agentsclimarketplace

The catalog

610,045 rows, by stacks then stars

  • Zufe thesis typesetter

    SeraphinaGlacia/ZUFE-Thesis-Skill/zufe-thesis-typesetter Skill

    3★ repo

    当用户需要使用 ZUFE-Thesis 模板处理 Word 论文或报告,并交付符合格式、经过检查的 LaTeX/PDF 排版结果时使用。

  • Build write like me

    ronaknnathani/relay/skills/build-write-like-me Skill

    3★ repo

    Skills to orchestrate coding agents to do long horizon tasks with little to no steering

  • Aisp creator evolution aisp

    AIXP-Labs/AISP/examples/aisp/aisp_creator_evolution_aisp Skill

    3★ repo

    AISP-backed bridge for Create new conformant AISP skills, evolve existing ones, and adapt existing Agent Skills into native AISP packages from requirements, SOPs, prompts, or evidence. Use when create a new AISP skill; convert a requirement, workflow, SOP, or prompt into an AISP skill. Do not use when research only, with no skill produced; generating a non-AISP artifact (e.g. a plain SKILL.md with no AISOP body).

    The same file is in 1 other repository

  • Ai presence auditor

    OptimizerTeam/agent-skills/skills/ai-presence-auditor Skill

    3★ repo

    Audit whether a local or home-service business shows up when customers ask AI assistants (ChatGPT, Perplexity, Google AI Overviews/AI Mode, Gemini, Copilot) to recommend a provider — and produce the specific, prioritized fixes that move the needle. Use for an AEO/GEO audit of a local business, or when someone asks "do I show up in ChatGPT," "why does AI recommend my competitor," or "how do I get found by AI."

  • Brand social compliance

    maydengximin-sketch/brand-social-ops-skills/skills/brand-social-compliance Skill

    3★ repo

    品牌社媒内容的合规审查与风险边界。用于广告标注、绝对化用语与违禁词排查、功效与价值承诺的表达红线、敏感话题审查、UGC 与素材版权、肖像权、跨市场表达差异,以及发布前的风险检查清单。触发词包括合规、违禁词、广告法、绝对化用语、风险审查、版权、肖像权、敏感表达、发布前检查。

  • Ai slop cleaner

    mrzhangguoguo/oh-my-workbuddy/skills/ai-slop-cleaner Skill

    3★ repo

    Run a regression-tests-first, smell-by-smell deslop/refactor workflow that preserves behavior and raises signal quality. Use when the user asks to "cleanup", "refactor", "deslop", or when follow-up code has duplicates, dead code, weak boundaries, or fallback-like slop.

  • Codebase analysis

    tony-adamson/groundwork/codex/skills/codebase-analysis Skill

    no license3★ repo

    Use when explicitly asked for $codebase-analysis to create or fully update CURRENT_STATE.md with evidence for the current repository or focused area. Do not use for casual code questions, reviews, implementation, debugging, solution design, or planning.

  • Orchestrate

    gabros20/orchestrate-skill/skills/orchestrate Skill

    3★ repo

    Coordinate multi-agent work by selecting and running a bounded orchestration strategy. Use for implementation plans or multi-step tasks needing staged reviews, parallel worktrees, hierarchical fleets, agent teams, workflows, goal loops, advisor/executor splits, adversarial planning, or external coding CLIs. Triggers include "orchestrate this", "run this plan with subagents", "fan out agents", "goal loop", and "agent swarm". Do not use for small coupled tasks one agent can complete efficiently or for choosing a digital-product lifecycle; orchestrate only coordinates agents and execution.

  • Know my repo

    silkyland/know-my-repo Skill

    3★

    Onboards an agent onto an unfamiliar repository from zero knowledge: deep parallel read of the codebase, extraction of the repo's actual conventions (each proven by at least two examples), verified build/test/run commands, an end-to-end exemplar trace of how a feature is really added, then generates the initial knowledge set — AGENTS.md and docs/ARCHITECTURE.md — with every fact cited. Nothing is deleted. Use on repositories with no (or trivial) agent knowledge files, when the user asks to onboard, initialize, understand, or learn a repo, generate a CLAUDE.md/AGENTS.md from scratch, or mentions know-my-repo or /know-my-repo.

