Search
Education · For developers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time. | THU-MAIC/ | 40k | — | ~1.7k | Automated safety check: Notes | MIT | today |
| 2 | Adversarial code review using cross-model approach. An agent skill from mengxi-ream/read-frog. | mengxi-ream/ | 10k | 1 repo | ~905 | Automated safety check: Pass | GPL-3.0 | today |
| 3 | Record polished, evidence-backed demos of the Read Frog extension as MP4 (and optional GIF) by driving real Chrome with the built extension, following captioned scene scripts, asserting extension… | mengxi-ream/ | 10k | — | ~2.8k | Automated safety check: Pass | GPL-3.0 | today |
| 4 | Quizzes you on Claude Code in a quick or deep mode, scores your level across 10 topics and recommends what to learn next, in Chinese. | lhfer/ | 2.3k | — | ~1.7k | Automated safety check: Pass | MIT | 2 mo ago |
| 5 | Converts PDFs, text, web pages or a codebase into an Obsidian vault of study notes, practice questions, or a developer onboarding guide. | bevibing/ | 1.3k | — | ~1.9k | Automated safety check: Notes | MIT | 7 mo ago |
| 6 | Runs a quick or deep quiz on Claude Code skills, scores ten feature areas and generates a personalized learning path with prioritized next steps. | luongnv89/ | 42k | — | ~5.6k | Automated safety check: Pass | MIT | today |
| 7 | Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout… | Human-Agent-Society/ | 1.1k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 8 | Turns a GitHub course repository into an interactive tutor for the MCP Associate certification, making the learner explain and defend each step. | rohitg00/ | 67k | — | ~3.5k | Automated safety check: Pass | MIT | today |
| 9 | Walks the sfdx-hardis training course end to end as a learner would, against a real Developer Edition org and fork, fixing broken steps and screenshots that no longer match. | hardisgroupcom/ | 404 | — | ~2.6k | Automated safety check: Notes | AGPL-3.0 | today |
| 10 | 10.Auto Improve GAN-style iterative improvement loop for any text artifact. An agent skill from crimeacs/auto-improve. | crimeacs/ | 135 | — | ~651 | Automated safety check: Pass | MIT | 2 mo ago |
| 11 | A Chinese-language tutorial on advanced Claude Code use: its core tools, REPL, slash commands, workflows, permissions, memory, MCP, hooks and sub-agents. | 2025Emma/ | 23k | 1 repo | ~1.4k | Automated safety check: Pass | MIT | 9 mo ago |
| 12 | 12.Pre Push A skill your agent uses when the user asks to check before pushing, pre-push, verificar antes de pushear, run all checks, or quiere validar que todo pasa antes de hacer push. | artcc/ | 165 | — | ~732 | Automated safety check: Pass | AGPL-3.0 | today |
| 13 | Review a specific vscode-containers pull request on demand from the CLI (or any interactive agent), the way a Container Tools maintainer would. | microsoft/ | 141 | — | ~900 | Automated safety check: Pass | Unknown | 3 days ago |
| 14 | 14.Nlm Skill Expert guide for the NotebookLM CLI (nlm) and MCP server - interfaces for Google NotebookLM. | iusztinpaul/ | 179 | 1 repo | ~6.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 15 | Publication-figure overlay for draw.io. An agent skill from bahayonghang/drawio-skills. | bahayonghang/ | 287 | — | ~3.2k | Automated safety check: Notes | MIT | 1 mo ago |
| 16 | 16.Run Tests A skill your agent uses when the user asks to run tests, ejecutar tests, lanzar tests, pytest, vitest, check types, typecheck, lint, or verify the codebase. | artcc/ | 165 | — | ~976 | Automated safety check: Pass | AGPL-3.0 | today |
