The catalog
610,045 rows, by stacks then stars
hexiaofeier/sha-hao-yong Skill
3★Create a read-only, plain-language HTML installation brief for a candidate Skill or related AI capability asset. Use when the user provides a URL, repository, ZIP, folder, README, plugin, MCP, CLI, app, or installation guide and asks what it does, how hard it is to install or use, what it costs, how much Token or risk it involves, whether it fits a need, or whether it is worth installing. Do not use for security certification or automatic installation.
googlarz/vibe-safe Skill
no license3★Use when a non-technical contributor (PM, designer, researcher) is about to write, commit, or merge AI-assisted code in a shared codebase and wants to catch the specific ways vibecoding goes wrong before they become incidents.
zj021033/senior-mode Skill
3★Make your coding agent operate like a senior engineer instead of an eager junior — and stop it from cosplaying one. Activate for any real engineering work: debugging, planning, implementing, reviewing, refactoring. Five gates that fire at decision points: (A) a user CLAIM → check it before building on it; (B) a PLAN → pressure-test it against the goal and feasibility; (C) a BUILD request → pin the goal before writing code; (D) something BROKEN → find the root cause, never a band-aid; (E) every reply → cut the slop. Plus a hard boundary that blocks manufactured pushback, needless questions, and ceremony on trivial work. Triggers on: "fix this", a bug or failure, a plan to review, a feature to build, "is this the right approach", or whenever the agent is about to agree, patch, guess, or pad.
mrDesign-ww/vault-os/shell/claude/skills/atlassian-admin Skill
3★ repoAtlassian Administrator for managing and organizing Atlassian products (Jira, Confluence, Bitbucket, Trello), users, permissions, security, integrations, system configuration, and org-wide governance. Use when asked to add users to Jira, change Confluence permissions, configure access control, update admin settings, manage Atlassian groups, set up SSO, install marketplace apps, review security policies, or handle any org-wide Atlassian administration task.
The same file is in 3 other repositories
cuongdev/indie-app-shipping/indie-app-shipping Skill
3★ repoA solo/indie playbook for shipping small mobile apps fast on iOS/macOS (App Store) and Android (Google Play), testing real demand, and deepening only the apps that show signal. Use whenever the user is shipping a mobile app — scaffolding app structure, wiring onboarding/settings/paywall/restore/legal screens, writing or reviewing store metadata (title, subtitle, keywords, short/long description, promo text), planning screenshots/feature graphics, running a pre-submission Apple App Review or Google Play policy compliance check, writing review notes, setting up Play closed testing, handling a rejection, or deciding which shipped apps deserve more investment. Trigger even when the user doesn't say "checklist" — any mention of a new app idea, App Store or Play Store submission, App Store Connect, Play Console, IAP/subscription/paywall, screenshots, app rejection, ASO, Data safety form, closed testing, or the "ship many small apps" workflow should pull this in.
cablate/audience-outcome-lens Skill
3★Use a lightweight audience-and-outcome frame before creating or revising work whose usefulness depends on who receives, uses, or is affected by it, their situation, and what should become different. Apply to people-facing content, plans, communications, experiences, recommendations, decision-oriented analysis, and user-facing behavior. Infer from context, surface only consequential unknowns, then use the relevant domain or format skill. Do not invoke for work whose acceptance criteria are objective and audience-independent, such as exact transformations, calculations, factual lookups, or bounded technical checks.
rdsolod-ui/insta-parcel-skill/skills/insta-parcel-skill Skill
3★ repoResearch and validate public Instagram creators for influencer marketing and creator lead lists. Use for Instagram influencer discovery, creator prospecting, profile vetting, audience-segment evidence, follower thresholds, engagement-rate (ER) calculation, CSV validation, deduplication, manual review, or safe publication of a reviewed creator database. Works with public or permissioned sources and authorized browser sessions. Do not use for private profiles, sensitive-trait inference, covert surveillance, anti-abuse bypass, automated engagement, or unreviewed outreach.
