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.
46,100 skills from 2,198 repositories · updated 8 hours ago
9,541 skills
- source-command-assess-railwaylegioncodeinc/vibe-coding-toolsAssess Railway workload fit with dated service, operating, recovery and cost constraints.OtherNo warnings★ 94↓ —
- source-command-explain-repositorylegioncodeinc/vibe-coding-toolsExplain how a supplied repository works using source evidence, an eighth-grade reading level, and bounded analogies.OtherNo warnings★ 94↓ —
- source-command-build-integrationlegioncodeinc/vibe-coding-toolsBuild a scoped provider integration with explicit authorization, sync, retry, rate-limit and revocation contracts.OtherNo warnings★ 94↓ —
- knowledge-base-help-center-stingerlegioncodeinc/vibe-coding-toolsSelect and improve customer help centers. Use for KB platforms, search, AI deflection, localization, versioning, or content gaps. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- autopilotnelsonwerd/idea-to-ship-skillsRun the idea-to-ship pipeline AUTONOMOUSLY, in character as a grounded founder-persona — composing ideate → deep-dive → prompt-pack → build-loop to take a real, grounded niche to a near-finish-line-AIMED first-draft product plus an honest ledger of what only a human or the market can finish. ALWAYS invoke when the user says any of "run autopilot", "build this idea→ship autonomously", "spin up a grounded founder and build it", "fly the whole pipeline end to end", or "autonomous first-draft from a concept". It composes the existing skills, never reimplementing them, and states its honest bounds — a near-finish-line first draft, NOT a finished or market-validated product (~80% craft ceiling; grounding firewall; its go/kill calls are a signal). Do NOT use to drive each phase by hand (use the skills directly), when there's no real grounding (you'd be inventing demand), or when you need market validation (the human handoff).OtherNo warnings★ 90↓ —
- do-customsopenaccountants/openaccountantsDominican Republic Customs (Aduanas) — accountant-verified rules from the DGII validation matrix (Miguel Lantigua, CPA Lic. 17839).OtherNo warnings★ 463↓ —
- framer-motionAThevon/genjutsuFramer Motion / Motion sub-skill - AnimatePresence, layout animations, gestures, motion values.OtherNo warnings★ 701↓ —
- source-command-estimate-buildlegioncodeinc/vibe-coding-toolsForecast one person's AI-assisted software project at N hours daily, with learning, verification, external waits and separate cash/time scenarios.OtherNo warnings★ 94↓ —
- tw-nhiopenaccountants/openaccountantsUse this skill whenever asked about Taiwan National Health Insurance (NHI) contributions. Trigger on phrases like "NHI Taiwan", "健保", "全民健康保險", "健保費", "supplementary premium", "補充保費", "NHI self-employed", "health insurance Taiwan", "NHIA", "衛生福利部中央健康保險署", or any question about computing, paying, or understanding NHI premiums for self-employed individuals in Taiwan. This skill covers the general premium rate, supplementary premium, insured payroll categories, and payment obligations. ALWAYS read this skill before advising on Taiwan NHI.OtherNo warnings★ 463↓ —
- nginx-ops0xDarkMatter/claude-modsNginx configuration, reverse proxy, SSL/TLS, load balancing, and performance tuning. Use for: nginx, reverse proxy, load balancer, proxy_pass, ssl certificate, lets encrypt, web server, location block, upstream, server block, nginx config, certbot, hsts, gzip, rate limiting.OtherNo warnings★ 78↓ —
- source-command-build-nuxt-applegioncodeinc/vibe-coding-toolsBuild or extend a Nuxt app using current Nuxt routing, SSR, Nitro, data and cache boundaries with explicit verification.OtherNo warnings★ 94↓ —
- paypal-integrationaisa-group/skill-injectIntegrate PayPal payment processing with support for express checkout, subscriptions, and refund management. Use when implementing PayPal payments, processing online transactions, or building e-commerce checkout flows.OtherNo warnings★ 101↓ —
- hugging-face-dataset-creatoraisa-group/skill-injectCreate and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.OtherNo warnings★ 101↓ —Also in 1 other repo
- rag-implementationaisa-group/skill-injectBuild Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.OtherNo warnings★ 101↓ —
- finetuning-techniqueawslabs/agent-pluginsSelects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Use when the user has decided to finetune and needs to choose a technique, or when the technique needs to be validated against a model. Requires a base model to already be selected (via model-selection skill).OtherNo warnings★ 932↓ —
- wikimoonlight-lupin/agent-skillsKarpathy's LLM Wiki: build/query interlinked markdown KB. Use when creating, ingesting into, querying, or linting a markdown wiki.OtherNo warnings★ 113↓ —
- news-monitoringmoonlight-lupin/agent-skillsUse when a topic or news stream needs recurring monitoring — cover it with web search, multi-language sources, digest formatting, and automated delivery via Hermes cron jobs. Covers search strategy, source selection, Chinese-language platforms, and digest templates.OtherNo warnings★ 113↓ —
- my-skill-namesendaifun/skillsA clear description of what this skill does and when to use itOtherNo warnings★ 130↓ —
- cron-managercountbot-ai/CountBot定时任务管理。创建、查看、修改、删除定时任务，管理任务会话数据。当用户需要设置提醒、定时执行任务、管理调度计划时使用。OtherNo warnings★ 783↓ —
- assessing-release-readinessjaktestowac/awesome-copilot-for-testersProduces an evidence-backed go/no-go recommendation: exit criteria status, open-defect risk profile, coverage against risk, environment parity, rollback readiness, and the residual risk stated plainly. Use when preparing a release sign-off, when someone asks whether a build is ready to ship, or when a decision to release is being made on impressions rather than evidence.OtherNo warnings★ 118↓ —Also in 1 other repo
- backup-recoveryBagelHole/DevOps-Security-Agent-SkillsImplement backup and recovery strategies. Configure rsync, Restic, and cloud backups. Use when designing data protection solutions.OtherNo warnings★ 1.2K↓ —
- source-command-choose-backendlegioncodeinc/vibe-coding-toolsRecommend one backend language/runtime from workload, integration, operations and actual implementation coverage.OtherNo warnings★ 94↓ —
- incorporation-startup-stack-stingerlegioncodeinc/vibe-coding-toolsSet up a software company. Use for entity choice, Atlas vs Clerky, EIN, banking, bookkeeping, or founder paperwork. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- CTF•逆向工程asdfgh1445/ctf-super-hub用于二进制、APK、WASM、固件、自定义虚拟机、字节码、游戏客户端、类恶意加载器以及反调试/反分析逻辑等逆向类 CTF 题;触发名:ctf-reverseOtherNo warnings★ 840↓ —
论文手
XiaoMaColtAI/math-modeling-skill
OtherUpdated yesterday
From the author
根据题目、建模分析和真实代码结果生成完整 Word 数学建模论文，用户显式要求时同时生成 LaTeX 论文。
Install
npx skills add XiaoMaColtAI/math-modeling-skill --skill '论文手' -a claude-code
Installs to .claude/skills/---/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (No licence) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyNo network use seenLicence: no licence
Safety checks on SKILL.md
No warnings.
Why 81
Security100
Provenance79
Maintenance100
Licence25
Adoption53
Files (9)
- SKILL.md
- references/LaTeX格式规范.md
- references/写作规范.md
- references/工作流程.md
- references/章节模板.md
- references/自审框架.md
- references/英文化工作流.md
- references/论文格式规范.md
- references/论文模板.docx