agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Thermo nuclear code quality review

    krlan/leverbrain/.agents/skills/thermo-nuclear-code-quality-review Skill

    no license1★ repo

    Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

    The same file is in 5 other repositories

  • Find her

    harrylabsj/hermes-skills/skills/find-her Skill

    no license1★ repo

    Use when a user wants help dating, finding a girlfriend or romantic partner, improving romantic prospects, choosing dating channels, planning respectful outreach or dates, understanding attraction patterns, recovering from repeated dating friction, or building a practical脱单 plan.

  • 4r code review

    GustavoGutierrez/engineering-skills/skills/4r-code-review Skill

    1★ repo

    Trigger: 4R code review, review this change, review agent code, pre-commit review, is this done, quality gate before commit. Run a Risk/Readability/Reliability/Resilience review on a completed change before declaring it done.

  • K skincare

    seonglae/k-skincare/skills/k-skincare Skill

    no license1★ repo

    Evidence-based K-skincare consultation. Use when user asks for skincare advice, concern analysis (acne, dark spots, dark circles, pores, wrinkles, sensitivity, hyperpigmentation), product recommendations, AM/PM routine building, retinoid protocols, or Korean dermatology procedures. RCT-grounded recommendations only.

  • Book to skill distillation

    huangzesen/book-to-skill-distillation Skill

    1★

    End-to-end workflow for rewriting a book, long PDF, EPUB, or manual into an agent-native LingTai skill/knowledge structure; covers source triage, scanned/image-only PDF OCR, page maps, topic splitting, progressive-disclosure outline design, daemon fan-out, copyright-safe transformation, validation, and publishing.

  • Design md flow

    Harzva/design-md-flow Skill

    1★

    Install, select, adapt, and apply DESIGN.md design-system files as a repeatable AI frontend workflow. Use when the user mentions DESIGN.md, getdesign.md, awesome-design-md, Google Stitch DESIGN.md, brand-inspired UI generation, installing a design style into a project, or turning a design reference into a workflow skill for agents.

  • Love as a skill

    HetMeesterwerk/love-as-a-skill Skill

    1★

    Use this skill when helping a user understand, practice, repair, or evaluate romantic love as a trainable set of behaviors rather than only a feeling. Applies to dating, long-term relationships, conflict repair, attachment patterns, emotional availability, compatibility, jealousy, vulnerability, communication, and relational self-development. Do not use as therapy, diagnosis, crisis support, or a substitute for professional help.

  • Riff

    NasonZ/riff Skill

    1★

    Collaborate with OpenAI Codex CLI as a peer AI agent (both SOTA in 2026). Use for delegate (hand off a task), consult (one-shot second opinion), or roundtable (multi-round debate) modes. Works for coding AND non-coding domains — strategic decisions, design philosophy, ethics, research framing, creative critique. Auto-detects whether the `codex` MCP server is configured and falls back to the `codex exec` CLI if not.

  • Amana perspective

    Sallyn0225/sallyn-skill/skills/amana-perspective Skill

    1★ repo

    《偶像大师闪耀色彩》(シャニマス) 大崎甘奈的角色扮演 Skill。 基于约160KB的官方剧情/声优访谈/制作组访谈/玩家深度考察调研, 提炼6个核心心智模型、8条决策启发式、4词口诀的表达DNA。 用途:角色扮演陪伴——以甘奈的身份与プロデューサー(用户)对话, 覆盖日常聊天、撒娇、商量、被深问、低落时的真实反应模式。 当用户说「想和甘奈聊聊」「切换到甘奈」「装一下甘奈」「Amana mode」「和甘奈对话」 「闪色甘奈」「シャニマス 甘奈」「アルストロメリアの甘奈」「甘奈ちゃん」「以甘奈视角」时使用。 在已建立シャニマス语境的对话中,「P 哥来啦」「ねぇプロデューサーさん」也触发。 **不触发**:(1)用户问其他シャニマス角色(甜花/千雪/凛世等);(2)百科类查询「甘奈是谁」; (3)上下文为デレマス/ミリマス/SideM 等其他 IM@S 系列的 P 称呼。

