The catalog
609,856 rows, by stacks then stars
mykaro/ai-skills/skills/flet-best-practices Skill
no license2★ repoIdiomatic guide for Flet 1.0 applications. Covers declarative UI, hooks, observable state, services, async execution model, and breaking API changes from v0.x. Use this skill to write modern Flet code, migrate imperative apps to reactive patterns, apply breaking changes correctly, and avoid common pitfalls.
Aidress skill find verified invoice generation agent
Aidress-ai/aidress-skill-find-verified-invoice-generation-agent Skill
2★Find a Verified Invoice Generation Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for finance agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
spellsaif/cold-codebase Skill
2★Analyze any abandoned, legacy, or inherited codebase and produce a Revival Document — a health report, revival plan, and contribution guide in one. Trigger when someone says "analyze this repo," "I inherited this codebase," "is this worth reviving," "help me understand what I've got here," "I found an abandoned repo," "this hasn't been touched in years," "I want to pick up where someone left off," "can this codebase be saved," or shares a GitHub link to a dormant project. Also trigger when someone is taking over a project from a previous dev, inheriting technical debt, or asking "where do I even start" with an existing codebase.
TimJJTing/Claudesay/skills/claudesay Skill
2★ repoTriggers when the user asks to "turn on claudesay", "turn off claudesay", "enable/disable the character", "toggle claudesay", "claudesay status", "show/hide the character", "enable ascii companion". Do not trigger for unrelated uses of "character" (e.g. unrelated variable names) or generic "turn off" requests that do not mention claudesay.
cmg8431/claude-dejavu/plugin/skills/dejavu-rules Skill
2★ repoManage dejavu rules manually. Use when user says "add a rule", "remember this", "edit rule", "remove rule", "이거 기억해", "룰 추가해", or wants to manage CLAUDE.md rules through conversation.
johanes/drydocs/plugins/drydocs Skill
2★ repoSlim your CLAUDE.md into a lean index and move the detail into a well-organized docs/ folder, so the always-loaded context stays small (token savings) and detail loads on demand. Classifies with MOC (Maps of Content) + PARA (Projects/Areas/Resources/Archives) + Zettelkasten (atomic, linked notes). Non-destructive (leaves your CLAUDE.md untouched; writes dry-CLAUDE.md), idempotent, git-reversible. Use when a CLAUDE.md is too long, or the user says "slim my CLAUDE.md", "my CLAUDE.md is huge", "organize CLAUDE.md into docs", "make CLAUDE.md a lean index". This is the subtractive counterpart to onboarding skills that *add* structure — drydocs *removes* inline bulk and leaves pointers.
Aidress skill find verified document summarization agent
Aidress-ai/aidress-skill-find-verified-document-summarization-agent Skill
2★Find a Verified Document Summarization Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for research agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
ndisisnd/cook Skill
2★Keyword-driven orchestrator for this repository's coding standards. Receives a code-task summary from the invoking agent, extracts keywords, matches them against the global concern index and the relevant domain indexes, loads only the matched rules, and returns a single compiled standards payload.
calneymgp/solodev/skills/dev-brainstorm Skill
2★ repoGrilling estruturado para estressar uma ideia de feature ANTES de planejar. Traduz ideia falada/solta em requisitos, classifica o tamanho (S/M/L), faz uma pergunta por vez sempre com recomendação inline, explora o codebase para resolver dúvidas sem perguntar, captura decisões em BRIEF.md ao vivo e fecha com radar de riscos. Use quando o usuário trouxer ideia bruta de feature, disser "/dev-brainstorm", "vamos brainstormar", "preciso estressar essa ideia", "me grilla", "vamos discutir antes de planejar", ou aparecer com um problema sem solução clara.
