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.
45,100 skills from 2,196 repositories · updated 15 hours ago
44,137 skills
- tao-train-ocrnetNVIDIA/skillsOCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCRNet model. Trigger phrases include "train OCRNet", "scene text recognition", "OCR cropped text", "CTC / attention text decoder".OtherNo warnings★ 3.7K↓ —
- nvshmem-enable-tmaNVIDIA/skillsPrepare or review NVSHMEM CUDA kernels for TMA SMEM registration and direct-SMEM transfers. Do not use for unrelated CUDA tuning.EngineeringNo warnings★ 3.7K↓ —
- youtube-fulldavepoon/buildwithclaudeUse when YouTube is or could be relevant — video/channel/playlist links, video IDs, @handles, creator lookups, summaries, quotes, topic research, tutorials, talks, product reviews, or anywhere video content is fresher or richer than text search. Covers transcripts, video/channel search, channel browsing, playlists, and in-channel search.MediaNo warnings★ 3.7K↓ —
- nvmolkit-usageNVIDIA/skillsUse when writing or debugging nvMolKit Python code for GPU-accelerated RDKit fingerprints, similarity, conformers, clustering, and molecular searches.WritingNo warnings★ 3.7K↓ —
- 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★ 3.7K↓ —
- doca-fireflyNVIDIA/skillsUse this skill when the user is operating the DOCA Firefly Service container on BlueField — picking the four PTP configuration axes (role / profile / domain / interface), wiring the BlueField PHC + host follower + consumer workload pairing, deciding whether PTP-grade time is even needed (vs. chrony / NTP), or debugging a Firefly deployment where PTP isn't syncing or the host clock isn't following. Trigger even when the user does not explicitly mention "DOCA Firefly" or "PTP" — typical implicit phrasings include "container green but PTP never advances past LISTENING", "Firefly says synced but the host clock still drifts", "sync acquired but offset is tens of microseconds", "my Rivermax SMPTE workload needs PTP", or "is chrony good enough". Refuse and route elsewhere for installing DOCA, host-side chrony / ptp4l config bodies, PTP topology / boundary-clock design, building DOCA apps that read the disciplined PHC, or other DOCA services (DMS, Flow-Inspector, HBN) — those belong to other skills.DevOpsNo warnings★ 3.7K↓ —
- doca-urom-svcNVIDIA/skillsOperate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using `doca-urom`: pull the NGC image, choose the UCX component, size queues, configure Comch pairing, and align host and service versions. SECURITY: the service has no standalone access control; Comch pairing and RDMA permissions are the boundary. Pair only intended hosts, expose least-privilege memory regions, and verify both views before start. Trigger for slow UCX collectives, unexpected NOT_PERMITTED, or missing completions. Do not use for host application code, MPI/UCX integration design, or DOCA install.SecurityNo warnings★ 3.7K↓ —
- nvflare-orientNVIDIA/skillsRoute open-ended NVFLARE advice and only conversion requests whose preliminary source inspection reports unresolved or conflicting ownership; never load this skill merely to inspect a concrete conversion request before selecting its detected framework converter.MarketingNo warnings★ 3.7K↓ —
- kiro-validate-implgotalab/cc-sddValidate feature-level integration after all tasks are implemented. Checks cross-task consistency, full test suite, and overall spec coverage.TestingNo warnings★ 3.7K↓ —
- hypothesis-generationforyourhealth111-pixel/Vibe-SkillsStructured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Also owns explicit HypoGeniC-style or automated LLM-driven hypothesis generation/testing requests inside this single skill. For open-ended ideation use scientific-brainstorming.TestingNo warnings★ 3.8K↓ —