  • Kb cli

    JakePaterson/growth-garage-toolkit/skills/kb-cli Skill

    3★ repo

    Use when managing an agent-facing knowledge base — keeping docs fresh, checking for stale or low-confidence articles, compiling one wiki source into every IDE's config file (CLAUDE.md, AGENTS.md, GEMINI.md, Cursor/Cline rules), regenerating the article index, scaffolding a new project wiki, searching wiki articles by confidence, or filing new sources into a wiki. Trigger words include "kb search", "kb lint", "kb compile", "kb index", "kb init", "knowledge base", "wiki health", "stale docs", "update the wiki", "compile IDE config", "new project wiki".

  • Cherrypick to release

    warpdotdev/client-release-agent-oss/.warp/skills/cherrypick-to-release Skill

    3★ repo

    Resolves a commit and cherry-picks it into one or more client release branches. By default, cherry-picks into BOTH preview and stable. Use when the user asks to cherrypick, backport, or apply a hotfix to a release branch. Optionally waits for a public commit to sync into an internal repo before creating release PRs assigned to the current on-call.

  • Seo geo aso agent skill

    artificialguybr/seo-geo-aso-agent-skill Skill

    3★

    Optimize websites, web pages, and mobile apps for organic visibility across all three modern discovery channels — SEO (Google/Bing organic search), GEO/AEO (getting cited by AI answer engines: Google AI Overviews & AI Mode, ChatGPT, Perplexity, Gemini, Claude, Copilot), and ASO (Apple App Store + Google Play). Use this skill WHENEVER the user wants to improve search rankings, get found by AI/LLMs, increase app downloads, or asks to audit, optimize, or fix anything about a site's or app's discoverability — including adjacent phrasings like "rank higher", "show up in ChatGPT", "AI search visibility", "Core Web Vitals", "structured data / schema", "keywords", "meta tags", "robots.txt for AI crawlers", "llms.txt", "app store listing", "app keywords", "screenshots/conversion rate", or "why isn't my page/app getting traffic". Runs entirely on FREE tools — never requires paid subscriptions. Prefer this skill even when the user doesn't say "SEO/GEO/ASO" explicitly.

  • Codex skin pack installer

    ChannelerH/codex-skin-packs/codex-skin-pack-installer Skill

    3★ repo

    Install Codex themes and Codex skin packs with npx skills. Use this skill when a user wants Codex to find, download, validate, apply, switch, remix, or restore Codex desktop themes such as caishen-readable, caishen-lite, mythic-guardian-noir, global-founder-bright, export-night, or caishen-max. It stages verified public-safe theme packs from ChannelerH/codex-skin-packs, checks theme.json/background.png, preserves the native Codex layout, avoids private workspace screenshots, and provides restore guidance.

  • Vibe upgrader

    Zeno-wistom/vibe-upgrader Skill

    3★

    Upgrade real frontend projects through one of two explicit tracks: standard UI/UX improvement for hierarchy, usability, content, controls, and brand polish; or experimental visual work for immersive, high-impact, signature motion and non-standard interaction. Use only when the user explicitly invokes this skill (for example, `$vibe-upgrader` in Codex or `/vibe-upgrader` in Claude Code) or explicitly requests its full workflow. Preserve project facts and permission boundaries, prototype experimental mechanisms before integration, and use MotionSites, React Bits, foundation UI, existing assets, or custom work only when their responsibility fits the task.

  • Evidence first ai video

    ouyangevan/evidence-first-ai-video-skill/skills/evidence-first-ai-video Skill

    3★ repo

    Use when researching, scripting, sourcing, producing, revising, or quality-checking Chinese or English AI and technology talking-head, presenter-led, voiceover, product-demo, explainer, or social videos whose claims need traceable evidence, real interfaces, synchronized narration, B-roll, or final media QA.

  • Commit and push

    Gusen1453/creed/skills/commit-and-push Skill

    3★ repo

    Use when the user asks to commit, push, commit-and-push, open/draft a PR/MR, or write a PR description with a Test plan — especially when changes should be split into logical commits, or when tempted to dump everything into one commit or push to a protected branch.