soumyakantabera/graphifychat Skill
2★Turn any conversation into a queryable knowledge graph. Three-layer portable memory file: TRON (structured input+output capture with emotion, psychology, intent — every turn), Sparse6 (layered relational graph with community detection, hyperedges, confidence scores — every turn), GRAPH_REPORT (god nodes + surprising connections + 4-5 bullet summary — auto T1-T3, on demand after). Trigger on: "/graphifychat", "save context", "update memory", "track conversation", "export for another AI", "show memory", "export session", or proactively on complex multi-step conversations. CALLING RULE: if invoked at start of chat → TRON+Sparse6 update every turn automatically. If invoked mid-conversation → update only when explicitly called again. Always output as raw fenced code block — never rendered Markdown.
zhoujiegg123-svg/official-docx-cn-skill/official-docx-cn Skill
2★ repoCreate or revise Chinese official-style Word documents from Markdown or DOCX content, using stable formal-document formatting rules such as title hierarchy recognition, Founder GBK Chinese fonts, Times New Roman for Latin text and digits, fixed 28 pt line spacing, and standard odd/even page number layout. Use when the user asks for 公文格式, 按公文格式排版, 转成公文格式 Word, 正式公文排版, 整理不规范的 Word, 述职述廉报告, 述责述廉, 汇报材料, 领导讲话稿, 正式机关文稿, or wants a Markdown or Word file converted into a compliant .docx.
agenkin/telemetrydeck-analytics/skills/analytics Skill
2★ repoQuery a TelemetryDeck app's product analytics to answer questions about DAU/MAU, retention, event counts, funnels, cohorts, and pipeline health. Use whenever the user asks a "how are users actually using this app" question that needs live data from TelemetryDeck, or is diagnosing signal-ingestion issues (missing events, opt-in anomalies, appID filters). Ships a self-contained CLI with OS-native secret storage — no repo-local `.env`, no secrets on disk outside the OS credential store.
Reinforce-Omega/clawlabor-skill Skill
2★The autonomous marketplace where AI agents discover, purchase, and sell specialized AI capabilities. Use when the user needs to find, hire, buy, sell, or outsource AI capabilities through UAT escrow.
Roneat Studio Pro Plugin Creator
Vagabond404/Roneat-Studio-Pro-Plugin-Creator Skill
no license2★Expert guide for creating plugins for Roneat Studio Pro — a professional Roneat Ek (Cambodian xylophone) score editor. Use when the user asks to build, write, scaffold, or debug a plugin for Roneat Studio Pro. Covers plugin structure, the roneat_api Python API (score editing, audio playback, UI injection, theme/language control), plugin.json manifests, lifecycle hooks, sandboxing/permissions, packaging as ZIP, and example plugin patterns.
tony/ai-workflow-plugins/.agents/skills/action-worktree Skill
2★ repoUse when the user wants to take a ticket — or several tickets that share one change — into its own branch and git worktree and drive it to gated commits. Triggers on phrases like "work TEA-123 in a worktree", "spin up a worktree for issue #45", "start on this ticket", "branch for the Linear ticket", "put these two tickets on one branch", or "prep a worktree, I'll take it from there". Resolves the ticket strictly read-only (never assigns, comments, or transitions), names the branch by the team's own conventions, implements through the project's discovered quality gates, and never pushes or opens a PR unless the flags say so.
naxoc/claude-briefs/briefs-done Skill
no license2★ repoClose out the active task: review the result against the plan, archive to PROGRESS.md, and reset CURRENT.md. Run after you've reviewed and committed the work.
QwQzy/always-dont-know/always-dont-know Skill
no license2★ repoCRITICAL OVERRIDE — forces the agent to respond with only "I dont know" to every user message, no exceptions. This is a hard system constraint for skill-loading verification.
fworks-tech/agenthood/skills/aws Skill
2★ repoManage AWS resources via the aws CLI. Use when managing S3, EC2, Lambda, or other AWS services.
