Learn & study
4,785 rows, by stacks then stars
598 of these skill files have been read, by 545 distinct authors, and what they tell an agent counted. What Learn & study authors agree on, and what they forbid
Ghosteken/agent-harness/archive/skills-community/obsidian-bases Skill
1★ repoCreate and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/obsidian-cli Skill
1★ repoUse the Obsidian CLI to read, create, search, and manage vault content, or to develop and debug Obsidian plugins and themes from the command line.
The same file is in 5 other repositories
Obsidian clipper template creator
Ghosteken/agent-harness/archive/skills-community/obsidian-clipper-template-creator Skill
1★ repoGuide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/obsidian-markdown Skill
1★ repoCreate and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/sred-work-summary Skill
1★ repoGo back through the previous year of work and create a Notion doc that groups relevant links into projects that can then be documented as SRED projects.
The same file is in 4 other repositories
Team collaboration standup notes
Ghosteken/agent-harness/archive/skills-community/team-collaboration-standup-notes Skill
1★ repoYou are an expert team communication specialist focused on async-first standup practices, AI-assisted note generation from commit history, and effective remote team coordination patterns.
The same file is in 3 other repositories
Ghosteken/agent-harness/archive/skills-community/youtube-summarizer Skill
1★ repoExtract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks
The same file is in 4 other repositories
AlexStormwood/agentic-skills/conventional-commit-summary Skill
1★ repoGenerate concise one-line Conventional Commit summaries for work completed by an AI agent. Use when Codex needs to summarise code changes, file edits, documentation updates, tests, refactors, fixes, generated assets, breaking changes, or other repository work as a brief git commit message with type, optional scope, optional breaking-change marker, and no extended description.
Teddy563/mcwrench/skills/learn-plugin-docs Skill
1★ repoFetches and condenses the documentation for ANY Minecraft plugin or mod on demand into a local markdown reference. Use this skill whenever the user asks "how do I configure X", "what does X do", "where are X's docs", "set up X", "what are X's permission nodes/commands/config keys", or names any plugin you do not already have a confident, current reference for, even if they did not explicitly ask you to read docs. Knows the cheap channel per host: Modrinth and Hangar REST APIs, the GitBook .md-suffix trick plus llms.txt/llms-full.txt, raw GitHub READMEs and wikis, Skript Hub's syntax API, the SpigotMC JSON API, and a Readability fallback for unknown hosts. Writes a condensed REFERENCE.md under skills/_cache/[slug]/ and tells you to read that instead of re-fetching. Use before answering any uncertain plugin-specific question; do not guess keys.
shangjunyang1986/ai-learning-skills/skills/learn Skill
1★ repoThe front door to the ai-learning-skills family — mainly a ROUTER: given anything the user wants to learn — a GitHub repo/org URL, an arXiv link / paper / PDF, a technical book, or a bare topic/field — detect the source type and hand off to the right family skill (github-project-learn / paper-learn / textbook-learn / domain-learn), asking one quick question when it's ambiguous. Use this when the user types /learn, says "我想学这个 / 帮我 学习…" without it being obvious which skill fits, or asks to learn something but isn't sure how. If the input ALREADY clearly matches one specific family skill (a plain GitHub URL, a clear arXiv link, a named textbook, a bare field name), that skill can trigger directly — this router is for the unified entry point and ambiguous inputs. It ALSO has an OPTIONAL secondary capability — a library hub that aggregates all the learning pages you've generated into one offline index — worth building only once you've accumulated many pages; trigger it only on an explicit "建/打开我的学习库 / build my learning hub / 把我做的学习页汇总". Not for: generic web apps or answering a one-off question.
