Research & Data

Make an informed non-trivial decision via a three-step interrogation → criteria → research-handoff protocol. Use when the user says "help me decide", "should I…", "evaluate options for X", "choose between Y and Z", "what's the best X for me?", "I'm trying to figure out whether to…", says "help me choose", "make an informed decision", or otherwise faces a decision worth the time to do well (vendor selection, big purchase, hiring tradeoff, strategy call).

Traces the full call chain from a given symbol or code location up to all entry points that can reach it (HTTP controllers, main functions, page components, routes, etc.). Works for any language indexed by CodeGraph. Use for blast-radius analysis before modifying a function, method, or class.

Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.

Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

Build an onboarding map of an unfamiliar repository covering purpose, entry points, how to run it, main modules, data flow and risky areas, with file references. Use when asked to explain, map or onboard onto a codebase.

Pull the people who liked or commented on any LinkedIn post and segment them by ICP fit (peer / aspirational / prospect / other). Produces an engager roster, tier breakdown, and outbound action lists (follow back, comment-drop, DM-able with one-line openers). Powered by Apify, no LinkedIn login. Triggers on \"who liked my post\", \"who engaged\", \"engagers report\", \"audience analytics\". Not for tracking author replies to your comments (use linkedin-thread-monitor).

Download open-access biomedical article PDFs from PMC with offline Proof-of-Work solving. Triggers: 下载文献PDF, PMC PDF, 403/404 on PDF link, Preparing to download, reCAPTCHA page, OA full text, supplementary files, download paper PDF.

Add cached official-asset and product research preflight before reference selection and build authorization.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

>- Run Codex CLI (exec, resume) for parallel work, delegating tasks to another model, or background code generation. Handles code analysis, refactoring, and automated editing. Includes Spark vs standard guidance. Triggers: "codex", "run codex", "use codex to".

基于多篇作者、博主、公众号或品牌内容的正文，进行全面、可解释、可复核的数据分析，覆盖样本质量、发布节奏、选题结构、关键词概念、标题策略、篇章结构、论证方式、证据体系、案例实体、语言风格、情绪立场、读者收益、行动引导、视觉使用、时间演化和维度关联，并进一步提炼作者定位、内容资产、选题系统、分析框架、判断标准、表达模板、案例库、金句风格、内容机会和写作 SOP。默认生成本地 Markdown 报告、独立文案框架、HTML 看板并同步飞书；只有用户明确关闭时才跳过 HTML 或飞书。

Use the Marvyn tools for anything about the user's own marketing - ads, SEO, AI search visibility, Shopify store, Google Analytics, social, site behaviour, tracking - whether reading results, investigating a change, or preparing a campaign, article, audience, pause or tracking change for approval.

Conducts systematic, scoping, and narrative literature reviews using PubMed, arXiv, bioRxiv, Semantic Scholar, and other appropriate sources. Use for research synthesis, reproducible literature searches, screening, citation checking, or preparing Markdown and PDF reviews. Tracks search coverage, records versus studies, and evidence limitations; supports meta-analysis planning but does not supply a meta-analysis engine.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Guide production backend development. Use for APIs, services, workers, queues, schedulers, and data systems; select the relevant backend guidance.

Prepare precise human approval decisions without stalling unrelated work. Use when an agent encounters changes to authority, methodology, data access, budget, deployment, or any other explicitly reserved decision.

>- Provides foundational Firebase CLI setup, CLI installation, version checks (`firebase-tools@latest --version`), CLI login (including --no-localhost), project creation, project selection (`firebase use`), and app config file downloads (`google-services.json`, `GoogleService-Info.plist`). Use ONLY for CLI login, project creation/switching, or downloading app config files. Don't use for Firebase Hosting deploy, Firestore, Auth, App Hosting, Data Connect, Crashlytics, or Remote Config.

Генерирует HTML-модуль для лендинга «ПрофПак» по контракту. Использовать, когда пользователь просит «сгенерируй компонент X», «создай модуль Y», «напиши блок Z» или присылает контракт модуля (Data In → HTML Out).

Sinyal scalping BUY/SELL LIMIT/STOP timeframe M3/M5 dengan SL maksimal $3 (lot 0.01, dikonversi otomatis ke point per pair via tick_value MT5) dan TP RR 1:1.5/1:2. Debat 2 AI (teknikal vs risk manager) + hakim netral, data murni MT5 lokal (cepat, tanpa web). Punya track record di Google Drive untuk pembelajaran AI: user melaporkan hasil via trigger "signal-result win/lose [alasan]". Gunakan saat user mengetik signal-<pair> (contoh signal-xauusd, signal-eurusd) atau signal-result.

Validate a business or startup idea against ten rubrics (problem, customer, market, alternatives, monetization, distribution, feasibility, defensibility, founder fit, risks), each scored 1 to 5 with evidence and confidence, and get a fixed-rule verdict (Build, Validate first, Pivot, Stop) with the riskiest assumption, three cheap experiments and open questions, as Markdown and JSON, in English or Polish. Use when asked to validate, assess, score, stress-test or sanity-check a business idea, startup idea, product idea, SaaS idea or side project, or when the user types /business-idea-validator with an idea. Not for market research reports, pitch decks or financial models.

Review supplied X analytics, find same-account outliers, run the weekly review, and plan 5 more versions of what worked. Analyzes only supplied data; never scrapes.

Build a production-ready, responsive, installable PWA (React 18 + Vite + Tailwind front end, one Express process, embedded node:sqlite, hand-written service worker, Web Push) from nothing but the user's project idea. Use this skill whenever the user asks to create, build, bootstrap, or scaffold a web app, PWA, mobile-installable web app, dashboard, tracker, portal, booking/ordering/notes/habit/fitness/expense-style app, or asks to "make an app for X" — even if they never say the words "PWA", "React", or "API". Also use it when someone wants a new app in an empty workspace and mentions installing it on their phone, pushing notifications, working offline, or sharing a public link.

Research and compare brand fonts, verify licensing, and optionally install and render a shortlist in Figma. Use for wordmark typography, font specimens or local-font troubleshooting; recommendations alone do not require installation.