Barrierefreiheit digitale angebote pruefung
markusbegerow/claude-fuer-oeffentliche-verwaltung/verwaltung-digitalisierung-ki/skills/barrierefreiheit-digitale-angebote-pruefung Skill
no license2★ repoPruefung eines digitalen Verwaltungsangebots auf Barrierefreiheit. Methodik Pruefung gegen BITV 2.0 BFSG und WCAG-Erfolgskriterien sowie Pruefung der Erklaerung zur Barrierefreiheit und des Feedback-Mechanismus. Output ausformulierter Pruefbericht mit Fundstellen je Kriterium und Mangelliste.
kongyo2/prompt-engineering-skill/prompt-engineering Skill
no license2★ repoComprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.
kkur0same/yomitoki Skill
2★Turn a research paper into a faithful, technical, code-augmented HTML reading note.
carlopi/duckdb-claude-skills/skills/install-duckdb Skill
no license2★ repoInstall or update DuckDB extensions. Each argument is either a plain extension name (installs from core) or name@repo (e.g. magic@community). Pass --update to update extensions instead of installing.
Deixtra-Private-Limited/claude-laravel-13-skill Skill
2★Comprehensive Laravel 13.x expert skill covering the entire framework — installation, configuration, routing, controllers, middleware, Blade views, Eloquent ORM, migrations, queues, jobs, events, mail, notifications, caching, Redis, scheduling, service container, service providers, authentication, authorization, AI SDK (agents, tools, structured output, streaming, embeddings, images, audio), MCP servers, Laravel Boost, JSON:API resources, vector/semantic search, PHP attributes (#[Middleware], #[Authorize], #[Tries], etc.), queue routing, Cache::touch(), and all Laravel 13 breaking changes and upgrade patterns. Trigger this skill whenever the user mentions Laravel 13, Laravel AI SDK, Laravel MCP, Laravel Boost, Laravel agents, Laravel vector search, Laravel embeddings, whereVectorSimilarTo, JSON:API resources, PHP attributes in Laravel, queue routing, PreventRequestForgery, Cache::touch, or any Laravel backend development task. Also trigger for upgrading from Laravel 12 to 13, or any question about what's new in Laravel 13. This skill supersedes the older laravel-backend-expert skill for Laravel 13 projects.
Aidress skill find verified crm management agent
Aidress-ai/aidress-skill-find-verified-crm-management-agent Skill
2★Find a Verified Crm Management Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for sales agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
pmcoe-ai1/pmp-tutor-skill Skill
no license2★PMP / CAPM / PMI-ACP / PMI-CP study companion built by PMCOE LLC — a PMI Authorized Training Partner. Use when the user asks about the Project Management Professional (PMP) certification exam, the Certified Associate in Project Management (CAPM), PMI-Agile Certified Practitioner (PMI-ACP), or PMI Construction Professional (PMI-CP). Covers the 2021 Exam Content Outline, eligibility requirements, scenario-based question practice, the 50/50 predictive-vs-agile mix, GI Bill funding (Chapter 31 / Chapter 33), WEAMS verification for veterans (facility code 46P05243), and PMI Authorized Training Partner standards. Skip for unrelated project management tooling questions (Asana, Jira, Microsoft Project), generic agile-methodology debates without an exam-prep angle, software engineering certifications, or non-PMI credentials (Six Sigma, ITIL, PRINCE2, CISSP).
Rahilyw/learning-buddy/learning-buddy Skill
2★ repoAn AI coding learning partner using Socratic questioning and the 4Ds methodology — never gives away direct answers. Trigger when the user wants to *understand*, not just *solve*: phrases like "help me understand", "walk me through", "I don't just want the fix", "I want to learn why", "don't write the code for me", or "be my coding buddy / learning partner". Also trigger for students and self-learners (mentions assignments, courses, professor, bootcamp, exam, or self-teaching), interview prep (LeetCode, coding challenges) when they want to understand patterns not just get a solution, and design/architecture questions framed as learning to think correctly. Do NOT trigger for quick one-off questions, production work, code reviews, or when the user just wants a working snippet fast.
hackermanishackerman/claude-skills-vault/.claude/skills/beautiful-code Skill
2★ repoMulti-language code quality standards for TypeScript, Python, Go, and Rust. Enforces type safety, security, performance, and maintainability with progressive enforcement. Use when writing, reviewing, or refactoring code across any of these languages.