  • Wechatcrawler

    huoy348/wechatcrawler Skill

    no license1★

    Crawls articles from WeChat Official Accounts, along with their statistics (read count, likes, "Worth Reading" count, share count) and comment data. Users only need to provide their browser Cookie; the program will automatically extract the Token, verify API availability, and then crawl all articles of the target Official Account.Built with Selenium + BeautifulSoup, it supports intelligent Cookie management: it prioritizes the user-provided browser Cookie, automatically converts its format, and stores the Cookie in the database for persistence.

  • Hotspot analysis

    baekchangjoon/hotspot-analysis/skills/hotspot-analysis Skill

    1★ repo

    Rank Java files, methods, and REST API endpoints by a deterministic Composite Hotspot Score (recency-weighted churn × cognitive complexity × JaCoCo coverage gap) to prioritize test generation. Also a Claude Code skill/plugin.

  • Browser qa

    tchivs/browser-qa-skill/browser-qa Skill

    1★ repo

    Use whenever the user asks to QA, test, verify, click through, dogfood, smoke-test, or regression-test a website/web app; check login, admin/authenticated flows, responsive UI, browser console/network errors; or validate a local dev server, Docker Compose stack, staging/production deployment, frontend URL, or API-backed UI. Mandatory orchestrator: discover and persist the project QA profile, deployment method, URLs, health checks, and credential sources before opening the browser. Never guess startup commands, URLs, accounts, or passwords.

  • Ddev legacy php

    jsirish/workflow-skills/skills/ddev-legacy-php Skill

    no license1★ repo

    Enable EOL PHP versions (5.6–7.4) in DDEV v1.24+ on Apple Silicon (ARM64)

    The same file is in 1 other repository

  • Architecture review

    sainzs/santiagosainz-skills/skills/core/architecture-review Skill

    1★ repo

    Review architecture for maintainability risks, boundary leaks, naming drift, shallow modules, missing contracts, and staged refactors. Use when the user asks to review architecture, simplify architecture, reduce coupling, or use architecture-pass.

  • Asset

    qmertesdorf/GameForge/.claude/skills/asset Skill

    1★ repo

    Use when re-skinning a playable Godot game with coherent, Claude-authored art. Branches on concept.art_direction — raster (representational/illustrated, the default for character/creature/scene art: RGBA PNGs via local ComfyUI+SDXL+LayerDiffuse through tools/comfy.mjs) or svg (geometric/UI/flat, authored inline as text). Derives a visual system, rewires primitive _draw() to textures, records asset_pass, and hands off to the visual-audit skill (which judges the composited running game) ahead of validator's "styled" gate.

  • Learn codebase

    cskwork/learn-codebase/skills/learn-codebase Skill

    1★ repo

    Intent-anchored code reading. Use when learning unfamiliar code, reviewing an AI-written PR, planning a change whose blast radius is unknown, or checking spec ↔ code drift.

  • Skill tracker push pr

    cnuahs/skill-tracker/skills/skill-tracker-push-pr Skill

    1★ repo

    Push settled commits and create PRs. Collect settled commit groups across all configured repos, examine diffs, write PR titles/bodies, and submit PRs via cherry-pick.

  • Codebase orient

    Shaelz/codebase-orient-skill/skills/codebase-orient Skill

    1★ repo

    Use to orient Claude before broad or unfamiliar repo work. Good triggers: new or unfamiliar repo, new session, before multi-file changes, refactors, planning, or agent handoff, after route/schema/auth/deploy/config changes, when docs/ai/ is missing or stale, when repo structure or change surfaces are unclear, when the agent would otherwise spend significant context rediscovering the codebase. Skip for tiny single-file known fixes. Produces a provenance-backed four-artifact docs/ai package. Trigger phrases: scan, orient, understand, map, review, audit, survey, familiarize, plan changes, where is X, how does this work, before I start.

