agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Idea validator

    dersi3/idea-validator-skill/skills/idea-validator Skill

    0★ repo

    Use when the user has a product/feature idea and asks "should I build this", "is there a market", "validate this idea" — or is about to spend days building something unvalidated.

  • Add faqs

    ProstDev/skills/plugins/content/skills/add-faqs Skill

    0★ repo

    Add a FAQs section to the end of a ProstDev blog post for AEO. Use when the user wants to add or update frequently-asked questions / Q&A on a post (the "add FAQs", "FAQ section", "AEO Q&A" ask). Writes an optional `faqs` frontmatter array — answers GROUNDED in the post body, never fabricated — that renders a `## FAQs` section, mirrors into the `.md` endpoint, and emits FAQPage JSON-LD. Verifies with a build.

  • Suite workflow

    BWBlueVector/suite-workflow Skill

    0★

    A four-stage batch-production workflow — Ideate, Build, Self-check, Parallelise — for any request that is a defined suite of similar items rather than a single artifact. Use whenever: (1) the user asks for N of something (10 product listings, 5 video scripts, a batch of thumbnails or posts), (2) a project reaches a "produce the set" milestone, (3) the user says "run the suite workflow" or references Ideate/Build/Self-check/ Parallelise by name. Do NOT use for single-item tasks, judgment-heavy one-offs, or exploratory work — those stay in the normal session flow.

  • Ewo image generate

    RZX00/ewo-skills/ewo-image-generate Skill

    0★ repo

    Generate or edit images. Use whenever the user asks to draw, create, or modify any picture, illustration, logo, poster, icon, or photo — 画图/画一张/生成图片/改图/做个logo/海报/插画/头像. Free to start — new ewo accounts get a trial credit; then pay-as-you-go with your own ewo key (sk-ewo-…), no subscription.

  • Reference atlas

    sapochat/reference-atlas Skill

    0★

    Use when building a visually ambitious site from screenshots and multiple references. Convert references into section-level evidence, resolve conflicts, implement a coherent first pass, and verify it in a real browser.

  • Boss screen and apply

    shixing-1/agent-skills/skills/boss-screen-and-apply Skill

    0★ repo

    Analyze a resume and job-search preferences, screen and verify current BOSS直聘 roles, rank matches, draft natural Chinese greetings under a character limit, present an approval-ready shortlist, and contact recruiters only after explicit confirmation. Use for BOSS直聘 internship or full-time searches involving resume-to-JD matching, city and company-size filters, recruiter activity checks, customized greetings, controlled batch applications, and delivery verification.

  • Checkhere

    Ryan-yang125/checkhere/skills/checkhere Skill

    0★ repo

    Run a local CheckHere browser release check, inspect the generated HTML, Markdown, and JSON reports, fix verified website issues when the user authorizes source changes, and rerun the check to compare results. Use whenever a user asks to inspect, QA, validate, debug, or release-gate a local development site, preview deployment, public URL, AI-built website, mobile layout, broken image, console error, metadata, Lighthouse result, or CheckHere report.

  • Oryxflow

    oryxintel/oryxflow-claude-plugin/skills/oryxflow Skill

    0★ repo

    Build highly effective data science workflows with oryxflow (parameterized tasks, dependencies, caching, reproducible pipelines). Use when working in a oryxflow project - the tasks.py / flow.py / run.py / cfg.py / flow_params.py files, pipeline tasks, workflow runs, loading / cleaning / transforming / analyzing data, output analysis, or publishing/rendering a report notebook to HTML.

  • Nextjs boost

    Sachingit01/nextjs-boost Skill

    0★

    Optimize Next.js (App Router, React 19) apps for Lighthouse (Performance, Accessibility, Best Practices, SEO) and Core Web Vitals without changing the existing UI, UX, animations, or branding. Use when improving Lighthouse scores, Core Web Vitals, hydration/bundle/load performance, or accessibility while keeping the exact visual design and animation behavior. Enforces a design-preservation contract, a 6-phase baseline → audit → optimize → verify workflow, and a visual-parity gate.