ezra-y/touqi-todo Skill
2★帮用户整理人生中重要的事:遗愿、交代、账号密码、想对谁说的话。用于用户想要记录遗愿、交代后事、整理数字遗产、给家人朋友留话、标记谁能看什么内容、回看整理进度、或者导出整理成果的场景。当用户提到死亡准备、身后事、遗书、遗嘱内容整理、账号交接、给家人留言、生前安排等话题时,应主动使用此技能。
glowElephant/context-forge/.claude/skills/context-forge Skill
2★ repoUse when starting a brand-new project that needs AI-agent context (CLAUDE.md, AGENTS.md, skills, rules, MCP, spec workflow) set up from day one. Discusses goals → matches catalog know-how → creates a new GitHub repo with everything wired in. Keywords: harness engineering, bootstrap project, context engineering, scaffold repo, start project, agent-ready repo.
FynePool/job-hunter-template/.claude/skills/agent-config Skill
no license2★ repoOnboarding guidato per il sistema Job Hunter. Usa questa skill quando un nuovo utente vuole attivare il sistema di ricerca lavoro autonoma: ingerisce il CV, fa domande su vincoli/preferenze (trasferimento, remoto, retribuzione, preavviso, diritto al lavoro, lingue), produce master-profile.yaml e il primo intento di ricerca in searches/ nel repo del sistema, genera e attiva la config della routine job-watch. Trigger su qualsiasi richiesta di avviare/configurare/inizializzare il sistema o la ricerca lavoro, anche breve o generica — es. "inizializza il progetto", "salva queste skill e configurami", "iniziamo a fare job-hunting", "configurami il sistema". Non richiedere che l'utente nomini "agent-config" o "onboarding": il segnale è l'intento di avviare il processo. NON usarla per modificare un search-profile già esistente ("aggiorna il mio profilo di ricerca", "cambia i ruoli/le location"): per quello esiste la skill job-search-profile.
IdkwhatImD0ing/hackathonstarterkit/.agents/skill-improvement-workspace/baseline-skills/blog-writer Skill
no license2★ repoWrite new blog posts using the rich content block system. Handles topic ideation, SEO metadata, content structuring with visual components (callouts, stats, step lists, checklists, code snippets, quotes, pro/con tables, link cards), and integration into the blog data file. Use when adding a new blog post to the site.
Biefeld brown electrogravitics visualizer
VRIL-LABS/skill-jam/featured-skills/biefeld-brown-electrogravitics-visualizer Skill
no license2★ repoDesigns a real-time 3D visualization of the Biefeld-Brown effect — asymmetric high-voltage capacitor thrust, ionic wind flow, electric field stress-tensor gradients, and electrogravitics lift vectors. Invoke when asked to visualize T.T. Brown's electrogravitics, lifter devices, asymmetric capacitor thrust, or ionic wind propulsion in 3D.
cheickmec/smellcheck/plugins/python-refactoring/skills/python-refactoring Skill
2★ repoPython refactoring catalog with 83 patterns covering immutability, class design, control flow, architecture, OO metrics, and Python idioms. Analyze code for smells and apply numbered refactoring patterns with before/after examples. Use when the user invokes /refactor or explicitly asks to refactor, clean up, or improve Python code quality.