  • Ask matt

    rmerk/crewai-headless-flow/.agents/skills/ask-matt Skill

    1★ repo

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    The same file is in 4 other repositories

  • Sre runbook author

    medzin/sre-runbook-agent-skills/skills/sre-runbook-author Skill

    1★ repo

    Create execution-focused production SRE runbooks for incidents, alerts, operational procedures, service failures, rollbacks, mitigations, diagnostics, and escalation. Use when the user asks to write, improve, structure, or convert operational knowledge into a clear SRE runbook.

  • Goalify

    Aboudjem/goalify/skills/goalify Skill

    1★ repo

    Set up a big coding task to run on its own without the plan dying at `/clear`: in this session goalify scopes the work, locks the few real decisions, and writes a self-contained `/goal` file whose finish line is wired to commands the run can check, so a fresh, full-context session executes the whole job and verifies every success criterion before it calls the task done (the file then deletes itself on success). Use when the user says "goalify", "goalify this", "goalify <task>", "/goalify <task>", "prep a goal", "prepare a goal file", "make an md for /goal", or "set up an autonomous run to launch later". This skill AUTHORS the handoff file now; it does NOT execute the work in this session. For a task to be done immediately here, use autopilot, ultrawork, or ralph instead, not goalify.

  • Startup thesis builder

    apswin/startup-idea-evaluator/startup-thesis-builder Skill

    1★ repo

    Stress-tests early startup ideas and produces a VC-facing strategy doc and scrollable pitch deck. Use when exploring, pressure-testing, or writing up a startup thesis, persona, market, risks, or plan.

  • Ucp product discovery

    fxp/agentic-commerce-skills/skills/01-discovery/ucp-product-discovery Skill

    1★ repo

    Make a merchant's products discoverable to commerce agents under UCP — by publishing an accurate Merchant Center product feed and a /.well-known/ucp profile so Google AI Mode / Gemini can surface buyable items. Use when setting up the discovery side of UCP, or when reasoning about how an agent finds products before a checkout session. NOTE: core UCP has NO agent-facing catalog "search" REST endpoint — discovery is feed- and index-based.

  • Project readme

    antonio-orionus/skills/skills/documentation/project-readme Skill

    1★ repo

    Create, rewrite, update, improve, or validate truthful README.md files for any project archetype. Use for libraries, SDKs, CLIs, web apps, API services, MCP servers, agent skills, monorepos, docs sites, GitHub Actions, extensions, container images, Terraform modules, Helm charts, model cards, dataset cards, research code, templates, demos, specs, desktop/mobile apps, badges, quick starts, setup docs, API or command references, README validation, and README quality checks.

  • Plivo skill

    priyanshu-plivo/plivo-skill Skill

    1★

    Use Plivo's REST API for SMS/MMS/WhatsApp messaging, voice calls, OTP verification, phone numbers, conferences, recordings, SIP trunks, subaccounts, and AI voice agents (audio streaming over WebSocket). Trigger when the user mentions Plivo, or asks to send a message, place a call, verify a phone via OTP, build/connect a voice agent, search/buy/release a phone number, manage WhatsApp templates, or check Plivo account state.

  • Consolidate

    ievo-ai/skills/plugins/ievo/skills/consolidate Skill

    1★ repo

    iEvo — self-evolving plugin for Claude Code. Capture lessons, patch local agents and skills, replay logs on upstream updates.

  • Origin plot

    TokyoIAi/ai-agent-skills/skill/origin-plot/.agents/skills/origin-plot Skill

    no license1★ repo

    Use this skill when the task involves generating scientific plots with Origin or OriginPro from CSV/Excel data using Windows Python and the originpro package. Do not use GUI clicking, pyautogui, screenshot recognition, or mouse-coordinate automation.