- gsd:ai-integration-phasedavepoon/buildwithclaudeGenerate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and evaluation strategyDesignNo warnings★ 3.7K↓ —
- kiro-steering-customgotalab/cc-sddCreate custom steering documents for specialized project contexts. Use when creating domain-specific steering files.PlanningNo warnings★ 3.7K↓ —
- geomasterforyourhealth111-pixel/Vibe-SkillsComprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, and 7 programming languages (Python, R, Julia, JavaScript, C++, Java, Go) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.ScienceNo warnings★ 3.8K↓ —
- session-investigatorevalstate/fast-agentInvestigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool call/result correlation, and common failure patterns.FinanceNo warnings★ 3.9K↓ —
- skill-competitor-analysisZJU-REAL/Easel分析竞品账号的内容策略，拆解选题、格式、爆款规律和互动模式，输出差异化机会与行动建议。 当用户说"分析竞品""竞品账号""对标账号""拆解爆款""竞品在做什么""对手内容策略""竞争分析"时使用。 和 skill-content-gap-analysis 的区别：本 SKILL 拆解具体竞品账号的内容策略与爆款规律； content-gap-analysis 从赛道整体供需找"没人做好"的蓝海选题空白。OtherNo warnings★ 4.1K↓ —
- skill-cross-platform-diffZJU-REAL/Easel跨平台内容差异深度分析。分析同一话题/内容在不同平台（小红书、抖音、B站、知乎、 微博、公众号、X 等）的呈现差异：内容形式、受众偏好、话语体系、流量逻辑、变现路径。 帮创作者理解"同一个内容在不同平台应该怎么做"。当用户说"小红书和抖音有什么区别"、 "这个话题在B站怎么做"、"跨平台差异"、"不同平台"、"各平台怎么做"、"平台特点"时触发。 和 skill-content-repurposing 的区别：repurposing 做格式适配和内容改写， cross-platform-diff 做深度差异分析和策略洞察。OtherNo warnings★ 4.1K↓ —
- 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★ 4.1K↓ —
- skill-topic-evaluatorZJU-REAL/Easel评估单个选题的潜力，按统一维度（流量潜力、账号匹配、 竞争差异化、时效价值、变现空间、制作成本、合规风险）打分，输出"做/不做/改方向"建议。 当用户说"这个选题值不值得做"、"评估一下"、"能不能火"、"有没有流量"、 "做不做这个"、"选题评估"、"值得做吗"、"这个话题行不行"、"帮我判断一下"时触发。 skill-content-matrix 批量生成选题池；skill-post-scorer 评估已完成内容，本 SKILL 评估尚未制作的单个选题。OtherNo warnings★ 4.1K↓ —
- skill-campaign-plannerZJU-REAL/Easel活动/营销策划（国内本地化）：为节日营销、电商大促（618/双11/年货节）、新品发布、活动造势 制定完整方案——目标拆解、营销节奏（预热-爆发-返场）、多平台内容矩阵、互动玩法、KOL 分层、 预算分配、风险合规、效果指标。当用户说"营销方案""活动策划""大促方案""618/双11 怎么做" "节日营销""新品发布方案""造势""campaign""营销节奏""怎么搞活动"时使用。MarketingNo warnings★ 4.1K↓ —
- skill-carousel-plannerZJU-REAL/Easel规划轮播图/多图笔记的分页结构：封面 Hook、内容节奏、每页文案和视觉方向、CTA 设计，附互动评分。 当用户说"轮播图策划""多图笔记""图集结构""分页设计""九宫格怎么排""每页写什么""carousel"时使用。 本 SKILL 出分页结构与文案规划（策划层）；实际渲染卡片图用 card-xiaohongshu / xhs-note-creator。PlanningNo warnings★ 4.1K↓ —
- 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★ 4.1K↓ —
- 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★ 4.1K↓ —
- skill-community-opsZJU-REAL/Easel评论区运营与舆情危机应对：为一批评论生成分层回复模板（赞美/提问/求购/杠精/黑粉） 与分级处理规则，从评论中挖掘选题反哺内容，负面事件时做危机分级 + 声明草稿 + 统一口径。 当用户说"回复评论"、"评论区运营"、"评论怎么回"、"钓评论"、"引导互动"、 "评论区选题"、"舆情"、"危机公关"、"差评"、"黑粉"、"被骂了"、"道歉声明"、 "统一口径"、"负面缠上来了"、"翻车了怎么办"时触发。 和 skill-quality-gate 的区别：quality-gate 是发布前合规质检， community-ops 是发布后的评论互动与危机响应。OtherNo warnings★ 4.1K↓ —
- skill-xhs-publisherZJU-REAL/Easel将图文/视频内容发布到小红书（XHS）。基于 Playwright + 持久化登录态，headless 即可运行， 流程与选择器移植自成熟开源实现 xiaohongshu-mcp（含发布成功校验、上传完成等待、话题联想绑定、 新旧发布按钮兼容、反检测）。适用场景：发布图文笔记、发布视频、扫码登录、发布前预检。TestingNo warnings★ 4.1K↓ —
patching-bugs
trailofbits/skills
EngineeringUpdated 3 days ago
From the author
Use when a known bug or falsifiable bug hypothesis in a local codebase needs a patch commit and reviewable proof report.
Install
npx skills add trailofbits/skills --skill patching-bugs -a claude-code
Installs to .claude/skills/patching-bugs/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (CC-BY-SA-4.0) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyNo network use seenLicence: CC-BY-SA-4.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance87
Maintenance100
Licence80
Adoption61
Files (1)
- SKILL.md