  • Family weekend activity finder

    cosmicshuai/family-weekend-activity-finder Skill

    no license0★

    Find weekend (or any-day) activities near the user that suit their family and kids. Use this skill whenever the user asks what to do this weekend, wants ideas for outings with their kids, asks for family-friendly events, things to do near a town/city, or anything like "help me plan something fun for the kids Saturday" — even if they don't say the word "activity." Searches local events from official and reputable sources within a chosen radius, filters by kids' ages and the family's interests, and returns a ranked shortlist with a source link for each so the user can verify details before going.

  • Expert

    bigblueboo/expert/skills/expert Skill

    0★ repo

    Consult GPT-5.6 Pro through the local `expert` CLI for second opinions on coding tasks. Use when the agent needs a high-quality external review, architecture/debugging help, test strategy feedback, implementation plan critique, or analysis of attached code/docs using explicit local files, directories, globs, or stdin. Especially useful for hard, ambiguous, high-risk, or long-running coding questions where a long blocking consult (up to 6 hours by default) is acceptable.

  • Introvert

    DeepakGanapathi97/introvert/skills/introvert Skill

    0★ repo

    Cuts output tokens up to 75% depending on level (standard/max), measured on live model output rather than estimated. Every sentence stays complete and grammatical at every level — never fragments like caveman-style compression. Use when the user says "introvert mode", "quiet mode", "talk less", "be minimal", "less words", "stop rambling", "fewer tokens", or invokes /introvert. A one-off "be brief" is not a trigger.

  • Expose private service

    CervantesVive/agent-skills/skills/infra/expose-private-service Skill

    no license0★ repo

    Expose a private-network-only homelab service over HTTPS through an existing Traefik reverse proxy and Cloudflare DNS, using a trusted wildcard cert. Use when adding a new self-hosted service (Docker Compose or otherwise) that should be reachable only over a private network (Tailscale, WireGuard, plain LAN, a cloud VPC's private subnet, etc.), not the public internet.

  • User machine constitution

    sapochat/user-machine-constitution Skill

    0★

    Use when a person and AI agent need to create, stress-test, ratify, deploy, or amend a bilateral operating constitution covering authority, disagreement, uncertainty, autonomy, approvals, memory, privacy, failure recovery, and verification.

  • Nock mcp

    tomkloevekorn/nock-agent-plugin/plugins/nock/skills/nock-mcp Skill

    0★ repo

    Safely operate a configured NOCK MCP server for support-ticket triage, investigation, creation, updates, internal notes, and customer replies. Use when an agent needs to read or change NOCK tickets through MCP.

  • New app

    euphoriawolf/ai-assisted-app-kit/skills/new-app Skill

    0★ repo

    Bootstrap a brand-new production web app from a proven Cloudflare-native starter. Use when the user wants to start a new app, product, SaaS, MVP, or side project from scratch and wants the same spine as a shipped production SaaS — Cloudflare Workers monorepo, Hono API, Astro SSR + SEO, shadcn design system, Google + magic-link auth, D1/Drizzle, optional queue pipeline, optional/provider-agnostic billing + credits (off by default), email lifecycle, and the living-docs (CLAUDE.md / BRAND.md / TODO.md) methodology. Triggers on "new app", "start a new project", "scaffold an app", "spin up a SaaS", "build me the foundation for X".

  • Apple docs

    martonpaulo/skills/apple-docs Skill

    0★ repo

    Research authoritative, version-aware Apple platform documentation for Swift, SwiftUI, UIKit, AppKit, Foundation, macOS, iOS, Xcode, Apple SDKs, Swift Evolution, compiler behavior, HIG, WWDC, signing, entitlements, capabilities, sandboxing, notarization, privacy manifests, distribution, and platform release changes. Use when implementation correctness depends on Apple API behavior, lifecycle, availability, deprecation, SDK or Xcode version, deployment target, platform conventions, or official guidance. In existing projects, detect Xcode, Swift, SDK, platform, dependencies, and deployment targets first. Prefer official Apple and Swift sources and clearly label forum discussions and community notes as secondary. Do not use for purely algorithmic Swift questions or non-Apple documentation.