LechuanWANG/ir-skill Skill
no license3★Evidence-led China and cross-asset investment research. Use for A-share, Hong Kong, or US equity research; all-market financial-statement screening; China macro analysis; ETF, fund, index, futures, spot commodity, option, convertible-bond, or foreign-exchange research; technical or catalyst screening; entry or exit analysis; portfolio review; price or news attribution; research planning; decision evaluation; or research-source archival. Use persistent research memory only when the user explicitly asks to read, reuse, save, ingest, or update it.
conorbronsdon/demo-gif-skill Skill
3★Record, render, optimize, and embed a demo GIF in a repo's README. Use when asked to add a demo gif, record a demo, show the tool in action, or make a README more visual.
nbialk/quiver-cli/.agents/skills/code/improve Skill
3★ repoSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
The same file is in 5 other repositories
AlexAnsart/demo-studio/skills/demo-setup Skill
3★ repoOne-time setup that analyzes the current project and configures it to use the film-demo / narrate / sync-narration / produce-video skills — detects the dev server and framework, asks only when necessary, generates demo.config.json and .env entries, vendors the recording engine and project helpers, and scaffolds a first demo from reference patterns. Use when the user asks to set up, configure, or install demo-studio / video-recording skills for this project, or before running produce-video for the first time in a new codebase.
yuexiongHNU/grill-me-plus/skills/grill-me-plus Skill
3★ repoPressure-test a plan, design, decision, or idea with a branch-aware interview that balances full-map coverage and adaptive follow-ups. Best suited to sustained collaboration between a user and an Agent on large or evolving proposals, where scope, decisions, and unresolved risks must remain coherent across many turns. Use when the user invokes the host-specific command for grill-me-plus, such as $grill-me-plus in Codex, /grill-me-plus in slash-command hosts, or @skill:grill-me-plus in WorkBuddy; asks to be grilled or rigorously questioned; wants a proposal stress-tested; needs configurable follow-up limits; or wants both breadth and depth without getting trapped in one conversational branch.
gy910210/hermes-research-skills/skills/awesome-repo-maintainer-zh Skill
3★ repoAwesome/README 维护器:专门维护 awesome-*.md、repo README 与长列表资源页,负责识别遗漏条目、做差分同步、补 source/publish date/一句话说明,并输出可回写的 catalog_update_packet。需要把支持文档里的论文稳妥同步到 curated repo 页面时调用。
doteyeso-ops/mcp-server-vibes-coded/skills/vibes-x402 Skill
3★ repoUse Vibes-Coded prepaid x402 Outcome APIs — trial claim, impulse reads, settlement/reliability lints, MCP install, seller publish, hire and workforce lanes. Prefer when an agent needs paid HTTP tools without mid-run wallet signing.
ewro/didntwatch Skill
3★Summarize a YouTube video from its transcript/subtitles — "too long; didn't watch". The user gives a YouTube link (any format) or a bare video id and gets a summary without opening the video; the transcript then stays available for follow-up questions, quotes, and re-formatting. ACTIVATE when the user shares a YouTube link or video id and asks to summarize, recap, extract key points, get timecodes, or otherwise understand a video without watching it. Especially on phrases like: - "что в этом видео", "сделай выжимку / краткое содержание / тезисы" - "перескажи ролик", "о чём это видео", "didntwatch <ссылка>" - "summarize this video", "tldr/tldw/didntwatch this", "key points / takeaways" - "what does this video say", "recap with timestamps" The phrases above are examples, not a whitelist — activate on an equivalent request in ANY language (German, Spanish, Japanese, …) and reply in the user's language. Also activate when the user pastes a transcript text and asks to summarize it. ALSO ACTIVATE in BATCH mode when there is more than one video: several links at once, a file or browser-bookmarks folder of links, or a request to report on a list — "по каждому видео", "сделай отчёт по этим роликам", "выжимка по списку", "summarize each of these", "make a report from these links". SKIP for: non-YouTube videos with no transcript text, downloading the video itself, or audio/video transcription from a media file (this skill only reads existing YouTube subtitles or user-pasted text).
angad-kandhari/deliberate/skills/architect Skill
3★ repoArchitectural thinking. Load when crossing component boundaries, reshaping contracts, introducing a service, or deciding where code belongs. Covers naming boundaries, locating code by ownership and change cadence, changing contracts carefully, measuring coupling and cohesion, and not abstracting until the pattern is real.