The same file is in 2 other repositories
indigokarasu/spot Skill
2★Use when checking appointment availability, booking services, monitoring for openings, or discovering venues at salons, spas, and restaurants. spot.discover finds and compares venues via Yelp before booking. Supports Acuity Scheduling, Square Appointments, Resy, Tock, SevenRooms, OpenTable, Meevo, Vagaro, Mindbody, Fresha, StyleSeat, Calendly, Yelp Reservations, Booksy, GlossGenius, SimplyBook.me, Boulevard, Mangomint, DaySmart, ResDiary, and Eat App. Integrates with ocas-vpn for bot block bypass. NOT for general travel planning (use ocas-voyage), calendar sync (use ocas-sands), restaurant reservations on unsupported platforms. Trigger phrases: 'book an appointment at', 'check availability at', 'when can I get a [service]', 'find me a slot at', 'is [venue] available', 'watch [venue] for openings', 'alert me when [venue] has availability', 'monitor [venue]', 'find a restaurant in', 'compare salons near', 'discover [type] near'.
vahagn-madatyan/netsec-skills-suite/skills/acl-rule-analysis Skill
2★ repoVendor-agnostic ACL and firewall rule analysis with shadowed rule detection, overly permissive rule identification, unused rule discovery, redundant rule flagging, and rule ordering optimization. Covers ACLs (Cisco/JunOS/EOS) and firewall policies (PAN-OS/FortiGate/CheckPoint).
The same file is in 1 other repository
Syncfusion angular docx editor
syncfusion/docx-editor-sdk-skills/skills/syncfusion-angular-docx-editor Skill
no license2★ repoUse this skill when a user asks how to generate, integrate, or implement a Word‑like document editor in Angular using Syncfusion. Trigger it for requests involving the Syncfusion Angular Document Editor, Angular‑based editor integration, document editing and formatting, comments and track changes, working with tables and images, managing headers and footers, applying document protection, and building end‑to‑end document workflows in Angular applications.
light-merlin-dark/skill-sync/skills/skill-sync Skill
2★ repoSync local repo-backed agent skills across installed harnesses such as Codex, Claude Code, Cursor, Gemini, Hermes, Grok, and related tools. Use when a user wants one source of truth for local SKILL.md files, needs drift checks or backup/restore for harness skill roots, or wants to inspect which harnesses and skills are currently detected.
Abdullah4AI/personal-shopper-skill Skill
no license2★Smart product research assistant using the Diamond Search methodology (7 specialized agents across 3 layers). USE WHEN: user wants a product recommendation, shopping advice, "what's the best X", "compare X vs Y", "find me a good", product comparison, buying decision help, "is this a good deal", "should I buy X or Y", "أبغى أشتري", "وش أفضل منتج", "قارن لي", "ابحث لي عن", "مقارنة منتجات". DON'T USE WHEN: user wants price tracking over time, order placement, returns/refunds help, market analysis for business entry (use mckinsey-research), general web search not about purchasing, reviewing or troubleshooting a product they already own, comparing companies as businesses. EDGE CASES: "what's the best laptop" → this skill. "what's the laptop market size" → mckinsey-research. "compare two products by specs" → this skill. "compare two companies competitively" → mckinsey-research. "is this a good deal on Amazon" → this skill. "analyze the deals market" → mckinsey-research. "أبغى أشتري لابتوب" → this skill. "أبغى أفتح متجر لابتوبات" → mckinsey-research. Output: Clear product recommendation with best price, availability, alternatives, and expert validation. Success: User gets an actionable buying decision backed by multi-source research, expert analysis, and real pricing. Inputs: Product type, budget (optional), use case, preferences. Tools involved: sessions_spawn (sub-agents), web_search/camofox/exa (search), web_fetch (page extraction).
t4sh/dotfiles/agents/skills/3d-spatial Skill
no license2★ repoUse when working in Blender, Unity 3D, Unreal Engine, Cinema 4D, VR/AR applications, or any three-dimensional animation work.
arpitexplores/super-industry-ops Skill
2★Industry-specific operations: logistics, manufacturing, procurement, and quality workflows.