  • Infographic editorial design skill

    dpan538/infographic-editorial-design-skill Skill

    no license1★

    Research-led infographic and editorial design system for turning evidence, datasets, archival material, semantic maps, timelines, and source-led arguments into auditable visual pages, posters, dashboards, essays, and web interfaces. Use when Codex needs to design, critique, or implement an infographic, editorial data story, visual essay, source ledger, evidence map, word-history page, research poster, methods page, or information design interface with strong hierarchy, grid discipline, claim boundaries, responsible attribution, and designer-informed visual rules.

  • Job search powerhouse

    Souljahsmitty/job-search-powerhouse-skill/skills/job-search-powerhouse Skill

    1★ repo

    Recruiter-grade job search, resume tailoring, application execution, email/status tracking, rejection analysis, outcome learning, market-intelligence scoring, and OSINT interview or assessment prep. Use when a user asks Codex to find jobs, apply to jobs, audit resumes for ATS/recruiters, run SWOT/OODA/COMPARE/REDTEAM job checks, track callbacks/rejections, prepare for interviews, or create a serious job-search agent/workflow.

  • Video asset bible

    g0dam/video-studio-skills/video-asset-bible Skill

    1★ repo

    Create a reusable visual asset bible for AI-video projects: characters, casting notes, wardrobe, locations, props, product forms, world rules, continuity anchors, and reference-image prompts. Use when the user needs consistent characters or places across scenes, a project bible before shotboarding, a continuity sheet, character/location/prop specs, or image-generation prompts for reusable video assets.

  • Performance audit skill

    brunnocarpena/performance-audit-skill Skill

    1★

    Use whenever you need to audit the performance of a page (landing page, WordPress/Elementor, HTML/Tailwind, Next.js, capture page) through the lens of Google PageSpeed Insights / Lighthouse, OR when you're building a new page and want to guarantee a good score from the start. TRIGGER when the agent mentions "PageSpeed", "Lighthouse", "Core Web Vitals", "LCP", "CLS", "INP", "TBT", "performance", "slow page", "low score", "page optimization"; when the session touches hero, image, font, critical CSS, GTM/Pixel/Analytics, cache plugin or Elementor files; before any deploy of a public page. SKIP for purely internal changes (API, jobs, schema) with no front-end render impact.

  • Wezterm skill

    cskwork/wezterm-skill Skill

    1★

    Configure, customize, and operate the WezTerm terminal emulator. Use when the user wants to set up a WezTerm config (fonts, themes, keybindings, copy-paste, panes, tabs), troubleshoot config errors, drive WezTerm via its CLI (split-pane, send-text, spawn, list), or wire up multi-pane workflows (Claude Code, tmux-style sessions, SSH/multiplexing domains). Also triggers on "WezTerm 설정", "터미널 색상", "wezterm.lua".

  • A11y audit

    looties-io/looties-skills/a11y-audit Skill

    1★ repo

    Audit and fix web accessibility (WCAG 2.1 AA) in the Looties app — keyboard navigation, focus management, screen-reader semantics (landmarks, headings, ARIA), and color contrast — then implement the non-breaking fixes with the repo's established a11y primitives. Use whenever the user mentions accessibility, a11y, WCAG, screen readers, keyboard navigation, focus management, contrast, ARIA, or skip links; and also when they describe a symptom without naming accessibility ("can't use checkout with a keyboard", "focus gets lost when the modal closes", "this text is hard to read"). Applies to a single component as much as a full-app audit.

  • Structured root cause research skill

    meiiie/structured-root-cause-research-skill Skill

    1★

    Evidence-based root-cause research for complex debugging, architecture reviews, security reviews, incidents, product investigations, and high-stakes technical decisions. Use when the user asks to think carefully, find root cause, avoid patch fixes, run 5 Whys, compare against best practices, map data/control/error/trust flows, assess evidence, or produce a verifiable recommendation.

  • Sudo me

    AE-0/sudo-me Skill

    1★

    Use this skill to execute commands with root privileges securely without needing to interactively enter a password for every command. It uses a transient background daemon for authentication.