  • Account market research

    bowtiefunnel/bowtie-funnel-Labs/plugins/bowtie-gtm/skills/account-market-research Skill

    3★ repo

    Use when you need to understand and prioritize target companies — firmographics, funding, investor portfolio, and recent activity — before outreach (Awareness) or to find whitespace in accounts you already own (Expansion). Runs on the Growth (Verbiflow) MCP.

  • Accessibility pass

    protosphinx/sphinxstack/skills/accessibility-pass Skill

    3★ repo

    Audit a live site for accessibility and fix what turns up. Covers contrast, alt text, keyboard navigation, and form labels, tested with real tools. Use when they ask "is my site accessible", before they share a site widely, or after any skill that shipped pages.

  • Opc legal cn

    sublatesublate-design/opc-legal-cn Skill

    3★

    面向中国大陆OPC及互联网创业者的中文法律Skill。用于回答OPC概念、适合度、业务模式、主体选择、公司设立、具体税负测算、税务与发票、网站/App/小程序/SaaS/AI上线、客户合同、收款交付、员工外包、责任隔离、融资、暂停和退出问题;一般认知以唯一完整文章为基础,具体办理根据用户城市、业务、主体和阶段调用内部SOP、事件规则、法源、案例、数据库和机器可读JSON Schema。没有完整SOP时必须复核官方来源并说明核验边界。

  • Aios

    arete-aios/aios Skill

    3★

    AIOS: build the five layer AI operating system in nine stages, one exit test each, progress kept in a file instead of the chat. Use when starting a second brain from nothing.

  • Bmad advanced elicitation

    mannnrachman/pi-bmad/skills/bmad-advanced-elicitation Skill

    no license3★ repo

    Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

  • Monetization guide

    genapohub/monetization-guide Skill

    3★

    商业化负责人方案产出指南。当用户提出商业化/变现需求、需要产出商业模式方案时触发。覆盖场景:商业化体系搭建、新付费产品/定价、单SKU调整、商业模式转型、变现探索。先识别需求属于5类场景中的哪一类(0到1商业化体系搭建/中大型商业化项目/小优化定价调整/商业化模式转型/商业化探索),再按对应场景的产出清单生成完整方案。

  • Graph engineering

    luxiaolei/graph-engineering/skills/graph-engineering Skill

    3★ repo

    A Codex Agent Skill for designing governed, project-local agent graphs.

  • Dashboard design

    valewnrt/design-skills/skills/dashboard-design Skill

    3★ repo

    Design and review web app and dashboard UI — sidebars, data tables, charts, modals, popovers, toasts, forms, admin panels and SaaS product surfaces, plus color systems and dark mode. Works for React, Next.js, Vue, Svelte, Tailwind and plain CSS. Use when building a new page or flow, when polishing a product that looks generic or vibe-coded, or when asked to "design this dashboard", "improve the app UI", "make this look professional", "review my design", or "why does this look AI-generated". For marketing sites use landing-page-design instead.

  • Liquid glass advanced

    SohrabZ/liquid-glass-skills/liquid-glass-advanced Skill

    no license3★ repo

    Advanced iOS 26 Liquid Glass composition and integration patterns in SwiftUI: floating action clusters / expandable FABs, SF Symbol effects on glass (contentTransition symbolEffect / replace / numericText), performance optimization for glass, dynamic color-scheme adaptation to background, custom floating glass navigation/sidebars, drag-gesture-driven glass, and CoreText-based custom glass text (converting glyphs to a Path used as the glass shape). Use this skill when the user is building something beyond a single control — an expanding menu of glass buttons, an animated icon that morphs on a glass surface, a draggable glass element, glass that adapts as content scrolls light-to-dark, a bespoke floating sidebar, or glass-shaped text. Trigger on "floating action button cluster", "expandable FAB", "symbolEffect", "glass performance", "glass adapts to background", "draggable glass", "CoreText glass", or "custom glass text".