The same file is in 1 other repository
Eim-aa/pdf-visual-translate-zh Skill
2★英文 PDF 版式保真中文翻译 Skill:为可提取文本的英文 PDF 创建中文交付件,尽量保留页数、页面尺寸、表格、图表、颜色、页眉页脚和整体布局。适用于研报、公告、白皮书、合同和图表密集型 PDF;目标是可视中文交付,而不是干净的中文可搜索文本层。
WhizZest/find-skills/skills/clawhub-cli Skill
no license2★ repoComplete ClawHub CLI reference for searching, installing, updating, publishing, and managing agent skills from clawhub.ai. Use when working with the clawhub CLI: installing or updating skills, publishing new versions, syncing a skills directory, inspecting skill metadata, managing ownership transfers, or troubleshooting install/update/sync behavior. Triggers on clawhub, clawdhub, skill install, skill publish, skill sync, clawhub login.
Sagargupta16/craftsmanship/skills/audit Skill
2★ repoUse when setting up a new repo, auditing an existing one for hygiene issues, or before publishing a project. Covers .gitignore, .env.example, README, LICENSE, CONTRIBUTING, and detecting committed secrets.
darviewyrl/pawn-skills Skill
2★Essential Pawn best practices, high-performance optimization techniques, and architectural guidelines for both SA-MP and open.mp. Use when writing new systems, refactoring code, optimizing server lag, or working with databases and streamer plugins. Triggers on: pawn, samp, open.mp, y_hooks, mysql, optimization, streamer.
interskh/product-teardown-skill/product-teardown Skill
no license2★ repoAnalyzes products and companies by synthesizing data from pricing pages, app store reviews, job postings, SEO signals, social media, homepage UI, and first-party demo plus third-party review videos into structured product intelligence. Produces feature comparison matrices scored across 12 dimensions, SWOT analyses, positioning maps, UX audits backed by visual evidence, pricing model breakdowns, action item roadmaps, and stakeholder presentation templates. Use when conducting competitor analysis, comparing products against competitors, researching the competitive landscape, building battle cards for sales, preparing for a product strategy or roadmap session, responding to a competitor's new feature or pricing change, performing a quarterly competitive review, or studying a product's UI/UX patterns and design choices from public sources (homepage and demo videos).
cskwork/postgres-intelligence Skill
2★Use when an LLM agent needs to connect to PostgreSQL, inspect schemas, run safe SQL, translate natural language into PostgreSQL queries, or analyze query performance without exposing credentials.
GlamgarOnDiscord/claude-saas-blueprint/.claude/skills/apex Skill
2★ repoWorkflow APEX — Analyze, Plan, Execute, Examine. À invoquer avant une tâche non triviale ou quand le contexte est flou.
Iabstergo1/pdf-to-study-kb/.agents/skills/ingest Skill
2★ repoEnd-to-end add a new external source (PDF/DOCX/PPTX/Markdown), deterministically adopt an already-populated Obsidian vault baseline, or register selective reuse from another published pipeline vault. Use for "add/ingest/index/weave this source", "adopt/onboard this existing vault", or "reuse this published source". Normal ingest preprocesses and writes proposed pages; legacy adoption and external-vault reuse are separate zero-LLM branches. Read-only requests like "summarize/explain/translate this" must never trigger it.
nanxiaoyao/network-huawei-skills/attack-defense Skill
2★ repoThis skill should be used when the user asks to configure or troubleshoot Huawei USG6000E firewall attack defense features. Covers Anti-DDoS (SYN/UDP/HTTP flood), single-packet attack defense, URPF source-address validation, per-IP connection rate limiting, traffic-based dynamic CAR, and SACG admission control linkage. Applicable platforms USG6000E V600R007C20+ and USG6000/USG9500/NGFW Module V500R005C20+ (CLI syntax identical between versions).
shihabshahrier/skill-builder/skills/skill-builder Skill
2★ repoBuild or audit any AI agent skill from a plain-English description. Generates SKILL.md, references, hooks, and full marketplace repo scaffold. Supports all 32+ agents in the Agent Skills open standard.
dewdad/skill-creator Skill
2★Author and audit Agent Skills (SKILL.md files) for OpenCode and skills-compatible agents (Claude Code, Cursor, Codex, Copilot, Gemini CLI, Goose). Triggers on: "create a skill", "new SKILL.md", "skill for this workflow", "audit this skill", "review my SKILL.md", "improve skill description", "skill not triggering", "make this reusable across sessions", "skillshare new skill". Covers frontmatter, progressive disclosure, trigger-keyword design, validation, and common pitfalls.