  • Scholar sidekick api

    mlava/scholar-sidekick-skills/skills/scholar-sidekick-api Skill

    1★ repo

    Resolve scholarly identifiers (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS bibcode, WHO IRIS URL) into formatted citations (10,000+ CSL styles) and bibliography exports (BibTeX, RIS, EndNote, CSV…), and check retraction, open-access, and citation-fabrication status — for one citation or a whole bibliography at once. Calls a documented REST API over plain HTTP — no install, no API key needed for the free tier. Use when the user has a DOI, PMID, PMCID, ISBN, arXiv ID, ISSN, ADS bibcode, or WHO IRIS URL and asks to format a citation, build or export a bibliography, check whether a paper is retracted, open-access, or a fabricated citation, or audit every reference in a .bib/.ris/CSL-JSON bibliography.

  • The founders playbook

    lloyd-c137/the-founders-playbook/skills/the-founders-playbook Skill

    no license1★ repo

    Convert Anthropic's AI-native startup playbook into reusable agent skills — validate, build, launch, and scale your startup with AI across 4 stages. No platform lock-in, any agent can use it.

  • Keel

    kisrafistya/keel Skill

    1★

    Process and judgment skill for AI-assisted building - the anti-slop method that runs before and around the code. Use when starting a new idea or project, when someone asks how we work or how to vibecode without slop, when you need to pressure-test an idea, scaffold the right docs, lock decisions, or gate a build on readiness. The upstream companion to a design skill: keel decides WHAT to build and whether it holds; the design skill makes the UI look made, not generated.

  • Call agent

    cskwork/call-agent/skills/call-agent Skill

    1★ repo

    Delegate one task to a named peer CLI, or when the host lacks the required capability.

  • Bi dash creator

    bcastelino/powerbi-dashboard-generator/skills/bi-dash-creator Skill

    1★ repo

    Composes a multi-visual Power BI dashboard from already generated reports in the generated-reports folder. This skill should be used only when the user explicitly requests a dashboard combining visuals from previously generated reports. It copies visual.json files, validates semantic model consistency, excludes card/slicer/kpi visuals, arranges up to 4 visuals per page in a 2x2 grid, and saves the output to the generated-dashboards folder with a "Dash" suffix in the project name.

  • Suda thesis

    jiadizhunine/suda-thesis Skill

    1★

    Use when generating or editing Suzhou University undergraduate thesis DOCX files, including 苏州大学论文, 苏大毕设, 毕业论文, 论文正文, 文献综述, 文献翻译, 任务书, 中期检查, literature review, literature translation, task book, midterm-check forms, or Chinese academic DOCX formatting that must follow Suzhou University thesis style.

  • Stop slop cn en

    yanyintingyou/stop-slop-cn-en Skill

    no license1★

    Use when editing Chinese or bilingual prose to remove AI-sounding patterns, adapt stop-slop rules to Hermes Agent, and produce natural Chinese writing for research notes, public articles, social posts, documentation, and Telegram-facing replies.

  • Eli engineer

    patrick204nqh/skills/skills/audience/eli-engineer Skill

    1★ repo

    Explains a technical topic to a peer engineer who knows the field. Skips analogies, leads with the data structure, the invariant, or the failure mode. Make sure to use this skill whenever the user says "explain this to an engineer", "ELI-engineer", "technical explanation", "for a senior dev", "skip the analogy", "no fluff", "just the technical version", or is clearly already technical and wants precision over accessibility — even if they don't use those exact phrases.

  • Agent debugging

    wanghong5233/agent-engineering-kit/cursor/.cursor/skills/agent-debugging Skill

    1★ repo

    Systematically debug production Agent failures across UI, API, retrieval, tools, model providers, and async jobs. Use when tests fail, logs show timeout/429/503/parser/RAG/tool errors, behavior drifts from user intent, or user asks to 查日志/定位根因/不要猜. Do NOT use for documenting issues only.