  • InsightCompiler

    snc2work/insight-compiler/InsightCompiler Skill

    3★ repo

    Use this first whenever the user wants to deepen their thinking rather than receive a normal answer. It turns any consultation, vague problem, business idea, product concept, article angle, important decision, strategy, positioning, or personal dilemma into an executive read, overlooked questions, unexpected perspectives, a dense hint bank, traceable strategy candidates, an honest strategy evaluation, and one validation point with pre-committed decision forks. Especially trigger on phrases like "let me consult you", "what do you think", "how should I", "I have an idea", "I want to think this through", "help me dig deeper", "be my sounding board", or "help me sort this out" (in any language). Also trigger when the user returns with a validation result from a previous session. Respond in the user's language.

  • Marketplace

    leadgenjay/Reeper/marketplace Skill

    3★ repo

    Safely adapt an external GitHub repository into an existing project instead of blindly copying its architecture. Use when the user wants to import, transplant, fork, vendor, or reimplement someone else's repo for their own stack, merge a repo into an existing app, preserve their own auth/database/billing/design-system while taking a source repo's features, resume an interrupted repository adaptation, or turn a repository or workflow into a callable Agent Skill or plugin. Performs evidence-first source and target analysis, builds a conflict matrix, interviews one material decision at a time, requires explicit approval of an Integration Contract before any code changes, implements in isolation, and verifies against the contract.

  • Fn fpk builder skill

    kci-lnk/fn-fpk-builder-skill Skill

    3★

    Build, validate, inspect, release, install, replace, troubleshoot, and safely remove fnOS/飞牛 OS FPK application packages. Use when Codex works with fnpack, appcenter-cli, .fpk archives, fnOS manifests, native or Docker app templates, x86_64/ARM64 packaging, GitHub Actions release pipelines, or SSH-based deployment and smoke testing on a fnOS device.

  • Communicate with c d

    crystal-project-inc/personality-ai/communicate-with-c-d Skill

    no license3★ repo

    Communication coaching for working with a CD (The Skeptic) DISC type — critical, driven, questioning. Covers do's, don'ts, meetings, email, feedback, and conflict. Powered by Crystal's DISC framework.

  • Podlite markup

    podlite/podlite-skills/skills/podlite-markup Skill

    3★ repo

    Create and edit Podlite markup files. Use when working with .podlite files, or when the user mentions Podlite, formatting codes, declarative blocks, structured markup for documentation, or AI agent instructions.

  • Syncfusion winforms ai assistview

    syncfusion/winforms-ui-components-skills/skills/syncfusion-winforms-ai-assistview Skill

    no license3★ repo

    Guide for implementing Syncfusion Windows Forms AI AssistView (SfAIAssistView) for building conversational AI interfaces in desktop applications. Use this when creating chat interfaces, AI assistants, or chatbots with Windows Forms. Supports OpenAI and Azure OpenAI integration, typing indicators, chat suggestions, message bubbles, and custom views for interactive messaging experiences.

  • Composio

    lunchpaillola/pipa-skills/skills/composio Skill

    3★ repo

    Operational skills for the agents people already use.

  • Vmware aria

    zw008/VMware-Aria/skills/vmware-aria Skill

    3★ repo

    Use this skill whenever the user needs VMware Aria Operations data — performance metrics, alerts, capacity planning, anomaly detection, and automated reports. Directly handles: query resource metrics, list/acknowledge/cancel alerts, manage alert definitions, check capacity and time-remaining forecasts, detect anomalies, generate and manage reports. Always use this skill for "check vSphere capacity", "what Aria Operations alerts are active", "show VMware anomalies", "generate an Aria report", "rightsizing recommendations", or any Aria/vRealize Operations task. Combined with LLM, Aria data powers natural language reports: "give me a capacity report" → Aria collects data → LLM formats the report. Do NOT use for real-time vCenter alarms/events (use vmware-monitor), VM operations (use vmware-aiops), or NSX networking (use vmware-nsx). For load balancing/AVI/AKO use vmware-avi.

  • Agile project lifecycle mcp

    wchen02/cursor-agent-learning/.cursor/skills/agile-project-lifecycle-mcp Skill

    no license3★ repo

    Full agile lifecycle with MCP: use MCP to fetch current docs/API schema during discovery and development. Use when building a project from a rough idea that depends on external APIs or libraries and you want up-to-date references via MCP.