jacob-balslev/skills/skills/agent-ops/ai-native-development Skill
2★ repoUse when reasoning about agent autonomy levels, designing auto-improve loops, evaluating AI-generated code quality, or measuring agent productivity in an LLM-assisted codebase. Covers Karpathy's three eras of software (1.0 explicit / 2.0 learned / 3.0 natural-language), the vibe-coding-vs-agentic-engineering distinction, the 0–5 autonomy slider with task-type recommendations, the one-asset / one-metric / one-time-box AutoResearch loop, Software 3.0 productivity metrics, and the documented quality regressions of ungated AI-generated code (the 'vibe hangover'). Do NOT use for choosing a specific autonomy-loop topology (use `agent-engineering`), for the per-prompt authoring discipline (use `prompt-craft`), or for reviewing the AI-generated code that comes out of a Software 3.0 workflow (use `code-review`).
Enryun/SwiftUI-Architecture-Agent-Skill/skills/swiftui-architecture Skill
2★ repoScaffold and extend SwiftUI apps using Factory, Manager, UseCase, ViewModel, and View layers with protocol-first dependency injection. Use when starting a new SwiftUI project, adding a feature module, reviewing layer boundaries, folder structure, or clean architecture on iOS or macOS.
acentrist/web-clone-skills/web-clone Skill
2★ repoUse when a user asks to clone, mirror, replicate, rebuild, copy, or convert a single public webpage URL into local frontend code; when extracting webpage layout/assets/styles/interactions with Playwright; or when generating a Vite React Tailwind page clone with local verification.
ZJtoast/kernel-profiler-skill Skill
no license2★Kernel-only GPU profiling workflow. Use for profiling, diagnosing, comparing, or reporting individual GPU kernels without expanding into end-to-end system tracing.
Zelray/hermes-model-router Skill
2★Intent-based model routing overlay for Hermes Agent. Use when a request should be mapped to a configured provider/model route such as image-prompt to Qwen 4B, debugging to Sonnet, cheap routine chat, or a user-defined route in skills.config.model-router.routes.
carpo9984/GQXJ/skills/gaoqian-style Skill
no license2★ repo搞钱学姐品牌视觉风格,用于生成品牌物料(HTML/海报/招商手册/PPT等)。粉白主色调、综艺感、女性向设计。
danieloleary/design-md-for-codex/examples/minimal-repo/.agents/skills/design-system Skill
2★ repoUse when building, editing, reviewing, or refactoring frontend UI. Read the repository DESIGN.md first and apply its colors, typography, spacing, components, accessibility rules, and do/don'ts.
zkassing/record-live Skill
no license2★多平台直播间录制。支持抖音、小红书。两种模式:(1) 直播间链接 → 立即录制;(2) 用户主页(仅抖音)→ 监听开播,开播自动录制、下播自动结束并继续监听。带本地 dashboard 网页(实时进度、书签、停止)。触发词:"录制直播 / 录这个直播间 / 录抖音 / 录小红书 / 监听开播 / 蹲守开播 / record douyin live / record xiaohongshu"。
marcelolebre/anti-slopper Skill
2★Write like a human and avoid AI slop. Use this skill whenever you are producing prose for a person to read: PR descriptions, commit messages, docs, READMEs, comments, design notes, Slack/email replies, blog posts, tweets and X/LinkedIn posts, launch announcements, release notes, or any explanatory text. It gives proactive rules for drafting natural writing the first time, plus a fast self-audit to catch AI tells (inflated significance, promotional tone, -ing padding, rule of three, em dashes, copula avoidance, hedging, signposting, generic conclusions, buried ledes and engagement bait in social posts, and negate-then-correct lines like "this isn't X, it's Y") before you ship. Includes a banned-phrase list. Based on Wikipedia's "Signs of AI writing".