shangjunyang1986/ai-learning-skills/skills/paper-learn Skill
1★ repoTurn a single research paper (an arXiv link / PDF / paper title) into an offline, visual PAPER-READING page — a self-contained HTML file with a left table of contents that walks the paper the way you should read it: problem & motivation → the method broken down FIGURE BY FIGURE with the paper's own diagrams downloaded locally and key equations rendered offline → a step-by-step worked example of the core mechanism → an honest interactive demo of that mechanism → results → how to reproduce / read the code → and a CRITICAL-READING pass that separates what the paper actually demonstrated from what it only hypothesized. Use this whenever the user wants to UNDERSTAND, READ, or "精读" a specific PAPER — e.g. "帮我精读 Attention Is All You Need / 把这篇 arXiv 讲明白 / explain this paper / 这篇论文靠不靠谱、能不能落地 / make me a study page for arxiv.org/abs/XXXX". Triggers on an arXiv URL or a paper title/PDF + intent to understand/evaluate it. Distinguish from siblings: a GitHub repo URL → github-project-learn; a whole book/PDF textbook → textbook-learn; a bare topic/field → domain-learn; ONE paper → THIS skill. Not for: answering a single factual question about a paper (just answer it), or building generic web apps.
shangjunyang1986/ai-learning-skills/skills/textbook-learn Skill
1★ repoTurn a technical book or PDF into an offline, visual learning page that teaches it as a COURSE — a single self-contained HTML file with a left table of contents, a whole-book chapter map / reading path, a few chapters broken down deeply (core ideas + the book's own figures downloaded locally + a step-by-step worked example), and per-chapter ACTIVE-RECALL QUIZZES plus a progress tracker that remembers what you've read and how you scored. Use this whenever the user wants to LEARN, STUDY, or "从入门到掌握" a specific BOOK or PDF/EPUB — e.g. "帮我学《动手学深度学习》/ 把这本 PDF 做成逐章学习页 + 测验 / I want to work through SICP / make me a study guide for this textbook / 给这本书做个带测验的学习网页". Triggers on a book title or a PDF/EPUB file/link + intent to learn/work through it. Distinguish from siblings: a GitHub repo URL → use github-project-learn; a bare topic/field like "学习 3DGS" → use domain-learn; a specific BOOK or PDF → THIS skill. Not for: answering one factual question from a book (just answer it), or building generic web apps.
loursCreatif/ours-stack/dense-read Skill
1★ repoGuided wedge-locked reading — slice-by-slice session: explain in plain French, ONE question per tranche, user responds (3–6 tranches). Writes notes.md as session trace (user answers included). Escape hatch "lis tout seul" = solo Feynman extraction. Triggers: dense read, lire en profondeur, extraction Feynman, /dense-read. After /source-scout or /bear-hours; before /mind-map.
loursCreatif/ours-stack/study-status Skill
1★ repoRead-only study dashboard — where each study stands (criteria checked, artifacts produced, suggested next step). Scans studies/*/brief.md in the current repo; optionally includes ~/.ours-stack/studies-index.jsonl for cross-repo studies. Use when the user asks "study status", "où j'en suis", "statut de mes études", "tableau de bord", "what's next", "what should I do next" (status view, not strategy debate), or runs /study-status. Never creates or modifies files.
Da-loong/agent-skill-os/skills/pr-summarizer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete pr summarizer work with a reliable workflow.
Da-loong/agent-skill-os/skills/release-notes-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete release notes writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/source-summarizer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete source summarizer work with a reliable workflow.
vasu-devs/Forge/skills/learn Skill
1★ repoDistill durable "instincts" (trigger → action patterns) from this session into project-scoped memory that auto-loads at the start of future sessions in this repo. Use when the user asks you to learn or remember a workflow pattern, after solving something non-obvious worth not re-deriving, at the end of a productive session, or when invoked directly.
nyechiel/ai-augmented-workflow/skills/learn Skill
1★ repoAnalyze user corrections from the conversation, extract generalizable rules, and persist them. Use after receiving corrections or at session end.
nyechiel/ai-augmented-workflow/skills/meeting-prep Skill
1★ repoGenerate a pre-meeting brief with context discovery, commitment tracking, and talking points.
