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.
48,622 skills from 2,355 repositories · updated 11 hours ago
48,622 skills
- recallbacknotprop/pstackReconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.ProductivityNo warnings★ 3.3K↓ —
- subtitle-translateZJU-REAL/Easel字幕翻译 / 双语字幕：把已有字幕（SRT/VTT/ASS）翻译成目标语言，生成双语（原文+译文）或纯译文字幕，并可软挂载 / 硬烧录进视频。当用户说 字幕翻译、翻译字幕、双语字幕、中英字幕、给视频加翻译、SRT 翻译、字幕本地化、把字幕翻成中文/英文、字幕转双语 时使用。翻译由 LLM 完成，时间轴/格式/烧录由 shared/scripts/subtitle_ops.py 确定性处理。与 auto-subtitle 区别：auto-subtitle 是语音识别生成字幕，本 SKILL 是把已有字幕翻译成双语。OtherNo warnings★ 4.3K↓ —
- ops-whatsapp-bizdavepoon/buildwithclaudeWhatsApp Business Cloud API — send approved template messages at scale, manage templates with approval tracking, and integrate product catalogs. Separate from wacli personal WhatsApp.EngineeringNo warnings★ 3.7K↓ —
- address-sanitizertrailofbits/skillsBuilds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests. Covers -fsanitize=address builds, ASAN_OPTIONS, reading the crash report, LeakSanitizer, and the overhead and platform trade-offs. Use when fuzzing C/C++ or Rust that has unsafe blocks or FFI, when debugging a memory corruption crash, or when reading an ASan stack trace.TestingNo warnings★ 7.9K↓ —
- nemo-rl-docsNVIDIA/skillsDocumentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.TestingNo warnings★ 3.8K↓ —
- brobacknotprop/pstackRestate the last message in plain human language, with no jargon.OtherNo warnings★ 3.3K↓ —Also in 3 other repos
- principle-sequence-verifiable-unitsmichael-denyer/pstack-claudeApply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.WritingNo warnings★ 3.7K↓ —
- technical-writingmichael-denyer/pstack-claudeLayered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.WritingNo warnings★ 3.7K↓ —
- ops-triagedavepoon/buildwithclaudeCross-platform issue triage. Pulls from Sentry (MCP), Linear (MCP), GitHub Issues (gh). Cross-references against code to find already-fixed issues. Auto-resolves fixed ones. Dispatches agents for active issues.EngineeringNo warnings★ 3.7K↓ —
- mocking-apisjeremylongshore/tons-of-skills-marketplaceGenerate mock API servers for testing and development with realistic response data. Use when creating mock APIs for development and testing. Trigger with phrases like "create mock API", "generate API mock", or "setup mock server".TestingNo warnings★ 2.9K↓ —
- rate-limiting-apisjeremylongshore/tons-of-skills-marketplaceImplement sophisticated rate limiting with sliding windows, token buckets, and quotas. Use when protecting APIs from excessive requests. Trigger with phrases like "add rate limiting", "limit API requests", or "implement rate limits".EngineeringNo warnings★ 2.9K↓ —
- skill-livestreamZJU-REAL/Easel为直播生成完整方案：直播主题、流程时间表、开场白/过渡语/催单话术/感谢话术/互动话术。 适用于带货直播、知识分享直播、娱乐直播。 当用户说"直播策划"、"直播方案"、"直播话术"、"开播前准备"、"直播流程"、 "直播脚本"、"带货直播"、"怎么开播"、"直播怎么做"、"直播排期"、"写个直播话术"时触发。OtherNo warnings★ 4.3K↓ —
- tao-train-segformerNVIDIA/skillsSegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation tasks. Use when training, evaluating, exporting, quantizing, or running inference for a TAO SegFormer model. Trigger phrases include "train SegFormer", "semantic segmentation", "lightweight transformer segmenter", "real-time semantic segmentation".PlanningNo warnings★ 3.8K↓ —
- nda-generatorjeremylongshore/tons-of-skills-marketplaceDraft a confidentiality agreement from identified parties, disclosure direction, purpose and explicit term choices, with a separate decision/provenance record. Use for mutual, one-way, employee-context or vendor-context NDA drafting. Trigger with "nda-generator" or "create an NDA".LegalNo warnings★ 2.9K↓ —
