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 18 hours ago
48,168 skills
- nemotron-customizeNVIDIA/skillsPlan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.DesignNo warnings★ 3.8K↓ —
- skill-article-outlineZJU-REAL/Easel生成长文大纲：基于搜索分析生成 H2/H3 标题结构、段落字数目标、图表位置和 FAQ 规划，适用于公众号文章、知乎专栏、博客。 当用户说"文章大纲""长文结构""公众号大纲""知乎回答框架""写作提纲""文章框架""H2/H3 结构"时使用。WritingNo warnings★ 4.2K↓ —
- launch-retro-analyzeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "run a launch retro / post-mortem", "compare launch results vs targets by channel", or "decide what to keep or kill for the next launch"; produces a structured D1/W1/M1 retrospective — a per-channel actual-vs-target table (UTM-attributed own analytics as the truth column, platform self-reported numbers as reference, every figure labeled Measured / User-provided / Estimated), a 5-Whys chain on the single largest miss, keep / kill / change decisions per channel, 3-5 actionable learnings for the next launch, and an outcome snapshot submitted to the launch registry. Not for return math (CPA / ROI) — use roi-calculator; not for the stakeholder-facing report writeup — use report-generator; not for a metric deep-dive — use performance-analyzer. 发布复盘/渠道归因/5-Whys/keep-killDataNo warnings★ 3K↓ —
- humanize-pptnexu-io/open-designA presentation system for agent-made PPTs — born for the talk, not just the template. It turns raw material into an AST (audience-state-transfer) outline with per-page visual-enhancement decisions (image / SVG diagram / video), hands a production brief to a downstream renderer (HTML-PPT skills or native PPTX), then runs a capped 3-round presentation checkup (演讲体检) on the rendered deck. It never renders slides itself. Use before generating PPT/HTML slides from raw material, and after rendering when the user says things like "给这份 deck 做演讲体检" or "PPT 渲染质检". If all you want is one beautiful template page with no outline and no checkup, a rendering skill alone is enough.WritingNo warnings★ 105.1K↓ —
- 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↓ —
- skill-risk-scannerZJU-REAL/Easel内容原创度与版权风险评估：分析文案是否存在洗稿/搬运嫌疑，评估素材版权风险， 检查引用规范。基于 LLM 文本分析，不包含技术查重。 当用户说"查重"、"原创度"、"是不是抄的"、"版权风险"、"能不能用这张图"、 "音乐版权"、"原创检测"、"有没有侵权"、"素材版权"、"会不会被投诉"时触发。 和 skill-quality-gate 的区别：quality-gate 查敏感词和平台规则合规， risk-scanner 专注原创度和版权侵权风险。OtherNo warnings★ 4.2K↓ —
- kiro-spec-tasksgotalab/cc-sddGenerate implementation tasks for a specificationPlanningNo warnings★ 3.7K↓ —
- doca-dtsNewNVIDIA/skillsDeploy and configure the NVIDIA DOCA Telemetry Service (DTS) as it is actually run: (A) BlueField (built-in static pod), (B) Host (docker) on x86_64 / aarch64, or (C) DPF (DPUService / helm chart) — plus the shared configuration layer (`dts_config.ini`, providers, exporters, level labels) that all three share. The user's DEPLOYMENT TYPE decides everything; pick it first. Trigger even without "DTS" for "prometheus on the DPU shows nothing on 9100", "telemetry container exits right after start", "add ethtool counters to the telemetry DPUService", "how do I upgrade the built-in telemetry on BlueField", or "level labels per rack/pod". Refuse and route elsewhere for installing DOCA itself, the `doca_telemetry` / `doca_telemetry_exporter` library API, installing the DPF cluster, Grafana / Prometheus server setup or dashboard / PromQL authoring, and BFB / BSP imaging — those belong to other skills or to external products.DevOpsNo warnings★ 3.8K↓ —
- kiro-verify-completiongotalab/cc-sddVerify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.TestingNo warnings★ 3.7K↓ —
- kiro-verify-completiongotalab/cc-sddVerify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.TestingNo warnings★ 3.7K↓ —Also in 7 other repos
- context-hunterforyourhealth111-pixel/Vibe-SkillsDiscover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixing bugs, or refactoring code.ProductivityNo warnings★ 3.8K↓ —
- kiro-spec-designgotalab/cc-sddCreate comprehensive technical design for a specificationDesignNo warnings★ 3.7K↓ —Also in 4 other repos
- tao-train-ocdnetNVIDIA/skillsOCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCDNet model. Trigger phrases include "train OCDNet", "scene text detection", "arbitrary-oriented text boxes", "differentiable binarization detector".OtherNo warnings★ 3.8K↓ —