| 17 | 学习笔记自动化:视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词:学习笔记、闪卡、Anki、知识提取、视频学习 | chubbyguan/ | 1.2k | — | ~898 | Automated safety check: Pass | MIT | 3 days ago |
| 18 | Interactive tutorial where the agent teaches Medusa development by guiding you through building a brands feature, with lessons and verification checkpoints. | medusajs/ | 228 | — | ~4.1k | Automated safety check: Pass | No licence | 6 days ago |
| 19 | 19.Darwin Skill Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch. | HHU3637kr/ | 145 | 1 repo | ~2.2k | Automated safety check: Pass | No licence | 18 days ago |
| 20 | Implement a feature from an existing design doc. An agent skill from janekbaraniewski/openusage. | janekbaraniewski/ | 221 | — | ~2k | Automated safety check: Pass | MIT | today |
| 21 | A skill your agent uses for repository documentation lifecycle and consolidation. | wengan-li/ | 151 | — | ~3.1k | Automated safety check: Pass | Unknown | 8 days ago |
| 22 | 22.Interview Use BEFORE roadmap or specify to get the idea OUT OF YOUR HEAD and onto disk — a Socratic interview that surfaces hidden assumptions, names tradeoffs, exposes imprecisions and proposes fresh angles… | genkovich/ | 171 | — | ~3.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 23 | 23.Course Guide AI Engineering from Scratch 课程的主题路由器。给它一个主题、问题或正在处理的 bug, 它会指出精确教授它的课程,以及下一条正确命令。触发短语: “在哪里学习”、“哪节课涵盖”、“课程导航”、“我卡在”、“接下来该做什么”、 “教我 MCP”、“教我 Agent Skills”、“在哪里准备 Claude certification”,或 "where do I… | fancyboi999/ | 1.2k | — | ~948 | Automated safety check: Pass | MIT | 2 days ago |
| 24 | Interactive tutor that teaches one lesson per invocation on creating, discovering, invoking, securing, evaluating, packaging and porting Agent Skills, logging progress to a file. | rohitg00/ | 67k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 25 | 25.Self Review Review your own verl-omni branch against the project rubric before opening or updating a PR. | verl-project/ | 1.2k | — | ~2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 26 | Review a design doc against the actual codebase, find inconsistencies, and quiz the user on needed fixes. | janekbaraniewski/ | 221 | — | ~892 | Automated safety check: Pass | MIT | today |
| 27 | 27.Deep Dive A Codex skill for Socratic interviews that deepen a spec or refine an existing agent blueprint. | byungjunjang/ | 120 | — | ~2.7k | Automated safety check: Pass | No licence | 2 mo ago |
| 28 | An interactive tutor for the Model Context Protocol path in AI Engineering from Scratch, teaching one lesson per invocation and recording wire evidence in MCP-LEARNING.md. | rohitg00/ | 67k | — | ~2.4k | Automated safety check: Pass | MIT | today |
| 29 | 29.Review Review code changes and return prioritized, actionable findings | 0xku/ | 354 | — | ~958 | Automated safety check: Pass | MIT | 8 days ago |
| 30 | 只讀審閱 Pi 藍皮書畢業專案的需求覆蓋、修改範圍、導航連接和驗收證據;用於實現完成後的獨立複核. An agent skill from xiaomoBoy/pi-bluebook. | xiaomoBoy/ | 308 | — | ~137 | Automated safety check: Pass | MIT | 9 days ago |
| 31 | An entry-level software engineering interviewer specializing in binary tree data structures. | PrepLabsAI/ | 112 | — | ~2.4k | Automated safety check: Pass | MIT | 4 days ago |
| 32 | Create custom external web service APIs for Moodle LMS. An agent skill from davila7/claude-code-templates. | davila7/ | 33k | 7 repos | ~4.6k | Automated safety check: Pass | MIT | today |
| 33 | Review Arm install guides for structural soundness, installation-only scope, verification quality, OS-specific sections, troubleshooting, multi-page guide behavior, and version-note placement. | ArmDeveloperEcosystem/ | 154 | — | ~780 | Automated safety check: Pass | Unknown | yesterday |