  • Video subtitle snapshot

    CoderAha/video-subtitle-snapshot/skill/video-subtitle-snapshot Skill

    0★ repo

    当用户提供本地视频、B站或抖音链接,并要求从指定时间点或短时间段生成字幕截图时使用;也适用于需要使用本人 B站登录状态获取可访问清晰度的请求。

  • Lc rules

    cloudh0/lc-rules/skills/lc-rules Skill

    0★ repo

    Create, audit, or change a workspace's routed rules/ tree and concise agent guidance without overwriting existing project instructions. Use when the user says "lc-rules 스킬 초기화 해줘", asks to initialize or refresh workspace rules, discover conventions across multiple projects, prepare rules for a new frontend/backend project, inherit rules from a reference project, connect AGENTS.md/CLAUDE.md/GEMINI.md to project rules, choose Git or branch conventions, says "브랜치 규칙 전환해줘", or checks an existing lc-rules installation.

  • Clean ui design

    theophile-wallez/clean-ui-design Skill

    0★

    Use when designing or building modern product UI — dashboards, SaaS web apps, admin panels, and mobile apps — in a calm, high-craft, minimal aesthetic. Apply for React/Tailwind/shadcn UI work, app screens, dark or light interfaces, data dashboards, metric cards, sidebars, tables, charts, and iOS-style mobile flows. Triggers on requests like "make it look clean/premium", "shadcn dashboard", "polish this UI", or "clean UI style".

  • Hello

    cympotek/skillcargo/tests/fixtures/sample/skills/hello Skill

    no license0★ repo

    Greet a user in a concise and friendly way

  • Job ai risk check cn

    caoproAI/job-ai-risk-check-cn Skill

    no license0★

    面向中国大陆普通职场人的AI替代、降薪与裁员信号体检 Skill。用户担心工作还能做多久、哪些任务会先被AI改变、老板是否开始压工资或减少岗位、自己应该学什么和如何转型时使用。通过逐题问答或读取用户提供的岗位说明、日常任务、公司变化与招聘信息,区分事实、自述、推断和待验证项,输出任务暴露、公司压力、个人护城河、准备窗口和30天行动表。不得精确预测下岗日期、老板意图、降薪概率或保证用户不会失业。

  • Writing claude 5 prompts

    CodingCossack/writing-claude-5-prompts Skill

    0★

    Use when writing, rewriting, reviewing, shortening, or handing off prompts, system prompts, agent briefs, skills, CLAUDE.md files, or task specifications targeting Opus 5 or Fable 5 — including when a prompt was tuned for an older model, has grown repetitive or over-scaffolded, or is unclear about scope, autonomy, evidence, output length, or stopping. Not for prompts whose primary result is a visual artefact; writing-claude-design-prompts owns those.

  • Bazi base

    AITCX08/xuanji-bazi-skills/skills/bazi-base Skill

    0★ repo

    Use when a 八字命盘需要首次核验,或尚未建立可复用的原局、旺衰、格局、调候、用忌与当前大运基础快照。

  • Barrierefreiheit check

    Appwood/skills/skills/barrierefreiheit-check Skill

    0★ repo

    Websites, HTML und Oberflächentexte auf Barrierefreiheit prüfen – ein technischer Erstcheck am Quelltext nach WCAG 2.1 AA plus den 2.2-AA-Kriterien, mit deutschem Kontext (BFSG, EN 301 549). Findet fehlende Alt-Texte, Kontrast-, Formular-, Tastatur-, Fokus- und Strukturprobleme, liefert je Fund Fundstelle, Fix, WCAG-Kriterium und Schweregrad; auf Wunsch behebt er mechanisch sichere Funde direkt. Nutze diesen Skill bei Stichworten wie „Barrierefreiheit“, „barrierefrei“, „BFSG“, „WCAG“, „Accessibility“, „a11y“, „Screenreader“, „Kontrast prüfen“, „Alt-Texte“, oder wenn eine Website fit für das Barrierefreiheitsstärkungsgesetz werden soll. Der Skill prüft Technik und Texte, gibt aber keine Rechtsberatung und bescheinigt keine Konformität.

