setupNVIDIA/skillsInstall or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines. Use for SAM3/TAO dependency conflicts, CUDA library failures, and depth-engine shape or precision decisions.OtherNo warnings★ 3.8K↓ —
- 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★ 70.6K↓ —
- deslopmichael-denyer/pstack-claudeRemove AI-generated code slop and clean up code styleEngineeringNo warnings★ 3.7K↓ —
- Verification & Quality Assuranceforyourhealth111-pixel/Vibe-SkillsComprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.EngineeringNo warnings★ 3.8K↓ —Also in 1 other repo
- windows-hook-debuggingforyourhealth111-pixel/Vibe-SkillsWindows环境下Claude Code插件Hook执行错误的诊断与修复。当遇到hook error、cannot execute binary file、.sh regex误匹配、WSL/Git Bash冲突时使用。EngineeringNo warnings★ 3.8K↓ —
- lcx-doctorcode-yeongyu/oh-my-openagentDiagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install audited and compared with the latest LazyCodex and Codex code.EngineeringNo warnings★ 70.6K↓ —
- jetson-customize-usbNVIDIA/skillsEnable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.WritingNo warnings★ 3.8K↓ —
- doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.OfficialWritingNo warnings★ 186.1K↓ —Also in 6 other repos
- anti-ui-slopdavepoon/buildwithclaudeStop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Codex, Claude Code, Cursor, Copilot, and other coding agents.DesignNo warnings★ 3.7K↓ —
- i4h-workflow-validateNVIDIA/skillsRun the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation, checkpoints, or local controllers; do not use for replay or dataset annotation.ProductivityNo warnings★ 3.8K↓ —
- conversion-signal-qaaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "QA my conversion tracking before launch", "check my UTMs / pixel / event firing", "set up a tracking pre-flight", or "set the dedup rule so Meta and Google stop double-counting"; builds and fixes the measurement plumbing — conversion-event firing, UTM hygiene, cross-platform dedup rules, attribution-window alignment, and offline/iOS-ATT modeled-gap flags — as a pre-flight checklist plus a UTM/event-spec builder. Not for scoring R1/R2 — that is a scored veto in ad-account-auditor; not for account structure — use campaign-architect. 付费广告转化追踪QA/UTM规范/跨平台去重TestingNo warnings★ 3K↓ —
- i4h-workflow-train-rlNVIDIA/skillsUse when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.ProductivityNo warnings★ 3.8K↓ —
- get-pr-commentsmichael-denyer/pstack-claudeFetch and summarize review comments from the active pull requestEngineeringNo warnings★ 3.7K↓ —
- ad-test-designeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试TestingNo warnings★ 3K↓ —
- offer-claims-registryaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "register this claim", "log our current offers", or "where is the proof for this figure"; curates claim wording, evidence, disclosures, terms, review dates, and live offers through the append-only claims event stream. Not for scoring claim vetoes — use the relevant auditor; not for writing ad copy — use ad-creative-builder. 广告声明台账/优惠信息登记/证据溯源MarketingNo warnings★ 3K↓ —
- ugc-ad-remixdavepoon/buildwithclaudeTurn a proven UGC video ad into a shot-by-shot script for your own product. Use when the user shares a TikTok, Reels or Shorts ad (link or transcript) and wants a version for their product, asks to "remix", "rewrite" or "copy the structure of" an ad, or needs a UGC script that is ready to film. Uses the free UGCfy AI MCP when it is connected; works from pasted ad text without it.MarketingNo warnings★ 3.7K↓ —
- theme-factorydavepoon/buildwithclaudeToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.DocumentsNo warnings★ 3.7K↓ —
rag-eval
NVIDIA/skills
OtherUpdated 2 days ago
From the author
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
Install
npx skills add NVIDIA/skills --skill rag-eval -a claude-code
Installs to .claude/skills/rag-eval/ · 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 (10)
- BENCHMARK.md
- SKILL.md
- eval/h100.json
- eval/nvidia_hosted.json
- references/benchmark-execution.md
- references/dataset-and-conversion.md
- references/evaluate-rag-cli.md
- references/result-analysis.md
- skill-card.md
- skill.oms.sig