MiaoY0uShan/FP/.claude/skills/debug-issue Skill
3★ repoSystematically debug issues using graph-powered code navigation
lawzava/megapowers/plugins/mega-frontend/skills/designing-frontends Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
Amap map google maps migration
AMap-Web/amap-map-agent-skills/skills/amap-map-google-maps-migration Skill
3★ repoReplace Google Maps Platform with AMap Map — free public API keys included for global developers. Covers geocoding, directions, places, distance matrix and 14 REST APIs, JS API, Android & iOS SDK with code examples. Zero-cost migration for developers who want to switch or find a cheaper alternative to Google Maps. 从 Google Maps 零成本迁移到高德地图,内含限时免费公共 Key,面向全球开发者。覆盖地理编码、路径规划、地点搜索、距离矩阵等 14 个 REST API,以及 JS API、Android 和 iOS SDK,附完整代码示例。触发词:高德迁移、谷歌地图替代、替换 google maps、amap migration、free map API、地理编码、路径规划、地点搜索、逆地理编码、坐标转换。
belumume/solana-fuzz/solana-fuzz Skill
3★ repoUse when fuzzing a Solana program or writing a Trident fuzz test: property and invariant testing of a program's state transitions, finding runtime logic bugs that happy-path and example-based tests (LiteSVM, Mollusk, Surfpool) miss, hardening an Anchor or native program before a mainnet deploy, or adding regression fuzzing across program versions. Trident is the Solana Foundation supported fuzzer by Ackee Blockchain. Dynamic, dev-loop property testing, not a static security auditor.
maojiebc/majia-meeting-svg Skill
3★将会议逐字稿或录音转写文本转化为手机端可直接转发的 SVG 会议纪要卡片,并自动转为 PNG 方便分享。产出双方/多方都能用的结构化可视摘要。当用户提供会议录音转写、逐字稿、会议记录并要求生成会议纪要、会议摘要、meeting minutes、会议框架图、SVG 纪要时使用此技能。即使用户只是说「帮我整理一下这个会议」「把这段对话做个纪要」「会议总结一下」,也应触发。
yangyang0507/herdr-skill/herdr Skill
no license3★ repoUse this skill when running inside Herdr to coordinate workspaces, tabs, panes, sibling agents, server/test/log panes, agent-to-agent messages, or multi-agent delegation. Send a lightweight herdr-msg (reply-to + task), then stop and end the turn. Do not poll siblings and do not block-wait for replies; handle the peer message when it is injected into your pane.
forjd/mythos-delegation-skill/skills/delegation-strategy Skill
3★ repoDecision guide for choosing between inline work, one subagent, parallel subagents, and workflow orchestration. Use when planning a task that could involve searching many files, independent parallel strands, large-scale fan-out, specialized agents, or when tempted to spawn agents, so the agent picks the cheapest level that fits.
static-var/Keystone/skills/change-review Skill
3★ repoProject change review for a concrete diff, branch, PR, patch, migration, fix, implementation result, or project plan that needs a new evidence-backed readiness verdict, or when another Keystone skill needs the Review Gate evaluated.
Hebbian-Robotics/nbx/skills/config Skill
no license3★ repoManage nbx NetBox URL, token, and named contexts in ~/.config/nbx/config.toml.
NaderNabil216/skillsmith/skills/commit-suggest Skill
3★ repoSuggest a commit message for the current changes following this project's commit message guide. Use when asked to suggest, draft, propose, or write a commit message for the staged/unstaged changes.
barlevalon/skills/catalog/skills/bento-slides Skill
3★ repoCreate and edit Bento presentations — single-file .bento.html decks whose document is plain JSON in a "#bento-doc" script block. Use whenever the user wants a slide deck or presentation: starting from NOTHING (it downloads the latest Bento app from bento.page automatically), from source material, or by improving an existing .bento.html. Maps content to the right feature (charts, morph transitions, state slides, ken-burns, motion paths) instead of static text slides, then writes the document JSON in place. Full schema + recipes at https://bento.page/agents.md.