  • Interaction proof

    shivam-bm/interaction-proof/skills/interaction-proof Skill

    0★ repo

    Prove mobile interaction quality with evidence-backed audits. Use for a single interaction, a screen or presentation surface, a multi-screen journey, or a pre-release matrix on Apple, Android, React Native, and Expo; also use when design or code review needs observed runtime behavior.

  • Build justfile

    gitt510/agent-skills/skills/build-justfile Skill

    0★ repo

    Create or fully restructure a justfile so its recipes follow the de-facto conventions of prominent open-source justfiles. Use when writing a new justfile, cleaning up or normalizing an existing one, or porting a Makefile to just. Not for adding a recipe or two to an existing justfile — a normal edit covers that.

  • Evidence video factory

    tars1230/evidence-video-factory/skills/evidence-video-factory Skill

    0★ repo

    Create high-quality evidence-driven videos about AI agents, local skills, software workflows, research reports, and project case studies. Use when turning a verified project, Skill, HTML report, code workflow, or structured research result into a narrated Remotion video with mandatory script approval, canonical Chinese subtitles, audio alignment, proxy review, and blocking audiovisual QC.

  • Fulcru

    gsmmediaro/fulcru-agent/skills/fulcru Skill

    0★ repo

    Get a brand named by AI search engines. Use when someone asks why ChatGPT/Gemini/Perplexity recommend competitors instead of them, wants to check if AI mentions their brand, asks about AEO, GEO, answer engine optimization, LLM SEO, or AI search visibility, or wants to write content that AI assistants will actually cite. Runs the full loop: audit a domain, find the questions it loses, write the page that closes the biggest gap, and re-measure.

  • Collage video studio

    DingYi1024/collage-video-studio Skill

    0★

    Create, resume, audit, recover, package, and extend editable editorial paper-collage video projects from a topic, talking-head recording, or portrait/product photo. Use for collage explainers, scrapbook motion pieces, cut-paper ads, zine-style shorts, narrated visual essays, photo-anchored promos, footage restyling, continuing an existing project, rerunning failed shots, connecting a media backend, technical QA, or producing a handoff package.

  • Brief to interface

    thanhaq/interface-compass-skills/skills/brief-to-interface Skill

    0★ repo

    Convert rough product briefs, feature ideas, or vague app and site requests into a concrete interface direction before implementation. Use when Codex needs to infer users, jobs, layout strategy, visual language, density, motion, responsive priorities, and acceptance checks before building a frontend.

  • Deep naming study

    sapochat/deep-naming-study Skill

    0★

    Use when naming work has reached like-but-dont-love, repeated synonym loops, or an inspiration whose effect is hard to reproduce. Recover the mechanism, generate from independent theories, criticize blindly, and test finalists in use.

  • Itpay

    itpay-ai/itpay-skill-hermes/skills/itpay Skill

    0★ repo

    Use ItPay in Hermes Agent when a human wants to discover, compare, buy, receive, recover, or refund a verified paid service. Run the bundled CLI through Hermes terminal tools and preserve one Hermes identity across the complete workflow.

  • Drophere

    Ryan-yang125/drophere/skills/drophere Skill

    0★ repo

    Publish and verify static websites through the official DropHere service at https://drophere.page. Use when a user explicitly asks to deploy, publish, host, share, preview, or turn a local HTML/frontend project into a public URL. Detect and build the correct static output, scan the exact upload directory for sensitive material, create a temporary guest deployment, verify the returned site and its local assets, and deliver a fixed status summary. Supports plain HTML, Vite, React, Vue, Svelte, Astro, Next static export, and other static-site generators.

  • Seo blog admin projects

    Wotaso/seodrafts-agent-skills/skills/seo-blog-admin-projects Skill

    no license0★ repo

    Connect a customer-owned website to SEODrafts, detect its real publishing stack, configure project context, and prepare secure Git, CMS, or webhook publishing.