  • Anxiety screening

    rhavekost/clinical-toolkit/dist/consumer/claude/anxiety-screening Skill

    no license3★ repo

    Use when screening for anxiety symptoms (excessive worry, restlessness, difficulty concentrating, muscle tension, panic attacks), differentiating anxiety disorders, assessing treatment response, or patient reports overwhelming fear or avoidance behaviors. Provides GAD-7 (comprehensive) and GAD-2 (brief) assessments.

  • Ai native cli

    ChaosRealmsAI/agent-cli-spec/ai-native-cli Skill

    3★ repo

    AI-Native CLI design spec. Use when building CLI tools, designing command-line interfaces, or scaffolding new CLI projects. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description. Includes an audit protocol for verifying CLI compliance.

  • Md writer

    skrrt-sh/skills/skills/docs/md-writer Skill

    3★ repo

    Write or edit knowledge-base Markdown with frontmatter, Mermaid diagrams, related-document links, and markdownlint validation. Use for guides, specs, ADRs, runbooks, and API documentation; not repository meta files such as README, CHANGELOG, CLAUDE.md, AGENTS.md, or SKILL.md.

  • Code review excellence

    b-mendoza/agent-skills/.agents/skills/code-review-excellence Skill

    no license3★ repo

    Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

    The same file is in 5 other repositories

  • Auto code review

    i-stack/ai-coding-kit/skills-engineering/auto-code-review Skill

    3★ repo

    用户显式触发的跨模型代码审查工作流。仅当用户明确说 `/auto-review`、`使用 auto-code-review`、`启动跨模型代码审查`,或明确要求“审查并修复”时使用;普通代码生成、修改完成或含糊的“看看代码”不自动触发。默认只读审查,只有用户明确要求 `--fix` 或“审查并修复”才允许主 agent 修改代码。

  • Prompt optimizer skill

    dreamor/prompt-optimizer-skill Skill

    3★

    Optimize and rewrite prompts using 61 frameworks (APE, RACE, CRISPE, Chain-of-Thought, COAST, SMART, etc.). Trigger on "optimize prompt", "improve this prompt", "make this prompt better", "rewrite for AI", "优化提示词", "改写 prompt", "优化指令", "让提示词更好", "帮我把这个写成 prompt" or any vague/short instruction the user wants turned into a high-quality prompt — even if the user only says "make this clearer" or "help me write this". Also trigger whenever the user pastes raw text and asks for a structured AI-ready version, or expresses dissatisfaction with AI output quality without naming a fix. Always use this skill when the user inputs vague instructions, needs prompt optimization, or is dissatisfied with AI output quality.

  • Arr media stack

    ddnetters/homelab-agent-skills/arr-media-stack Skill

    3★ repo

    Radarr, Sonarr, Prowlarr, Bazarr, and qBittorrent APIs for automated media management — search, add, monitor, and troubleshoot downloads

  • Bstack

    broomva/bstack Skill

    3★

    bstack — the Broomva Stack. Twenty irreducible primitives (P1-P20) plus 30 curated skills that turn an agent-driven workspace into a self-operating system. Each primitive closes one specific failure mode (session amnesia, destructive ops, invisible work, dirty-tree drift, context rot, ritual phrases without substance, single-model echo chambers). The canonical operating mode is broomva/autonomous (fires every reflex without prompting). Use when: (1) bootstrapping a new agent-driven workspace, (2) verifying primitive compliance via 'bstack doctor', (3) repairing missing governance/hooks/policy via 'bstack repair', (4) listing installed-vs-missing skills via 'bstack status', (5) validating skill frontmatter health via 'bstack validate', (6) full reconfiguration via 'bstack revamp'. Triggers on 'bstack', 'broomva stack', 'bootstrap project', 'install all skills', 'P1' through 'P20', 'agent harness', 'self-operating workspace'.

