sergeyizmailov
UserAgent Skills (SKILL.md) for Claude Code, Codex, Cursor, and Gemini CLI — only the expertise a frontier model doesn't already reliably know.
Categories
Indexed Skills (16)
design-stack-picker
Use when building or restyling frontend UI and choosing building blocks — icon sets, fonts, component/block libraries, accessible primitives, imagery sources, color systems, motion, shadows, spacing, and image optimization. For landing pages, ecommerce, dashboards, web apps, emails, and single components.
responsive-adapter
Make an existing landing page, admin panel, dashboard, or any non-responsive page work at every viewport from 320px to 2560px+ without changing the visual design. Triggers on requests to make a page responsive, fix mobile layout or breakpoints, adapt a landing or admin to phones / tablets / widescreens, and on symptoms alone — horizontal scroll, elements overflowing, text unreadable on mobile, sidebar broken on tablet, empty space on widescreen — even when the word "responsive" is never used.
normcore-web
Use when building or restyling a website that should look like ordinary, long-running commercial web rather than a freshly art-directed product — B2B and professional services, online shops and catalogues, news and publishing, corporate and institutional sites, directories and portals. Covers the plain 2012–2020 commercial register: default fonts, dense functional layout, no motion, real photographs. Triggers on explicit requests for a conventional corporate, page-builder, legacy-agency, retail, or 'real company website' look. Do NOT trigger merely because a design should look less AI-generated. Not for product UI, SaaS app shells, dashboards, portfolios, or editorial brand sites.
web-scraping
Mass crawl/scrape sites incl. anti-bot (Cloudflare, Akamai, DataDome, PerimeterX). Crawl4AI = scale (arun_many, dispatchers, deep crawl, LLM-ready markdown); Camoufox = fingerprint evasion. For: scrape N pages, crawl a site, extract structured data, 403/challenge/bot-detection, captcha.
deep-research
Use when asked to research deeply, compare options or vendors, fact-check a claim, investigate an unfamiliar topic, prepare a report or briefing, build a knowledge base or reference doc, or trace a claim to its primary source.
google-ads
Senior Google Ads, single-account layer: plan, launch, audit, diagnose, scale one account. Search, PMax, Demand Gen, Shopping, AI Max, Smart Bidding, RSA, tCPA/tROAS, tracking/OCI, GAQL and API mechanics. Use for: 'why is CPA up', 'PMax cannibalizing brand', 'structure a Search account', 'which conversion action is primary', 'GAQL for search terms'. Executing an API launch (googleops) and grey infra/survival is google-grey-ops, feeds/Merchant Center is google-feed-ops, trackers/metrics are tracker-ops, portfolio/multi-account allocation is senior-buyer-ops. Not organic SEO.
google-feed-ops
Google Merchant Center (GMC) launch and operation plus the retail data layer: new-account launch sequence (site trust → ToS → verify+claim → business info → shipping/tax → data source → review → programs → Ads link → first campaign), Merchant API v1 mechanics and the gmcops CLI, feed spec and attributes, feed rules and supplemental sources, titles, custom_label schema, GTIN, suspensions and appeals, MC↔Ads link, free listings, CSS. Use for: 'set up Merchant Center for a new store', 'products not showing / disapproved', 'GMC suspended Misrepresentation', 'push products via API', 'link Merchant Center to Google Ads'. Campaign types and PMax bidding live in google-ads; grey cascade in google-grey-ops.
google-grey-ops
Launch and run Google Ads via the API from a developer token + OAuth/service account — the googleops CLI (workspace, doctor, plan=validate_only, apply PAUSED, verify read-back, activate, bulk across customers under an MCC), gmcops for Merchant Center — plus grey-market survival: agency/MCC account supply, identity/payment infra, AdsBot/cloaking/review-layer filters, RSA/unicode/path tricks, selfie/BOV verification, geo isolation, no-cloak surfaces, ban replacement, enforcement tracks, failure forensics, MC cascade, per-vertical playbooks (gambling, finance/crypto, nutra, dating, loans, apps). Use for: 'launch Google ads through the API', 'I have a developer token / MCC, set up campaigns', 'bulk launch on N customer ids', 'PMax/Shopping/Search via script', 'why did the mutate fail', 'USER_PERMISSION_DENIED'. Clean buying theory = google-ads; feed spec/GMC launch = google-feed-ops; metrics = tracker-ops.