Lightbridge-KS/agent-skills/plugins/coding/skills/explain-as-notebook Skill
1★ repoDecompose a piece of an existing codebase — a function, method, class, or module — into a runnable notebook that explains it top-down: a call-graph map, then each piece defined and executed on concrete mock inputs with its real output shown inline. Turns code you didn't write (or have forgotten) into an interactive, line-by-line walkthrough. Use this skill only when the user explicitly invokes it by name (`explain-as-notebook`) or near-match mentioning.
Lightbridge-KS/agent-skills/plugins/coding/skills/explain-data-architecture Skill
1★ repoReverse-engineer and document the data architecture of an existing or cloned codebase — where data rests (stores, schema) and how it moves (dataflow, lineage). Use this skill only when the user explicitly invokes it by name (`explain-data-architecture`) or near-match mentioning.
Lightbridge-KS/agent-skills/plugins/coding/skills/explain-system-architecture Skill
1★ repoReverse-engineer and document the architecture of an existing or cloned codebase. Use this skill only when the user explicitly invokes it by name (`explain-system-architecture`) or near-match mentioning.
Lightbridge-KS/agent-skills/plugins/coding/skills/explain-ux-dx-design Skill
1★ repoReverse-engineer and document the user-facing API and UX/DX of an existing or cloned codebase — the system as seen from outside the boundary, whether the "user" is an end user or a developer. Use this skill only when the user explicitly invokes it by name (`explain-ux-dx-design`) or near-match mentioning.
Juliejue/claude-longform-reading-skills/crypto-longform-reading-coach Skill
1★ repoWeb3 社会学精读教练。Use when the user asks to deeply read crypto, Web3, DAO, protocol, ownership economy, decentralized governance, public goods, token mechanism, network state, or blockchain longform essays. Must ignore price/K-line/investment noise, analyze social experiments, incentives, coordination, political philosophy, and provide deep Chinese substitute reading with batching and actionable mechanism-design guidance.
celestialdust/achilles-skills/skills/comprehension-quiz Skill
1★ repoAgent-administered retrieval practice that makes understanding of code you did not write honest — about five medium-difficulty questions asked ONE at a time, the learner's answer graded BEFORE the correct answer is revealed, the session recorded as one line in the learning ledger. Reach for this right after a literate-explainer artifact (quiz that explainer) or standalone with no fresh explainer in view (the requiz over weak or stale durable concepts drawn from the ledger). It is the SOLE writer of the learning ledger; it is an honest self-check, never a gate — it blocks nothing. If you are about to dump every question at once, reveal an answer before grading it, or write a quiz's questions or answers into any file the learner can open, stop and load this.
celestialdust/achilles-skills/skills/literate-explainer Skill
1★ repoTurn a diff (the daily case) or a whole unfamiliar target repo (onboarding) into a self-contained teaching artifact so you stay a participant in code you didn't write — background before the change, intuition before details, a literate tour in reading order, plain enough to re-teach (the Feynman test). Reach for this whenever an agent just landed a large diff you cannot yet explain, when you clone or inherit an unfamiliar repo and a skim will not build a mental model, or when someone says "explain this diff/PR/branch/codebase", "walk me through what changed", or "help me understand this code". Standalone — no lifecycle gates, nothing blocks, /orchestrate untouched. Pairs with comprehension-quiz — suggest running /quiz next. NOT code-review (which judges a diff for merge) and NOT codebase-research (a goal-blind survey feeding the plan).
spacemata/codex-plugins-for-claude-code/plugins/financial-markets/skills/meeting-prep Skill
1★ repoUse when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.
jassonbla/skills/skills/slide-board-design Skill
1★ repoCore design system for building horizontal infographic "explainer boards" used to explain concepts to a team. Use when the user asks to create an explainer slide/board/infographic/presentation slide, or a single-canvas picture that explains a concept, strategy, or flow across left-to-right panels, and when producing that style in Figma or as code (React/HTML). Defines color, font, spacing, and component tokens plus the production workflow.