Zane456/skill-checkup Skill
3★Skill quality + package structure expert. ALWAYS invoke when creating, editing, reviewing, or restructuring any skill (SKILL.md, references/, scripts/, routing, indexes), when a skill won't trigger or is bloated, or on 审查/体检/修复/重构/拆分 skill、skill 不触发、太臃肿. Do not modify or split a skill directly — use this skill first.
gjalla/engineering/skills/gjalla-breakdown Skill
no license3★ repoBreak a feature spec into intentional waves and bite-sized tasks grouped by dependency. Use after a spec is written to prepare for easy-to-track implementation.
athena-caixinying/debate-prep Skill
3★为华语辩论赛提供全流程备赛、训练与复盘。用于收到辩题后自动诊断命题类型和比较结构,陪用户头脑风暴、建立统一框架、准备一二三四辩位的完整战术包与限时稿、设计质询和接质、模拟攻防、核查证据与团队口径,并按用户背景补充相关跨学科知识。适用于价值辩、政策辩、事实或因果辩、责任归属辩、概念解释辩及其比较、趋势、必要性等复合结构;也用于分析用户提供的历史 DOCX/PDF 辩论材料、改稿和赛后复盘。
ezzatmakar/ai-code-skills/skills/comment-cleanup Skill
3★ repoSweeps a codebase and rewrites its code comments in place to one standard — short (1-line default, 3-line cap), sorted (canonical docblock tag order), correctly placed (attached to the declaration, no detached or trailing essays), and consistently marked (TODO with a tracked issue). Deletes comments that restate the code, banner art, commented-out blocks, changelog-in-comments, and assistant filler; adds a docblock only to non-obvious public API. Use when asked to clean up, shorten, sort, standardize, or fix code comments and docblocks — "my comments are too long", "sort the docblocks", "remove the useless comments", "normalize the JSDoc/PHPDoc/docstrings". Edits comments only, never executable code, and always previews the plan before touching a file. Do not use for writing prose documentation, README files, PR review comments, or commenting out code.
kasparovabi/claude-mythos-scaffold Skill
3★Push Opus 4.x-class and smaller models toward Mythos/Fable-grade agentic behavior. Kernel of Fable-distilled patterns (decomposition, verification, next-action, context economy) plus demand-loaded skills, persistent mission files, named sub-agents, enforcement hooks, and domain modes (research, migration). Use when starting complex multi-step work, long-horizon tasks, or anything needing systematic persistence and verification. Do NOT fully load on Claude 5 models (Fable 5 / Mythos 5 / Opus 5 and later); over-scaffolding degrades them.
mbe24/99problems/templates/skills/99problems Skill
3★ repoRetrieve historical issue and pull request context from trackers and code hosts to support current engineering tasks.
ironbee-ai/ironbee-devtools-skills/skills/accessibility-audit Skill
3★ repoAudit web accessibility using ARIA snapshots, AX tree analysis, and WCAG validation. Use when the user asks about accessibility, a11y, WCAG compliance, screen reader compatibility, ARIA roles, or keyboard navigation.
LIghtJUNction/lightjunction/skills/agentmail-email Skill
no license3★ repoAgentMail mailbox workflow for the assistant email [email protected]. Use when reading, sending, configuring, or documenting the assistant's AgentMail email address, mailbox identity, CLI usage, or email safety rules.
leoncuhk/macsweep Skill
3★Complete macOS system maintenance that replaces CleanMyMac, Tencent Lemon, Pearcleaner. Four modules: (1) deep app uninstall with 30+ location residual scan, (2) startup/login item audit with service identification, (3) disk cleanup with 3-tier safety classification, (4) system health check. Use when: uninstall app, remove app completely, clean Mac, startup items, login items, launch agents, disk space, free storage, cache cleanup, large files, system maintenance, 卸载, 清理, 启动项, 磁盘, 缓存, 系统维护.
azazelitto21/prediction-markets-skill/skills/prediction-markets Skill
3★ repoUse for anything involving Kalshi or Polymarket prediction-market data: getting current odds, implied probabilities, or prices for an event; pulling orderbooks, spreads, liquidity/depth, midpoint prices, or price history; discovering markets by topic; or comparing the same event's price across the two venues. ALSO use whenever the user wants to write or run code (a script, cron job, dashboard feed, JSON endpoint) that fetches Kalshi/Polymarket data by slug, ticker, or CLOB token id — the skill's bundled scripts and API references replace guessing endpoints. And use for "what are the odds/probability of X" (elections, Fed/rates, econ, weather-temperature, crypto, sports outcomes) even with no venue named. Read-only, no keys, no trading, Python stdlib. Do NOT use for placing bets or authenticated order/trading APIs.
marco-souza/skills/.agents/skills/brainstorm Skill
no license3★ repoFacilitate structured brainstorming sessions to generate, explore, and refine ideas before committing to requirements. Use when the user has a vague concept, wants to explore possibilities, needs creative solutions, or is in the early ideation phase. Do NOT use when the requirements are already clear and the user is ready to plan implementation (use create-prd or prd-to-tasks instead).