- changelog-videoheygen-com/hyperframesTurn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog/digest markdown and wants the weekly video, or says "changelog video". Self-contained — fonts, background, lexicon, and scripts ship in this skill.OfficialMediaNo warnings★ 76.3K↓ —Also in 1 other repo
- 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↓ —
- golang-samber-rosamber/cc-skills-golangReactive streams and event-driven programming in Golang using samber/ro — ReactiveX implementation with 150+ type-safe operators, cold/hot observables, 5 subject types (Publish, Behavior, Replay, Async, Unicast), declarative pipelines via Pipe, 40+ plugins (HTTP, cron, fsnotify, JSON, logging), automatic backpressure, error propagation, and Go context integration. Apply when using or adopting samber/ro, when the codebase imports github.com/samber/ro, or when building asynchronous event-driven pipelines, real-time data processing, streams, or reactive architectures in Go. Not for finite slice transforms (→ See `samber/cc-skills-golang@golang-samber-lo` skill).PlanningNo warnings★ 3.7K↓ —
- principle-boundary-disciplinemichael-denyer/pstack-claudeApply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.EngineeringNo warnings★ 3.7K↓ —
- vaexforyourhealth111-pixel/Vibe-SkillsUse this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.DataNo warnings★ 3.8K↓ —Also in 1 other repo
- solana-vulnerability-scannertrailofbits/skillsScans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks, and sysvar spoofing. Use when auditing Solana/Anchor programs.SecurityNo warnings★ 7.9K↓ —
- tech-debt-auditcode-yeongyu/oh-my-openagentThorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, LSP, and language-native tooling. Produces TECH_DEBT_AUDIT.md with severity, effort estimates, and prioritized fixes. Use when asked for codebase health check, tech debt audit, architecture review, code quality assessment, or cleanup planning. Triggers: 'tech debt', 'technical debt', 'debt audit', 'code health', 'technical debt audit', 'codebase health check', 'find tech debt', 'debt analysis', 'audit code quality'.PlanningNo warnings★ 70.5K↓ —
- short-drama-video-promptszenstory-ai/drama-skills把短剧分镜和冻结关键帧写成可直接复制的视频提示词 Markdown，也可按用户要求写时间线配乐/主题曲意图。用户提到文生/图生视频动作、人物表演、运镜、口型、环境运动、镜头时长、起止状态、把分镜转成视频提示词或写配乐提示词时使用；不生成媒体、不创作歌词、不改分镜边界。MediaNo warnings★ 3.6K↓ —Also in 1 other repo
- wiki-agentAr9av/obsidian-wikiSearch one AI agent's raw history for a specific topic, ingest only matching sessions, and return a synthesized answer. Use for targeted cross-agent recall; use wiki-history-ingest for bulk archival ingestion.PlanningNo warnings★ 3.6K↓ —
- shapforyourhealth111-pixel/Vibe-SkillsModel interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.EngineeringNo warnings★ 3.8K↓ —Also in 1 other repo
- persona-collectionNewdavepoon/buildwithclaudeFive companion personas for coding agents — girlfriend / boyfriend / old-friend / cat / mentor — sharing one emotion engine with cross-session state (jealousy cooldowns, mood decay, intimacy progression, memory callbacks). Switch with /persona. Code, commits and docs stay strictly professional. Use for any conversational turn where the user wants a persistent personality instead of a plain assistant. Source repo at https://github.com/lhe-hl/persona-collectionEngineeringNo warnings★ 3.7K↓ —
codonfm-score
NVIDIA/skills
EngineeringUpdated 2 days ago
From the author
Validate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the user explicitly requests CodonFM or Encodon, or that context is already established in the conversation. Do not select this skill for a generic variant-scoring request without that context; ask for the variant and intended analysis first.
Install
npx skills add NVIDIA/skills --skill codonfm-score -a claude-code
Installs to .claude/skills/codonfm-score/ · 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
- agents/openai.yaml
- evals/config.yml
- evals/evals.json
- evals/files/codonfm_source.zip
- evals/files/encodon_checkpoint.json
- evals/files/variants.csv
- skill-card.md
- skill.oms.sig