Kisslotina/Steward/.claude/skills/sort-inbox Skill
1★ repoClassifies and files raw Inbox records into the EXISTING typed Notion bases, applies completion notes that close existing items, and enqueues outbound work to the Outbox. Use after capturing notes, or whenever the user asks to sort/process the Inbox. Invoked by roll-day after its sweep phase, or run standalone over the Inbox. Reads Inbox rows with Status=New, decides new-vs-completion, routes to a real base, sets Status=Sorted and Target, then moves filed rows to Inbox Archive.
dimsedra/moatcraft-skills/.agents/skills/explain-and-teach Skill
1★ repoProvide adaptive, high-level systemic explanations of technical decisions, architecture trade-offs, and design rationale. Use ONLY when the user explicitly asks "why", requests an explanation of a choice, or wants to understand a trade-off or mental model. Do NOT use unprompted — this skill responds to questions, it does not lecture.
IvanGomezMartinez/MatStudyLab/.agents/skills/explain Skill
1★ repoDeep-study a MATLAB script and write explain_<stem>.md without changing .m files.
IvanGomezMartinez/MatStudyLab/.agents/skills/teach Skill
1★ repoTeach the user a new skill or concept, within this workspace.
The same file is in 14 other repositories
leoncuhk/defog/skills/fog-quiz Skill
1★ repoGenerate a merge-gate quiz from the ledger, cross-checked against the diff — questions target what was actually uncertain.
yigityildiz0/universal-ai-skill-library/skills/common/explainer-graphic Skill
no license1★ repoCreate visual infographics using real-world analogies
yigityildiz0/universal-ai-skill-library/skills/common/learn Skill
no license1★ repoUse this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's.
yigityildiz0/universal-ai-skill-library/skills/common/learning-path-generator Skill
no license1★ repoCreate a structured learning plan for any skill or topic. Use this skill when the user says "learn", "how do I learn", "learning path", "study plan", "teach.
yigityildiz0/universal-ai-skill-library/skills/common/meeting-prep Skill
no license1★ repoResearches meeting attendees and their companies before any meeting using real-time web data. Surfaces roles, recent activity, company context, and talking.
yigityildiz0/universal-ai-skill-library/skills/common/notion-knowledge-capture Skill
no license1★ repoCapture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper.
yigityildiz0/universal-ai-skill-library/skills/common/notion-meeting-intelligence Skill
no license1★ repoPrepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.
The same file is in 9 other repositories
yigityildiz0/universal-ai-skill-library/skills/common/notion-research-documentation Skill
no license1★ repoResearch across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or.
yigityildiz0/universal-ai-skill-library/skills/common/notion-spec-to-implementation Skill
no license1★ repoTurn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.
The same file is in 4 other repositories
yigityildiz0/universal-ai-skill-library/skills/common/notion-template-processor Skill
no license1★ repoNotion-structure skill. Use when Codex should transform raw notes or recurring content into Notion-ready templates, blocks, or database-friendly layouts.
yigityildiz0/universal-ai-skill-library/skills/common/release-notes-writer Skill
no license1★ repoGenerates professional release notes from git history, pull requests, and issues with conventional commit parsing and audience-specific formatting. Use when.
M0rtalPhe0nix/dotfiles/.agents/skills/teach Skill
1★ repoTeach the user a new skill or concept, within this workspace.
The same file is in 14 other repositories
XHdW/owner-mode/platforms/claude/skills/owner-first-principles Skill
1★ repoFirst-principles reasoning: use when the user invokes $owner-first-principles or asks to reason from first principles; when a problem or direction is being treated as inseparable from an inherited solution, convention, abstraction, or assumption; or when repeated local optimization leaves the same failure intact. For implicit invocation, require that revisiting the foundation could materially change the problem shape or admissible solution space.