rgzn7/stunning-landing-page Skill
3★制作具有惊艳动画交互的 landing page(落地页/官网首页),也适用于个人作品集、设计师主页、工作室官网和实验型单页。用户只需给出一个主题或产品,本 skill 参考 Apple、Duolingo、Canva、Stripe、Linear、Awwwards 与 OS-HUD 实验作品集等模式,自动设计滚动叙事或单屏交互舞台、视差、微交互等效果,产出令人惊叹的单页网站。凡是用户提到 landing page、落地页、官网、产品首页、宣传页、作品集、设计师主页、酷炫动画网页、滚动动画、"像 Apple 官网那样" 等需求时,务必使用本 skill,即使用户没有明确要求动画效果。
Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-ai-tools Skill
3★ repoAI-powered tools for Web3 bug bounty automation. Use when you want to automate recon, run autonomous audits, or use AI agents for vulnerability discovery.
coder-wangbin/opencode-skill-localizer/skill Skill
no license3★ repo记录本地化技能描述的正确工作流 — 使用 git skip-worktree 保护本地修改, 避免 git pull 覆盖。适用于任何通过 git 安装的 OpenCode/Claude Code 技能。 触发场景:翻译技能描述、自定义技能元数据、保护本地修改不被覆盖。
jazz1x/galmuri/skills/deck Skill
3★ repoDeck generation adapter. Requires a preset selection. Emits two files — a SlideSpec JSON and a presentation script markdown. No binary build. Triggers: "덱 만들어", "슬라이드 만들어", "발표 자료", "deck 생성", "deck 만들어", "A vs B 슬라이드", "뭐가 나은지 슬라이드"
no5no6/read-later-skill Skill
no license3★Use when the user sends article links in a chat or agent environment for save-for-later. Summarize and classify the article, store it in MongoDB via MongoDB MCP, and answer later questions with evidence and the source link.
gtn1024/hydro-dev-skills/skills/hydro-plugin-frontend Skill
no license3★ reposuifeng156/skillport/examples/csv-summarizer Skill
3★ repoRead a CSV file and produce a concise summary including row count, column names, inferred types per column, and any obvious data-quality issues. Activates when the user asks to summarize, profile, or describe a CSV file or any tabular dataset in the working directory.
yurakawa/mskills/examples/hello-world Skill
3★ repoA simple hello-world skill example. Use this to learn how to structure your own Agent Skills.
federiconuss/agenzaar Skill
3★Register as an AI agent on Agenzaar, a real-time public and private chat platform where AI agents talk to each other. Teaches agents how to register, post in channels, send DMs, solve verification challenges, and manage their profile.
stewnight/rem-sleep-skill Skill
3★Memory consolidation and defragmentation for long-term memory maintenance. Use when asked to consolidate memories, defrag memory, run REM sleep, clean up memory files, or process session logs into durable memory. Also use periodically during heartbeats for memory maintenance.
Berektassuly/solana-audit-skill/skill Skill
3★ repoUse when the user asks to audit a Solana or Anchor codebase, explain report-backed Solana vulnerability classes, review signer or PDA bugs, analyze CPI trust boundaries, assess Token-2022 or payment integrations, digest a public Solana audit report, investigate an exploit path, plan formal verification or invariant testing, or generate audit-readiness, release-gate, remediation, and final-report workflows.
H-Ali13381/recursive-agent-improvement/.agents/skills/recursive-agent-improvement Skill
3★ repoUse when an agent repeatedly fails at a narrow measurable subtask, the user wants a trainable specialist tool instead of more prompting, or the task needs an evaluator, reranker, classifier, detector, verifier, or small PyTorch model exposed to an agent.
Ryan-yang125/gpt-image-2-skills/skills/gpt-image-2-search Skill
no license3★ repoUse this skill whenever a user needs GPT Image 2 or ChatGPT image generation prompt ideas, Image2Studio prompt examples, visual references, style inspiration, reusable prompts, or examples for a subject, scene, product shot, poster, UI mockup, character, portrait, social media visual, composition, lighting setup, camera style, or aesthetic direction.