  • Build ppt from sources

    2233531707/build-ppt-from-sources Skill

    0★

    基于用户上传的 Word、PDF、PPT、表格、图片及文本资料,按“资料检查与分类—PPT大纲确认—逐页文案确认—每批5页生图预览确认—逐页还原可编辑PPT—渲染质检”的门禁流程创建或重做演示文稿。用于用户要求制作汇报PPT、研究汇报、项目汇报、领导汇报、方案汇报,或要求先看效果图再生成可编辑PPT的任务。

  • Learn programming with ai

    Wayne62314/learn-programming-with-ai Skill

    0★

    Use AI as a normal part of learning programming languages, frameworks, architectures, tools, and engineering practices through real development tasks. Use when the user asks to learn while designing, implementing, reviewing, or debugging; requests coach, pair-programming, review, or debugging mode; or wants task completion together with the ability to understand, verify, modify, debug, and maintain the result.

  • Ado pr build monitor

    ridermw/my-skills/skills/ado-pr-build-monitor Skill

    0★ repo

    Portable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.

  • Workplace problem solver

    yingyilin278-tech/workplace-problem-solver/workplace-problem-solver Skill

    0★ repo

    诊断并解决中文职场与求职问题,输出可直接使用的对话话术、书面沟通、判断意见和分阶段行动方案。用于处理向上沟通、同事协作、跨部门冲突、需求拒绝、工作汇报、绩效晋升、职责边界、背锅甩锅、职场关系、转岗离职、劳动争议前的信息整理,也用于处理求职定位、简历优化、JD 匹配、自我介绍、项目叙事、模拟面试、offer 比较与谈薪等请求。也用于把书籍、论文、访谈、课程和视频字幕蒸馏成可检索、可追溯、可执行的职场知识卡。涉及即时人身危险、医疗危机或具体法律结论时,只做风险识别、证据整理和求助路径,不替代专业人士。

  • Alibaba inquiry review

    tanghongming0/renyi-alibaba-ops/skills/alibaba-inquiry-review Skill

    no license0★ repo

    Prepare an Alibaba International Station inquiry review or weekly inquiry meeting from inquiry, IM conversation, salesperson, and follow-up data. Use when asked to review inquiry handling, identify neglected buyers, evaluate salesperson follow-up quality, prepare a weekly inquiry meeting, or produce owner-and-deadline action items. Keep verified data, interpretation, and missing evidence separate; never send messages or change backend data.

  • Keepassxc secrets

    jidckii/agents-keepassxc-skill/skills/keepassxc-secrets Skill

    0★ repo

    Use when a command needs a password, token or API key that lives in a local KeePassXC database — resolve it into the command's environment without ever printing the value. Covers kp:// secret references and kpsec run/check/ls/add.

  • 3d bloom scene

    VJDiPaola/skill-forge/3d-bloom-scene Skill

    0★ repo

    Scaffold a Three.js scene with bloom post-processing, atmospheric lighting, and fog. Use when the user asks for a Three.js scene, bloom or glow effects, or an atmospheric 3D hero visual.

  • Run ab experiments

    shahriarfarzadi/run-ab-experiments-skill/skills/run-ab-experiments Skill

    0★ repo

    Use this skill when a user wants to plan, review, launch, manage, intervene in, ramp, monitor, analyze, or interpret an online controlled experiment or A/B test; choose hypotheses, units, variants, exposure, metrics/OEC, guardrails, sample size, duration, stopping rules, SRM checks, or ship/iterate/stop decisions. Manage the full lifecycle in three modes—plan, manage, and interpret—with explicit cognitive-load reviews and concise, non-repetitive outputs grounded in Kohavi, Tang, and Xu. Always begin with a mandatory question-first interview and context-and-assumptions confirmation before work. Do not use it for observational-only causal claims unless deciding whether an experiment is feasible.

  • Song storyteller

    kosbushe/song-storyteller/skills/song-storyteller Skill

    0★ repo

    Research and write a vivid, fact-checked story about any song in the reader's language, beginning with a clear explanation of what the song is really about. Use when a user provides a song title, artist, lyrics excerpt, recording link, remix, cover, traditional song, or instrumental work and asks for its meaning, translation context, origin, production story, cultural impact, disputed legend, or a music-magazine-style feature.

  • Dont read the code core

    YYshen07/dont-read-the-code-core Skill

    no license0★

    Set up, configure, run, or audit a four-role SwarmForge delivery pipeline with specifier, coder, refactorer, and architect agents plus deterministic quality gates. Use for Java, Python, Shell, R, SQL, or Swift projects on Linux or macOS when humans should approve specifications and evidence instead of reviewing AI-generated code line by line.

