Search: "lists"

Performs pathway and gene-set enrichment analysis on gene lists or ranked gene data and interprets the results. Used when the user has a set of genes (differentially expressed genes from PyDESeq2/Scanpy, CRISPR-screen hits, cluster marker genes, proteomics hits) and wants to know which biological pathways, GO terms, or gene sets are over-represented or enriched. Covers over-representation analysis (ORA / Enrichr / Fisher / hypergeometric), ranked Gene Set Enrichment Analysis (GSEA / preranked), single-sample scoring (ssGSEA/GSVA), and functional profiling via gseapy, g:Profiler, Enrichr libraries, MSigDB, GO, KEGG, Reactome, and WikiPathways — plus gene-ID mapping, choosing the right background universe, multiple-testing correction, redundancy reduction, dotplots/enrichment maps, and publication-ready tables. Use this for "pathway analysis", "enrichment analysis", "GO enrichment", "KEGG/Reactome pathways", "GSEA", "over-representation", "functional annotation", or "what pathways are my genes in".

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.

Token integration and implementation analyzer based on Trail of Bits' token integration checklist. Analyzes token implementations for ERC20/ERC721 conformity, checks for 20+ weird token patterns, assesses contract composition and owner privileges, performs on-chain scarcity analysis, and evaluates how protocols handle non-standard tokens. Use when integrating or accepting arbitrary ERC20/ERC721 tokens, auditing a token implementation for standards conformity, or assessing risk from weird tokens such as fee-on-transfer, rebasing, missing return values, or blocklists.

Entry point and router for every Expo or EAS task. Load this skill first — before writing code and before choosing another expo-* / eas-* skill — when the request, PRD, or spec mentions Expo, EAS, Expo Go, or an expo-* package, or the project has an `expo` dependency in `package.json`. Within that gate it also covers app specs and designs to implement (tabs, stacks, maps, lists, navigation, building from a screenshot), and phrasings like 'implement a mobile app', 'make my app look native', 'add navigation', 'fetch some data', 'upgrade my SDK', 'add Expo to my existing native app', 'ship to the App Store', or 'I'm new to Expo, where do I start'. A fully specified request (SDK pinned, libraries named, layout given) still routes through here — the shared setup rules still apply. Do NOT load it when neither signal is present: a bare React Native project with no `expo` dependency is not Expo work. Detects the real goal, routes to the right expo-* / eas-* skill, and owns the shared setup rules.

Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

Operating procedure for Meta Ads (Facebook and Instagram) through Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about Meta campaigns, ad sets, ads, objectives, optimisation goals, audiences, placements, pixels, lead forms, creative fatigue or budgets, and whenever they ask to launch, pause, duplicate or re-budget anything on Facebook or Instagram. It lists the 43 Meta tools by job, the objective rules that decide whether an ad set is legal, the resolvers that must run before a write, and the order a launch is built in.

Operating procedure for Google Ads through Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about Google Ads campaigns, ad groups, keywords, search terms, quality score, budgets, bid strategies, Performance Max, assets and extensions, conversion actions, labels, ad schedules or device bid modifiers, and whenever they ask to create, pause, re-budget or otherwise change a Google Ads account. It lists the 70 Google tools by job, the order a campaign must be built in, the resolvers that have to run before any write, and the platform rules that cause most rejections.

Operating procedure for Meta Ads (Facebook and Instagram) through Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about Meta campaigns, ad sets, ads, objectives, optimisation goals, audiences, placements, pixels, lead forms, creative fatigue or budgets, and whenever they ask to launch, pause, duplicate or re-budget anything on Facebook or Instagram. It lists the 43 Meta tools by job, the objective rules that decide whether an ad set is legal, the resolvers that must run before a write, and the order a launch is built in.

Operating procedure for ChatGPT Ads through Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about ChatGPT Ads campaigns, ad groups, chat card ads, context hints, spend limits, geo targeting, measurement pixels or review verdicts on that platform, and whenever they ask to launch, pause, resume or edit a ChatGPT Ads campaign. It lists the 23 ChatGPT Ads tools by job, the chat card limits, the account and budget rules, and the order a launch is built in.

Operating procedure for LinkedIn Ads through Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about LinkedIn campaign groups, campaigns, sponsored content creatives, B2B targeting by job title, industry, seniority or company size, audience size and forecasts, lead gen forms, conversion rules, cost per lead or creative fatigue on LinkedIn, and whenever they ask to launch, clone, pause or re-budget a LinkedIn campaign. It lists the 34 LinkedIn tools by job, the organisation and audience-size rules, the asset limits, and the order a launch is built in.

Operating procedure for TikTok Ads through Adako (not available yet — TikTok has not approved API access, so every TikTok tool says so and nothing runs), the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about TikTok campaigns, ad groups, in-feed video ads, Spark Ads, identities, video metrics such as hook rate and 6-second views, TikTok pixels and events, interest targeting or creative fatigue on TikTok, and whenever they ask to launch, pause or re-budget a TikTok campaign. It lists the 30 TikTok tools by job, the objective and pixel-event rules, the video asset rules, the budget floors, and the order a launch is built in.

Operating procedure for Google Ads through Adako, the MCP server and REST API that connects this assistant to Google Ads, Meta Ads, ChatGPT Ads, TikTok Ads and LinkedIn Ads. Use it whenever the user asks about Google Ads campaigns, ad groups, keywords, search terms, quality score, budgets, bid strategies, Performance Max, assets and extensions, conversion actions, labels, ad schedules or device bid modifiers, and whenever they ask to create, pause, re-budget or otherwise change a Google Ads account. It lists the 70 Google tools by job, the order a campaign must be built in, the resolvers that have to run before any write, and the platform rules that cause most rejections.