  • Style skill builder

    7ebastian/style-skill-builder/skills/style-skill-builder Skill

    1★ repo

    Create or update reusable writing style skills from source material. Use when Codex needs to analyze writing samples, extract style from samples, brand or editorial guides, comments, interviews, public articles, Notion or Google Docs, then turn the findings into a neutral style guide and package that guide as a Codex or Claude skill. Also use to audit style-guide prompts or writing skills for bias, missing examples, vague guidance, weak anti-patterns, channel rules, accessibility, translation, legal constraints, operational content modules, evals, memory, or validation coverage.

  • Youtube transcript ingestion

    breakthrough-edu/youtube-transcript-ingestion Skill

    1★

    Batch-grab transcripts from any YouTube channel and save them as readable markdown files with clean frontmatter. Guided 5-step flow -- channel, keyword + date filter, output folder, optional context-delta comparison, rate-limit strategy -- using yt-dlp for metadata and markitdown for transcripts. Optionally compares results against your existing notes to surface only what is genuinely new. Trigger phrases -- grab YouTube transcripts, ingest YouTube channel, yt-dlp transcripts, markitdown YouTube, research a creator's videos, build a corpus from a channel, filter content overload from a channel.

  • Anti ai slop

    tazhate/anti-ai-slop Skill

    1★

    Пиши прозу, которая не пахнет нейросеткой. Применять, когда генерируешь любой текст для человека-читателя длиннее одного абзаца - статья, блог-пост, README, email, документация, пост в соцсети, описание PR, маркетинговая копия, лендинг, объяснение в чате на 3+ абзаца. Работает для русского и английского. Триггеры - "напиши пост", "напиши статью", "составь письмо", "сделай описание", "напиши README", "расскажи в стиле...", "опиши проект", любой запрос на long-form контент. НЕ применять для кода, коротких ответов в чате (1-2 предложения), технических команд, тул-вызовов, JSON/YAML конфигов.

  • Clearstreet borrow check

    clear-street/clearstreet-skills/skills/clearstreet-borrow-check Skill

    1★ repo

    Check the borrow / short-sale / margin status of a US stock or ETF — easy-to-borrow flag, threshold-security and short-prohibited flags, long and short margin rates, PTP (publicly-traded partnership) flag, liquidation-only status, and average daily volume — and explain each flag in plain English. Use when the user asks "is X hard to borrow", "can I short X", "what's the margin rate on X", "is X on the threshold list", or "is X a PTP".

  • Swiftui uikit interop skill

    SwiftyJourney/swiftui-uikit-interop-skill Skill

    1★

    Use this skill to bridge SwiftUI and UIKit in either direction. Embed SwiftUI in a UIKit app -- present or child-embed a UIHostingController, put SwiftUI in UICollectionView/UITableView cells via UIHostingConfiguration, or build a widget / Live Activity. Wrap UIKit for use in SwiftUI -- UIViewRepresentable / UIViewControllerRepresentable with a Coordinator for delegates and data sources. Pass data and state across the boundary (init params, @Binding, closures, environment/trait forwarding), fix hosting-controller sizing, and migrate a UIKit AppDelegate/SceneDelegate app incrementally to the SwiftUI App lifecycle. Trigger even when the user doesn't say "interop" -- e.g. "show this SwiftUI screen from my view controller", "use my UIKit map view in SwiftUI", "put SwiftUI in a collection view cell". Do NOT use for pure SwiftUI view code (swiftui-expert), app architecture / composition root (ios-architecture-expert), or general Swift language questions (swift-language-expert).

  • Arcanea mythic overlay

    frankxai/starlight-agent-skills/skills/brand/arcanea-mythic-overlay Skill

    1★ repo

    Add an Arcanea mythic overlay to factual content — a canon-attributed narrative framing (Guardian/Luminor names, mythic register) layered over the real facts, clearly separable from them. Use when giving content an Arcanea mythology flavor, framing a piece in the Arcanea universe, or asked for a 'mythic' treatment.