| 34 | Teaches the lo2cin4bt backtesting product from the repository's own docs and code, in the learner's language, ending each answer with one next step. | lo2cin4/ | 289 | — | ~1.8k | Automated safety check: Pass | Unknown | 2 mo ago |
| 35 | Review rubric for the /review pull-request command. An agent skill from NVIDIA/Megatron-LM. | NVIDIA/ | 18k | — | ~839 | Automated safety check: Pass | Apache-2.0 | today |
| 36 | Scaffolds eval.yaml evaluation specs for skills, custom agents, and redistributable gh-aw workflow packages in the dotnet/skills repository. | dotnet/ | 5.6k | 1 repo | ~6.1k | Automated safety check: Pass | MIT | yesterday |
| 37 | 37.Skip To Skip ahead to a specific chapter in Learn Docker & K8s, with a knowledge quiz for skipped chapters. | ericboy0224/ | 491 | — | ~482 | Automated safety check: Pass | No licence | 6 mo ago |
| 38 | Offers short, optional learning exercises after architectural work so you understand AI-written code instead of just accepting it. | tech-leads-club/ | 7k | — | ~1.3k | Automated safety check: Pass | CC-BY-4.0 | 2 days ago |
| 39 | 39.Eval Loop This skill should be used when a specific quality problem (UX, data, architecture, feature) needs systematic diagnosis and iterative fixing toward a defined target. | jacob-dietle/ | 111 | — | ~5.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 40 | AI Engineering from Scratch 课程的一次性入门流程(523 节课、20 个阶段)。访谈学习者、 运行分级测验,并写入由 learn skill 驱动的持久学习计划 LEARNING.md。触发短语: “开始学习”、“设置课程”、“开始课程”、“带我入门”、“创建学习计划”,或 "start learning", "set up the course", "begin… | fancyboi999/ | 1.2k | — | ~1.1k | Automated safety check: Pass | MIT | 2 days ago |
| 41 | Asks the user mid-run from inside an FSM action or Python type: user agent via the elicitation tools — requesttoolaccess for allowlist approvals and requesthumaninput for HITL (human-in-the-loop)… | friday-platform/ | 104 | — | ~2.4k | Automated safety check: Pass | Unknown | 1 mo ago |
| 42 | Interactive training for the GitHub Copilot CLI. An agent skill from github/awesome-copilot. | github/ | 40k | 2 repos | ~517 | Automated safety check: Pass | MIT | 2 days ago |
| 43 | 43.Interview Socratic interview to crystallize vague requirements. An agent skill from Q00/ouroboros. | Q00/ | 6.2k | — | ~13k | Automated safety check: Pass | MIT | 4 days ago |
| 44 | Generate an MP3 pronunciation of a glossary term using ElevenLabs TTS API and insert a "Pronounce" button into the term's entry in a markdown file. | dmccreary/ | 105 | — | ~1.9k | Automated safety check: Pass | No licence | yesterday |
| 45 | Copilot left 14 review comments on your PR — half are nits. An agent skill from github/awesome-copilot. | github/ | 40k | — | ~3.4k | Automated safety check: Pass | MIT | 2 days ago |
| 46 | LLM-as-a-judge rubric for code comments (forbidden, false, stale, narration, noise, keep). | fmflurry/ | 171 | — | ~2.5k | Automated safety check: Pass | MIT | 4 days ago |
| 47 | 47.Woo AI Smoke Evaluate WooAIAssistant against a structured scenario suite with hard invariants + LLM-as-judge rubric scoring. | woocommerce/ | 358 | — | ~7.4k | Automated safety check: Notes | GPL-2.0 | yesterday |
| 48 | A skill your agent uses when someone wants public Shopify App Store reviews, low-star reviews, or merchant feedback triaged, prioritized, clustered, or turned into a product or support brief. | github/ | 40k | — | ~4.2k | Automated safety check: Pass | MIT | 2 days ago |