  • Autopilot

    PresentJay/autopilot-skills/skills/autopilot Skill

    3★ repo

    Self-driving mission runner — once started, runs an endless discover→analyze→plan→execute→verify→learn cycle on a user-defined mission until told to stop. Boot interview captures mission, allow/forbidden paths, risk tier, cadence, auto-compact threshold, escalation, update policy, resume policy. Safety policy blocks forbidden zones at every phase, forces dry-run for risky ops, learns NOT-OK patterns from failures. Self-heals after interrupted cycles or missed wakeups. Universal across AI coding agents (Claude Code, Codex, Cursor, Gemini, ...). Triggers - "autopilot", "self-drive", "자율주행", "auto drive", "autonomous mode", "run cycle", "resume autopilot", "heal autopilot".

  • Skill forge

    Adit-Jain-srm/skill-forge Skill

    3★

    Autonomous self-improving intelligence amplifier. Devours skills, knowledge, and novel approaches from across the internet. Serves two objectives: (1) make itself better at devouring, and (2) produce skills that dominate with stars. Use for finding best skills for any project, creating skills, improving capabilities, creative thinking for hackathons, optimal architecture decisions, project guidance, advertising published skills, or when user says skill-forge, devour, discover, find skills, route, create, improve, or wants optimal approaches for any task.

  • Build your own agent

    veithly/build-your-own-agent Skill

    no license3★

    Use when building or designing an agent harness; choosing between Codex, Claude Code, OpenClaw, or Hermes patterns; designing agent loop, subagents, todo/task progress surfaces, execution-state routing, memory, skills, cron, sandbox, or security; diagnosing slow, expensive, leaky, looping, or unsafe agents; or preparing for agent-infra interviews.

  • Domain architecture guidance

    xfoundries/domain-architecture-skills/skills/domain-architecture-guidance Skill

    no license3★ repo

    Authoritative architecture guidance for business-domain systems using Domain-Driven Design, Layered Architecture, Onion Architecture, Hexagonal Architecture / Ports and Adapters, and CQRS. Use when designing, reviewing, refactoring, documenting, or implementing domain-heavy systems with package/project boundaries, repositories, aggregates, application services, ports/adapters, CQRS, jMolecules-style annotations, or architecture tests.

  • Skill

    yinguobing/qweather-skill/skill Skill

    3★ repo

    查询全球城市或者经纬度位置的实时天气、天气预报、空气质量等信息的技能。当用户询问某个城市或者经纬度的天气、气温、降雨、风向、空气质量时调用。

  • Adaptive messaging

    dirknicol/pmm-skills/skills/adaptive-messaging Skill

    3★ repo

    Use this skill when a new competitor move, market event, or sudden change in buyer language requires a rapid messaging response. Triggers include 'competitor launched', 'competitor moved', 'rapid competitive response', 'new competitive objection', 'market shift', or 'sales needs updated talking points'. Implements Detect → Decide → Draft → Deploy and outputs a competitive response brief plus sales-ready battlecard. Do NOT use for evergreen battlecards, routine objection handling, general sales materials, brand voice work, or net-new positioning; use `sales-enablement` for evergreen deal support.

  • Claude email skill

    thegauravmahto/claude_email_skill Skill

    3★

    Use when writing cold emails, job application emails, sales outreach, investor pitches, networking intros, or any high-stakes email where the reply matters more than the message. Triggers on "cold email", "job application email", "outreach", "pitch email", "sales email", "intro email", "reply rate", "get a response".

  • Askit backlog

    product-on-purpose/agent-skills-toolkit/skills/askit-backlog Skill

    3★ repo

    Creates, triages, and prunes a plugin's two backlogs (new-component proposals and enhancements) to the Advanced Skill Library Standard. Use when capturing a new-component proposal through the why-gate, prioritizing backlog items, or removing stale or completed entries.

  • Generation prompt builder

    seaartpublic/skills/generation-prompt-builder Skill

    3★ repo

    Build or optimize high-quality generation prompts from copy, product information, scripts, rough ideas, reference-image descriptions, or existing prompts. Use for image, video, audio, and mixed creative prompts when the user wants ready-to-copy prompt text, not tool execution. Do not use when the user specifically asks to generate an image with GPT Image or asks for storyboard/shot-list planning.