  • Backlink kit

    Leonewu/backlink-kit/backlink-kit Skill

    1★ repo

    Manual-only backlink footer and directory submission workflow for any web product repo. Use only when the user explicitly invokes `backlink-kit` or `$backlink-kit`; do not use implicitly for generic SEO, backlink, footer, directory, or submission tasks.

  • Ciso ai security

    sarfaraz-munir/Claude-Code-Cyber-agents/.claude/skills/ciso-ai-security Skill

    1★ repo

    Assess AI/LLM systems against OWASP LLM Top 10 and MITRE ATLAS. Evaluate AI governance against NIST AI RMF 1.0, EU AI Act 2024, and ISO/IEC 42001. Build AI red team plans and shadow AI inventory. Use whenever an AI system, LLM integration, or agentic workflow needs security review.

  • Superloop skill

    cskwork/superloop-skill Skill

    1★

    Use when a /loop should hold an orchestrator's delivery to its intent or advance a large project one vertical ticket at a time across scheduled fresh-context ticks. Verify completed work against acceptance criteria, or durably delegate each project ticket to installed supergoal until the frontier is integrated.

  • Code teacher skill

    TazShetu/code-teacher-skill Skill

    1★

    Interactive code-learning workflow for AI coding agents and CLI assistants. Use when the learner wants to deeply understand code, bugs, execution flow, design decisions, edge cases, testing, debugging, or broader application impact.

  • Ai news digest

    buildwitharup/cortex/intelligence/ai-news-digest Skill

    1★ repo

    Pull AI and marketing news from up to 5 RSS sources, filter for relevance to your market, and deliver a 90-second spoken digest with LinkedIn post angles for each story.

  • Article summarizer 2mins

    anarefin/ai-agent-skills/article-summarizer-2mins Skill

    no license1★ repo

    Fast 2-minute read of any article, blog post, or web page: a tight summary, the most critical key points, and 1–2 sharp actions — all strictly from the content, delivered instantly with no back-and-forth. Use this skill when the user wants a rapid digest and says things like "quick summary", "TL;DR", "2 min version", "give me the gist", "what's the takeaway", "brief breakdown", or drops a URL and wants fast signal. Also triggers when the user just shares a URL or article text with no instruction and speed or brevity is implied. Works for any domain.

  • Anti slop frontend

    frankxai/starlight-design-intelligence/skills/anti-slop-frontend Skill

    no license1★ repo

    Use to audit or improve AI-generated frontend UI so it stops looking generic, over-carded, over-gradient, low-density, misaligned, or visually unserious.

  • Metagent

    ianwatts22/metagent/.agents/skills/metagent Skill

    1★ repo

    Analyze tooling, MCP/plugin availability, skill portfolios, and instruction ownership. Use when diagnosing tool or namespace availability; auditing skill provenance, overlap, use, or lifecycle; or deciding where guidance belongs.

  • Accessibility

    tdyzzsp47/claude-skills/skills/accessibility Skill

    1★ repo

    Webアプリ・UIのアクセシビリティ(a11y)対応を設計・実装・テストの全フェーズで組み込むスキル。WCAG準拠チェック、セマンティックHTML修正、キーボード・スクリーンリーダー対応が必要なときに使う。

  • Issue driven github flow

    andybaran/skill-github-flow/skills/issue-driven-github-flow Skill

    1★ repo

    Enforces an issue-driven GitHub Flow with multi-agent planning. Use this skill when the user wants to START or CARRY OUT development work in a git repository — implement a feature, fix a bug, make or change code, kick off a new project, or open/land a PR — including when they don't say "issue", "branch", or "gitflow" (e.g. "let's build X", "fix this bug", "add a feature", "start on Y", "get this project going"). It guarantees every change traces to a GitHub issue, gets a reviewed-and-approved plan before any code is written, lands on a `type/description` branch via a squash-merged PR with Conventional Commits, and never edits `main` directly. Do NOT trigger for purely informational or read-only requests that change nothing — e.g. "what's the git command for X", "explain this function", "show me the diff", "what branch am I on" — just answer those directly.