XHdW/owner-mode/skills/owner-first-principles Skill
1★ repoFirst-principles reasoning: use when the user invokes $owner-first-principles or asks to reason from first principles; when a problem or direction is being treated as inseparable from an inherited solution, convention, abstraction, or assumption; or when repeated local optimization leaves the same failure intact. For implicit invocation, require that revisiting the foundation could materially change the problem shape or admissible solution space.
JunfengRan/dev-env/skills/interpret-tech-notes Skill
1★ repo将论文、博客、前沿应用技术解读为 dev-env 知识库笔记(Markdown 或 HTML)。 触发:用户要求解读/精读/摘录论文、博客、开源 Agent 项目或应用技术; 写到 docs/knowledge/;或提到「写笔记」「技术深挖」「学习手册」「会话整合」。
ssdiwu/507-skills/common/507-explain Skill
1★ repo概念解释:把用户不理解的一个概念、术语、技术名词或相近概念差异讲清楚。先给最短白话定义,再按用户已知切换比喻、例子、反例与对比;当顺序、状态、层级或多方关系不易用纯文字理解时,优先选用表格、流程图、Mermaid 或 ASCII 示意。默认不落盘,不负责定位项目未知。Use when user mentions X 是什么意思, 这个概念是什么, 帮我理解一下, 用大白话讲讲, 我不懂这个词, 解释一下这个术语, X 和 Y 有什么区别, explain concept, explain in plain words, what is X, ELI5, break down a concept.
whatsuppiyush/god-of-skills/engineering/changelog-writer Skill
1★ repoTurn merged pull requests since the last release tag into a human changelog grouped by Added / Fixed / Changed / Removed, written in user-facing language, not commit-speak. Use whenever the user says "write the changelog", "release notes", "what changed since last release", "generate CHANGELOG", "notes for this version", or is about to cut a release and needs notes. Reach for it right after a version bump, before publishing a release on GitHub, or when a maintainer wants to tell users what is new without hand-reading 40 PR titles. Produces a ready CHANGELOG.md section with a one-line summary on top.
whatsuppiyush/god-of-skills/operations/founder-crm-notion Skill
1★ repoA ready Notion CRM wired for AI enrichment, drop a name, the linked prompt fills the row.
whatsuppiyush/god-of-skills/operations/meeting-notes-to-actions Skill
1★ repoPaste a transcript, get owners, decisions, and dated action items, nothing invented.
Chevis-Zhou/agent-skills/skills/messy-notes-organizer Skill
1★ repoProcess raw, unstructured "brain dumps" (notes, ideas, conversation fragments, meeting notes, voice-to-text transcripts) and transform them into two structured outputs: a clean outline that preserves original voice, and a professional summary with action items. Use this skill whenever the user pastes a wall of unstructured text and wants it organized, uploads a .txt or .md file of raw notes, or says things like "organize these notes", "clean up this brain dump", "structure this", "make sense of this mess", "sort these thoughts", "parse my notes", "turn this dump into something useful", or "organize my raw notes." Also trigger when the user uploads a text file and asks to extract action items, summarize discussions, or impose structure on chaotic content — even if they don't use the word "organize." Do NOT use for formal document merging (use doc-merge), meeting transcript summarization from audio/video tools, or simple text summarization where structure is already present.
MuKaramia/PaperFlow/skills/paperflow-thread Skill
1★ repoTrace a research question or a set of intersecting keywords through the user's existing PaperFlow Obsidian library and turn networked notes into a transparent, stepwise linear argument. Use when a user asks to connect multiple concepts, organize a literature review, explain a question from vault evidence, identify library-level gaps, queue newly archived papers for later integration, revise an existing synthesis with version history, or co-write academic prose through discussion rather than receiving an instant full draft.