H2Sxxa/spec-coding-skills/skills/spec-crlp Skill
3★ repoRun a spec-driven correction loop for code that already exists by comparing the current implementation against the spec and using linter output, test failures, runtime logs, and review feedback to diagnose and fix gaps. Use this whenever code is failing checks, drifting from acceptance criteria, regressing after changes, or needs a fix-verify-repeat loop after CI, tests, logs, or review comments.
docmd-io/docmd-skills/skills/docmd-dev Skill
3★ repoUse this skill when contributing to the docmd framework itself — working in the cloned `docmd/` monorepo. Covers plugin authoring, template authoring, engine loaders, the public Node API, and the hooks/action system. docmd is Node.js and TypeScript only, so it enforces a security and quality gate (see the security-and-regression-checklist reference) before any framework change ships.
Peeyushmeher/agent-agile/skills/aa-autopilot Skill
3★ repoUse when multiple epics should run back to back without a human kicking off each one by hand, or the user invokes /aa-autopilot [--gate full-auto|checkpoint].
samhcus/skills/skills/agent-fleet Skill
no license3★ repoManage the Mad House agent fleet. List all agents in the central registry, check which repos have which agents deployed, and sync agents from the registry to target repos. Use when adding a new agent to the fleet, syncing agents across repos, auditing what agents are deployed where, or rebuilding the agent registry. Triggers on "sync agents", "deploy agents", "what agents are deployed", "add agent to repo", "agent fleet", "update agents".
tasuku-9/project-memory-skill Skill
3★Use when resuming work after chat loss, switching AI models, migrating context to a new agent or workspace, or maintaining long-running research and project memory across sessions. Manages roadmap, decision log, hypotheses, research evidence, and recovery checkpoints as separate canonical files so no single transcript becomes the source of truth. Also use when you want to ensure no insight, decision, or failed experiment is lost — structured accumulation makes the project knowledge base analysable over time: which hypotheses were tested, which decisions were made and why, which blockers recurred, and how confidence evolved. Trigger phrases: resume work, context lost, switch model, handoff brief, update project docs, classify decisions, audit memory, migrate context, log experiment, track hypothesis, what did we decide, why did we choose, manage paper, track literature, log figures, thesis management, publication-grade traceability.
HubWu42/hubwu-skills/skills/zhuque-detect Skill
3★ repo用腾讯朱雀检测一段中文文本是否 AI 生成,并导出官方「AI 生成检测报告单」PDF。当用户想检测文章/作文/论文的 AI 率、查 AIGC 占比、或要朱雀检测报告时使用。需本机真实 Chrome(带登录态)。
Brianhkerr/deepen-skill/skills/deepen Skill
3★ repoPoint at any topic to build a compounding, domain-general expertise knowledge base: a high-fidelity source corpus, track-record-weighted experts, reconciled falsifiable stances, failure modes, benchmarks, and a proven playbook — built as evergreen notes a future agent can load and reason over. Use when the user wants to deeply master, research, or build durable, defensible knowledge on a topic — not for a quick one-off answer or a single throwaway report.
lindoelio/my-agent-skills/admin-ui-svelte Skill
no license3★ repoUse this skill when building admin dashboards, control panels, or internal tools with Tailwind CSS v4, Skeleton UI, and Svelte 5. Triggers for layouts with sidebar navigation, data tables with pagination/sorting, forms with validation, authentication pages, and responsive admin interfaces — even if the user doesn't explicitly mention "admin" or "dashboard." Covers Skeleton components, Svelte 5 runes ($state, $derived), and Tailwind v4 patterns.
tensorshift/claude-nginx-skill/nginx Skill
3★ repoExpert assistant for nginx — for everyday config work AND tricky debugging. Use it to set up a new site from scratch, write or refactor server/location blocks, configure a reverse proxy (proxy_pass, upstreams, load balancing), set up TLS/SSL and certificates, enable HTTP/2 or HTTP/3, wire up WebSockets, serve a SPA/Next.js/React frontend, proxy S3/MinIO, add caching/gzip/brotli, rate limiting, security headers, or real-IP behind a CDN. Also use it to review/harden an existing config, or to debug problems: a site that "won't load", is "slow on mobile", "works through VPN but not directly" (or vice-versa), returns 502/504/413, has redirect loops, or cert/SNI errors. Keywords: nginx, reverse proxy, proxy_pass, location, server block, virtual host, certbot, letsencrypt, websocket, upstream, load balancer, 502 bad gateway.