Loading...
Loading...
Found 1,676 Skills
When the user wants to identify or fix keyword cannibalization in Google Ads — where multiple campaigns or ad groups are competing against each other in the same auction. Triggers on 'keyword cannibalization', 'campaigns competing with each other', 'duplicate keywords', 'keyword overlap', 'internal competition', 'same keyword in multiple campaigns', 'cannibalization check', 'campaign conflict', 'which campaign wins the auction', 'overlapping match types', or 'cross-campaign negatives'. For general negative keyword strategy see google-ads-negative-keywords.
Detect and fix SQL injection vulnerabilities in any framework. Covers Laravel (DB::raw, whereRaw), Node.js (template literals in queries), Python (f-strings in SQL), and Cloudflare D1. Enforces parameterized bindings everywhere. Use when writing database queries, reviewing code for injection, or fixing SQL injection findings.
Use this skill to translate a classifier's in-place verdict into a precise, page-by-page work plan for the docs-sync panel. Activate after docs-impact-classifier returns verdict in_place; reads the candidate page list, fetches the actual page contents, narrows scope to specific sections within each page, and emits the per-page task brief the panel fans out against.
Use when building UI with gluestack-ui components. Covers component composition, variants, sizes, states, accessibility props, and platform-specific considerations for React and React Native.
Validate project space structure, boilerplate docs, and consistency with ideas/
Enforces using GNU coreutils commands with 'g' prefix instead of Mac default BSD commands. Prohibits using Mac standard commands. MUST ALWAYS be applied when using coreutils commands like ls, find, sed, awk, grep, etc.
Cross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check with claude', 'consult another AI', 'ask opencode', 'copilot opinion', or wants a second opinion from a different AI tool.
Dotfile management with stow, chezmoi, or git bare repo for configuration sync across machines. Use when user asks to "manage dotfiles", "sync configs", "setup dotfiles", "backup shell config", or organize configuration files.
Direct research projects by gathering team feedback and delegating implementation tasks. Writes publication-quality scientific text and coordinates bioinformaticians, software developers, and biologist commentators via technical-pm.
Normalize messy creator campaign metrics from multiple sources into a single clean table with standardized field names ready to merge into your master tracker. This skill should be used when cleaning up influencer metrics, standardizing campaign data from multiple platforms, normalizing creator performance numbers, merging metrics from Instagram and TikTok and YouTube into one sheet, formatting messy analytics exports, preparing campaign data for a master spreadsheet, converting raw platform stats into a consistent format, combining metrics from different reporting tools, deduplicating creator data from multiple sources, fixing inconsistent column names across exports, or cleaning up a metrics dump before reporting. For calculating engagement rates, see engagement-rate-calculator-benchmarker. For full campaign reports, see campaign-roi-calculator. For parsing a single Story screenshot, see story-metrics-screenshot-parser.
분석 에이전트 공통 규칙. 웹검색 직접 호출, 원문 인용, 교차 검증 프로토콜을 정의합니다. 환각 방지의 핵심 방어선.
TanStack Hotkeys for type-safe keyboard shortcuts with React hooks. Use when adding keyboard shortcuts, hotkey sequences, shortcut recording, key hold detection, or platform-aware shortcut display. Use for hotkeys, keyboard-shortcuts, shortcuts, key-binding, Mod key, hotkey-recorder, key-sequences.