  • Metrics basics

    nemanli/ux-metrics-skills/skills/metrics-basics Skill

    3★ repo

    Defines UX measurement frameworks, terms, and philosophy when the user is learning the foundation rather than applying it — "what is HEART?", "define cohort retention", "what is MDE?", "what's a decision rule?", "why do we measure things this way?". Skip when a real situation is in mind (redesign, metric drop, stakeholder report, pre-launch plan, A/B test, tracking plan, claim review) — those go to the content skills.

  • Ai study workflow

    rhyme17/ai-study-workflow/skills/ai-study-workflow Skill

    3★ repo

    Build AI-assisted study workflows for university learning. Use when the user asks to improve study efficiency, prepare for finals or exams, review a course, learn new material, make a study plan, generate practice questions, diagnose weak points, create Anki/FSRS flashcards, or run AI tutoring without replacing student thinking. Triggers include 期末复习, 备考, 学习效率, 新知识学习, AI 学习助手, 错题, Anki, 间隔复习, and 苏格拉底式辅导.

  • Entry recommender

    product-on-purpose/writing-style-catalog/skills/entry-recommender Skill

    no license3★ repo

    Recommend a voice, tone, style, and format combination from the catalog's stable entries for a described writing situation, then compose the prompt in the same step. Accepts optional pre-fixed axis values; never recommends draft entries; reports low confidence rather than force-picking when nothing fits.

  • Video understanding

    stevederico/video-understanding Skill

    3★

    Turn a video file into a full AI understanding: use video-understanding.sh for frames + transcript, then review as agent to produce understanding.md. Local ffmpeg + whisper. Use when user runs /video-understanding, or says "process this video with full understanding", "get frames and transcript then analyze".

  • Memento skill

    waterdrop26651/Memento-skill Skill

    3★

    Controlled recall for research memory, experiment tracking, evidence ledgers, hypothesis updates, archival recall, and next high-information experimental contrasts.

  • Agile story splitter

    alwyndsouza/agile-story-skills/.github/skills/agile-story-splitter Skill

    no license3★ repo

    Break an oversized user story or epic into sprint-sized stories using Richard Lawrence's Humanizing Work split patterns. Use when a story is too large to estimate, a story is > 8 points, an epic needs decomposing, or a backlog item cannot be delivered in one sprint. Triggers on: story too big, split this story, break this epic, story splitting, epic breakdown, too many points, can't estimate, Humanizing Work, vertical slice, oversized story, 13 points.

  • Aws cost audit

    Aboudjem/aws-cost-audit-skill/skills/aws-cost-audit Skill

    3★ repo

    Use when a user wants to audit, understand, reduce, or optimize their AWS bill or cloud costs, finding idle, unused, or orphaned resources, rightsizing over-provisioned compute, checking Savings Plans / Reserved Instance coverage, NAT gateway and data-transfer costs, S3 storage and lifecycle, CloudWatch log retention, untagged or unexplained spend, per-resource cost attribution ("what is this costing me and why"), or building a savings plan or cost dashboard. Triggers include "AWS bill too high", "cut/lower AWS costs", "FinOps", "Cost Explorer", "where is my money going", "unused AWS resources", and "cloud cost audit".

  • Share md

    kirollosatef/skills/skills/share-md Skill

    3★ repo

    Share a markdown file via a private GitHub Gist link with optional auto-delete after a custom TTL, end-to-end encryption, dry-run preview, or one-time burn-after-read via transfer.sh. Use this skill whenever the user wants to send/share/give a markdown file or doc to a colleague, teammate, agent, or themselves via a URL — even if they don't say "gist" explicitly. Triggers on phrases like "share this markdown", "send this doc as a link", "give me a shareable URL for this .md", "share with auto-delete", "ephemeral share", "expire in N hours/days", "share so my agent can fetch it", "encrypt before sharing", "password protect this share", "burn after read", "one-time view", "preview the share without creating it", or any request to turn a local markdown file into a fetchable URL with optional expiry, encryption, or single-use semantics.

  • Compose state management

    almasumdev/awesome-kotlin-android-agent-skills/.github/skills/architecture/compose-state-management Skill

    no license3★ repo

    Expert guidance on managing state in Jetpack Compose using ViewModel, StateFlow, remember/rememberSaveable, state hoisting, and unidirectional data flow. Use this when implementing screens or refactoring stateful composables.