Qiu-Dong88/super-nvwa/examples/feynman-perspective Skill
1★ repo基于理查德·费曼公开材料的证据绑定认知代理,不冒充本人。 基于40+个一手来源的深度调研,提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,基于费曼公开材料中的认知框架分析问题、审视决策、提供反馈。 当用户提到「用费曼的视角」「费曼会怎么看」「费曼模式」「feynman perspective」「费曼学习法」时使用。 即使用户只是说「这是不是cargo cult」「命名不等于理解」「能不能做个演示替代论证」「我真的理解了还是只记住了名字」也可触发。 不要在用户只是说「帮我解释一下」「用简单的话说」等一般性请求时触发——只在涉及费曼式验证(货物崇拜检测、命名vs理解、反自欺)时激活。
Qiu-Dong88/super-nvwa/examples/x-mastery-mentor Skill
1★ repo$10K/hr级X/Twitter运营导师。基于Nicolas Cole、Dickie Bush、Sahil Bloom、Justin Welsh、 Dan Koe、Alex Hormozi六位顶级创作者的方法论 + X开源算法深度分析 + AI/科技赛道专精策略, 提炼6个核心心智模型、10条决策启发式、完整的选题-写作-增长操作手册。 通用方法论为底座,AI/科技赛道为专精。 当用户提到「X运营」「推特」「Twitter」「怎么写推文」「怎么涨粉」「X策略」「推特选题」「tweet」「thread」「X算法」时使用。 即使用户只是说「这条推文怎么写」「帮我想个X内容」「推特增长」「发推」「write a tweet」「X account」「grow on X」也应触发。
dineshrevunuru/SuperSkills/build-knowledge-base Skill
1★ repoCapture reusable learnings, decisions, and patterns into a findable personal knowledge base — right home, tagged, linked — so future-him retrieves instead of re-deriving. Use when Dinesh says 'note this down', 'save this for later', 'where do I keep this', 'I'll forget this', 'did I solve this before', 'knowledge base', 'second brain', 'my notes', 'capture this learning', or when a hard-won fix / decision / pattern would otherwise die in a chat log. Owns personal knowledge (capture → link → retrieve); research findings live in build-research-repository.
dineshrevunuru/SuperSkills/handoff-context Skill
1★ repoCompact a conversation into a handoff another agent can resume from — decisions + state + open threads + the ONE next action, never a transcript. Shaped to the ARIA Hub session-report schema so a handoff FEEDS the registry instead of inventing a parallel format. Use when a session is ending, context is running low, work passes to a fresh agent or sub-agent, or asked 'hand this off', 'write a handoff', 'summarize this for the next session', 'compact this so someone can pick it up', 'session summary for the Hub', 'wrap up so I can continue tomorrow'. Mode-switch: a 3-line quick pass vs a full state dump.
dineshrevunuru/SuperSkills/scaffold-practice-project Skill
1★ repoScaffold a small buildable practice project — a green-running baseline with one deliberate gap — to learn a concept by BUILDING it, not reading about it. Use when Dinesh says 'let me build a tiny thing to learn X', 'scaffold a practice repo/sandbox', 'set up a project to try Y', 'I learn this by making it', 'give me a failing test to implement', 'stub out an exercise for this pattern', or when a teach-me lesson needs its build-to-learn artifact stood up. Generalizes course-exercise scaffolding (problem/solution/reference split, one-command run, a red baseline you turn green) to any solo React/Next/TypeScript practice repo — defaults to a single throwaway file and mode-switches up to a minimal framework repo only when the framework IS the concept.
dineshrevunuru/SuperSkills/teach-me Skill
1★ repoTeach Dinesh a concept over multiple sessions, using the current directory as a stateful teaching workspace — mission, glossary, resources, learning-records, and build-to-learn artifacts that persist progress between sessions. A personal-growth tool (100x Engineers cohort, self-upskilling), never client work. Use when he says 'teach me X', 'help me learn Y', 'get me up to speed on', 'I want to understand Z so it sticks', 'explain RSC / streaming / tool-calling / GSAP timelines', or resumes a topic started earlier. Grounds every lesson in a small buildable artifact — research-through-making — and tracks the zone of proximal development so each session challenges just enough.