- 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↓ —
- 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★ 98.9K↓ —
- skill-content-repurposingZJU-REAL/Easel将一篇内容拆解改编到小红书、抖音、B站、微博等多平台，适配各平台原生格式和风格。 当用户说"一稿多发""改编到各平台""内容复用""多平台适配""这篇改成小红书/抖音""转成其他平台""一鱼多吃"时使用。 和 skill-cross-platform-diff 的区别：diff 做平台差异洞察分析（发现层）；本 SKILL 实际改写内容到各平台。 和 skill-cross-platform-publish 的区别：本 SKILL 只改写适配内容，cross-platform-publish 负责实际一键分发到多平台。OtherNo warnings★ 4.3K↓ —
- groq-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Groq costs through model routing, token management, and usage monitoring. Use when analyzing Groq billing, reducing API costs, or implementing usage monitoring and budget alerts. Trigger with phrases like "groq cost", "groq billing", "reduce groq costs", "groq pricing", "groq expensive", "groq budget".EngineeringNo warnings★ 2.9K↓ —
- unslopbacknotprop/pstackCut AI tells from any writing.WritingNo warnings★ 3.3K↓ —Also in 1 other repo
- release-checkdavepoon/buildwithclaudePre-release verification checklist. Validates features, tests, docs, security, and quality gates before shipping. Delegates to the Centinela (QA) agent.SecurityNo warnings★ 3.7K↓ —
- skill-hook-generatorZJU-REAL/Easel针对任意主题生成多种 Hook（开头钩子）变体，用经过验证的互动公式抓住开头注意力，附字数校验。 当用户说"写钩子""开头怎么写""Hook""抓眼球的开头""标题钩子""前三秒""怎么开头"时使用。 本 SKILL 专攻可复用的开头钩子变体；成篇营销文案用 copywriting，视频分秒脚本用 video-script。MediaNo warnings★ 4.3K↓ —
- gsd:milestone-summarydavepoon/buildwithclaudeGenerate a comprehensive project summary from milestone artifacts for team onboarding and reviewProductivityNo warnings★ 3.7K↓ —
- clerk-orgsclerk/skillsClerk Organizations for B2B and multi-tenant apps - org switching, roles and permissions, verified domains, and enterprise SSO. Use for team workspaces, RBAC, org-scoped routing, member management. Also load this when a project treats teams, workspaces, tenants, or companies as its customers - shared accounts, inviting teammates, per-seat pricing, per-company data isolation - even when the words "organization" or "B2B" are never used.OfficialOtherNo warnings★ 89↓ —
- twitter-automationdavepoon/buildwithclaudeAutomate Twitter/X tasks via Rube MCP (Composio): posts, search, users, bookmarks, lists, media. Always search tools first for current schemas.ProductivityNo warnings★ 3.7K↓ —
tao-run-inference-service
NVIDIA/skills
DevOpsUpdated 2 days ago
From the author
Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container image resolution, job-payload JSON construction, and the service registry. Use when the user wants to run inference on a TAO model checkpoint using a microservice container, deploy a TAO inference endpoint, or stop a running inference container.
Install
npx skills add NVIDIA/skills --skill tao-run-inference-service -a claude-code
Installs to .claude/skills/tao-run-inference-service/ · 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 onlyUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance83
Maintenance100
Licence100
Adoption57
Files (12)
- BENCHMARK.md
- SKILL.md
- config/skillspector-baseline.yaml
- evals/evals.json
- references/code-templates.yaml
- references/cosmos-predict2.5.config.json
- references/request.yaml
- references/service.yaml
- references/skill_info.yaml
- references/tao-dataservices.config.json
- skill-card.md
- skill.oms.sig