js-obfuscation
Use when obfuscating JavaScript, building anti-detection layers, evading Google Safe Browsing, hiding payloads from scanners, adding anti-bot/anti-DevTools protection, or preparing phishing/red-team pages for deployment
knowledge-delta-skill-architect
Writes, audits, and compresses agent skills so they earn their tokens. Covers include-vs-cut, real expertise vs what the model already knows, sizing and progressive disclosure, description/trigger design, multi-file skills. For: write a skill for X, improve/shrink this skill, is this skill worth its tokens, my skill never triggers, port domain expertise into SKILL.md, split one into references.
measurement-experimentation-ops
Decide whether a media-buying result is real before scaling it: testing-mode choice (causal / screening / infrastructure), validity traps (SRM, peeking, contamination, lag, multiple testing), and the platforms' measurement tools — Meta (A/B Test, ad_study API, Conversion Lift, GeoLift, Robyn) and Google (Experiments, Conversion Lift, Meridian MMM, brand-search incrementality). Pairs with the media-buying set.
meta-ads
Senior Meta (FB/IG) ads, clean-marketing layer: plan, structure, audit, diagnose, scale an ad account — ODAX objectives, CBO/ABO, Advantage+ audiences and creative, attribution windows, Pixel/CAPI/EMQ, learning phase, creative fatigue, policy rejections, unit economics, API error codes. Use for: 'why is CPA up', 'ad set stuck in learning', 'CBO vs ABO', 'which attribution setting', 'pixel vs CAPI events mismatch', 'Meta ad rejected Personal Attributes', 'Graph API error 1885501'. Executing an API launch and grey infra/survival = meta-grey-ops; tracker metrics = tracker-ops; portfolio decisions = senior-buyer-ops.
meta-grey-ops
Launch and run Meta (FB/IG) ads via the workspace-bound Marketing API CLI (metaops): access/scopes/System User, MCP vs API, PAUSED bulk launch across ad accounts, edit/clone/rules, catalog/DLO/carousel creatives, catalog as an agent-edited Google Sheet, attribution 1/1/1, Advantage+ and multi-advertiser opt-out, EU DSA, BM setup (accounts/pixel/CAPI/users), review/monitor/comments, plus grey-market survival: antidetect/proxy/session hygiene, agency accounts, token death, cloaking/review-layer tricks, verification gates, no-path verticals, per-vertical playbooks (casino, nutra, crypto, news-tg). Use for: 'launch FB ads through the API', 'I have a BM access token, set up campaigns', 'bulk launch on N accounts', 'connect Claude to Meta ads / MCP', 'why did the ad set create fail', 'duplicate campaigns / set kill rules / hide comments via API'. Clean marketing theory = meta-ads; tracker metrics = tracker-ops.
secure-coding
Use when writing JavaScript, Node.js, HTML, CSS code for websites, landing pages, admin panels, APIs. Reduces common vulnerability classes (XSS, injection, SSRF, etc.) via secure libraries, proper headers, and safe patterns. Includes AI code vulnerability patterns.
senior-buyer-ops
Senior media-buyer / team-lead operating layer (clean and grey portfolios alike): day-1 operating contract, portfolio allocation across accounts (test/scale/reserve), kill/watch/scale + marginal scaling, creative-intelligence pipeline, end-to-end funnel QA, cross-platform (Meta + Google) allocation. Orchestrates meta-ads / meta-grey-ops / google-ads / google-grey-ops / google-feed-ops / tracker-ops / measurement-experimentation-ops.
tracker-ops
Tracker ops for affiliate/media buying: Keitaro + Binom APIs (keys, reports, cost push), postback/S2S, metric discipline (payout event vs all-conversions, timezones, CPL math), daily spend-sync, gclid/OCI chain for Google. Principles port to other trackers.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.