  • Skill doctor

    014-code/agent-skill-doctor/skills/skill-doctor Skill

    0★ repo

    Statically audit Agent Skill directories for invalid SKILL.md structure, weak metadata, broken local references, packaging problems, and risky script or instruction patterns. Use when reviewing, validating, publishing, installing, or CI-checking a Codex, Claude Code, or compatible Agent Skill, especially before trusting a third-party Skill.

  • Sherlock

    MJgumbot/sherlock Skill

    0★

    Interrogate a build request adversarially before any code is written — refuse to accept vague requirements, challenge every unstated assumption, and force the user to think the design through until they can state it precisely. Ends by emitting a compiled, detailed build prompt plus a logged list of accepted unknowns. Use this whenever the user asks to build, design, or spec something and wants pushback rather than compliance — triggered by "!sherlock", "!angry", "angry agent", "challenge me on this", "poke holes in this", "interrogate this idea", "stress-test my spec", "am I missing anything", "tell me why this is a bad idea", or any request to review a plan, PRD, ticket, or feature description before implementation. Also use proactively when a build request arrives full of hedges and abstractions ("just a simple app that basically lets users manage their stuff") and building it directly would mean guessing at half the requirements.

  • Sqlite fast migration skill

    AkatQuas/sqlite-fast-migration-skill Skill

    0★

    High-speed cross-machine SQLite database migration using dump + gzip compression + local rebuild. Replaces slow, fragile rsync for GB-sized databases.

  • Manimgl video

    do-gongil/manimgl-skill/skills/manimgl-video Skill

    0★ repo

    Writes math explainer animation code with ManimGL — 3Blue1Brown's own Manim (`pip install manimgl`, `from manimlib import *`). Use when the user wants animated equations, function graphs and coordinate systems, geometric constructions, or ValueTracker-driven continuous change, and when the project targets manimgl / manimlib / 3b1b's engine. Do NOT use for Manim Community Edition (`pip install manim`, `from manim import *`) — the two libraries share class names with different meanings; use a Manim CE skill or the CE docs instead.

  • Compound learning

    Pandasocool/compound-learning/skill/compound-learning Skill

    0★ repo

    基于开放 Agent Skills 结构,将播客、视频、访谈、演讲、课程和文章转化为可行动、可复盘的长期学习系统,并保存到用户选择的 Obsidian 或飞书文档。适用于 Codex、Claude Code、WorkBuddy 及其他支持 SKILL.md 的 Agent。用户提供内容链接、要求提炼内容并沉淀到知识库、建立学习地图、选择性制定长期实践计划,或要求周、月、半年、年度学习复盘及芒格式逆向分析时使用。也用于首次介绍功能、选择存储端、初始化学习根目录、固定笔记格式、检测或恢复连接。

  • Integrations

    luucabg/terseforge/assets/integrations Skill

    0★ repo

    Activate, configure, inspect, or use TerseForge in a coding project. Use when someone asks to "activate TerseForge in this project," use a safe, lean, or ultra preset, change the TerseForge mode, check whether it is active, or make a coding-agent workflow more token-efficient without weakening verification. Match equivalent requests in any language.

  • Outlook native

    mc856/outlook-native/skills/outlook-native Skill

    0★ repo

    Query, search, and extract Outlook email content, compose rich HTML Outlook drafts with inline images, and organize a mailbox with folders and server-side rules. Use this skill whenever the user wants to search their Outlook mailbox, extract or export emails (查邮件/提取邮件/导出邮件), parse .ost or .pst files, summarize email threads, draft/backfill an Outlook email (回填邮件/生成草稿/写邮件到Outlook), or tidy up their inbox (整理邮箱/建文件夹/建规则/归档邮件). Trigger even if the user only mentions "my Outlook", "mailbox", an .ost/.pst file path, or pasting HTML into an email that broke its formatting.

  • Resurrect

    dhruvtoprani/resurrect Skill

    0★

    Recover dormant, abandoned, or unfinished software repositories into evidence-backed product decisions and safe comeback branches. Use when the user invokes $resurrect or /resurrect, runs resurrect with a project name, asks to revive an old repo, scan their GitHub account for unfinished projects, reconstruct original intent, diagnose why a project stalled, compare what changed since then, produce a Resurrection Contract, or execute a bounded Milestone Zero in a repository.

  • Developing with understanding

    outstanding1301/developing-with-understanding/skills/developing-with-understanding Skill

    0★ repo

    Use when AI-generated feature, architecture, or unfamiliar-code changes could outpace the user's mental model, especially across domain behavior, interfaces, data flows, system boundaries, concurrency, authentication, payments, migrations, irreversible changes, or data integrity.

  • Adversarial review

    kevinb361/agent-skills/skills/adversarial-review Skill

    no license0★ repo

    Attempt to falsify a code change's behavioral and operational claims using concrete counterexamples, hostile conditions, and failure sequences. Use as a deeper second-pass review for high-risk, stateful, concurrent, migration, recovery, or production-critical changes.

  • Playwright e2e

    alsovdev/playwright-e2e Skill

    no license0★

    Hybrid E2E UI testing workflow for AI coding agents (Qwen Code, Claude Code, Cursor). Use Browser MCP / Playwright MCP to EXPLORE the live app, write a Markdown test plan, and GENERATE or DEBUG Playwright Test specs — then EXECUTE the suite through the Playwright Test runner as a queue (sequential, with retries) producing HTML + JUnit artifacts and a Markdown summary. Includes a CI/CD template for GitHub Actions with a self-hosted macOS runner. Use when the user wants to create, run, or maintain interface/UI automated tests, needs queue execution with rerun-of-failed, wants Markdown artifacts per run, or wants to wire E2E into CI/CD. Do NOT use MCP as the test executor — MCP is the authoring/debugging layer only.

  • Obsidian vault conventions

    BWBlueVector/obsidian-vault-conventions Skill

    0★

    Enforces Obsidian-compatible writing conventions for a Claude Code memory vault that a human also browses directly in Obsidian, not just an AI-facing memory store. Use this skill whenever: (1) starting a new ongoing project and deciding flat-file vs. project-folder, (2) creating or editing any file inside that memory directory (project_*.md, playbook_*.md, howto_*.md, lesson_*.md, feedback_*.md, an index file), (3) adding a wikilink between memory files, (4) adding tags or aliases, (5) immediately after writing to a memory file, to verify the frontmatter wasn't silently reformatted.

  • Autoxeo creator orchestrator

    stella-dust/autoxeo-marketplace/plugins/autoxeo-creator/skills/autoxeo-creator-orchestrator Skill

    0★ repo

    Route AutoXEO Creator requests across GEO requirement diagnosis, custom skill/plugin blueprinting, scaffolding, marketplace packaging, and service handoff.

  • Cvitae growth

    Isasola/cvitae-growth-skill/cvitae-growth Skill

    0★ repo

    Audit, redesign, and improve business websites across visual design, UX, accessibility, technical SEO, conversion, and local-market relevance. Use when Codex must review a URL, screenshot, HTML, or frontend repository; diagnose generic AI-generated UI; prioritize website improvements; redesign without cloning references; localize a site for a target market; or turn findings into implementation-ready changes.

  • Release assistant

    Octo-o-o-o/release-assistant Skill

    0★

    Run end-to-end app store release campaigns across Apple App Store, Google Play, and Huawei AppGallery (HarmonyOS NEXT), including China-market compliance (ICP App 备案, software copyright 软著, AI-generated-content declaration, privacy labels). Use when asked to publish/submit/release a mobile app to any store, prepare store listings or screenshots, fill privacy or data-safety forms, handle a store rejection (ITMS-*, Guideline *, AGC 驳回), set up signing or store credentials, plan a multi-store launch, or run post-approval actions. Trigger phrases include publishing to App Store / TestFlight / Google Play / Play Console / AppGallery / AGC, app 上架, 提审, 应用商店发布, 应用市场提交, ICP 备案, 软著, store rejection, release checklist. Not for desktop app distribution or backend deployments.