global-invoicing-research

Automatically improve OpenClaw skills, prompts, or articles through iterative mutation-testing loops. Inspired by Karpathy's autoresearch. Use when user says 'optimize [skill]', 'autoresearch [skill]', 'improve my skill', 'optimize this prompt', 'improve my prompt', 'polish this article', 'improve this article', or explicitly requests quality improvement for any text-based content. Supports three modes: skill (SKILL.md files), prompt (any prompt text), and article (any document).

Research trending topics, ideas, and conversations on X (Twitter) using twitterapi.io.

Comprehensive token research for EVM chains (Base, ETH, Arbitrum) and Solana. Use this skill when you want to research crypto tokens, deep-dive projects or monitor tokens.

Run a second-hop deep research pass through the Tavily CLI after an initial scan, then normalize the result into a local `research.md` contract. Use when Codex needs cited follow-up research for a chosen topic from `news-collect`, or wants a reusable research report saved into `content-production/inbox/`.

Conduct comprehensive AI-powered research with citations via the Tavily CLI. Use this skill when the user wants deep research, a detailed report, a comparison, market analysis, literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", "what does the market look like for", or needs multi-source synthesis with explicit citations. Returns a structured report grounded in web sources. Takes 30-120 seconds. For quick fact-finding, use tavily-search instead.

Find brands actively spending on influencer and creator campaigns. Scans trade press, Instagram, job boards, and news for active-spender signals, then outputs a scored, prioritized prospect list with contacts. Use when you need to find brands to pitch, identify active advertisers, build a prospect list, research which brands are hiring influencer marketers, or find companies launching creator campaigns. Triggers on: 'find brands to pitch,' 'prospect list,' 'who's spending on influencers,' 'brand prospects,' 'active advertisers,' 'campaign activity,' or any request to identify brands actively investing in creator/influencer marketing.

Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test causal relationships. Triggers: "design a two-sample MR study", "build a publishable MR paper", "test whether this biomarker causally affects this disease", "generate Lite/Standard/Advanced MR plans", "screen multiple exposures with MR", "bidirectional MR design", "causal inference using GWAS summary statistics", or "I want to study X and Y using MR". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.

Generates complete network toxicology + molecular docking research designs from a user-provided toxicant and disease/phenotype. Always use this skill when users want to investigate how an environmental toxicant, endocrine disruptor, heavy metal, food contaminant, pharmaceutical residue, or consumer product chemical may contribute to a disease through shared molecular targets, hub genes, pathways, and docking evidence. Trigger for: "network toxicology study", "toxicology mechanism paper", "target prediction + PPI + docking", "environmental pollutant and disease mechanism", "hub genes and docking for toxicant", "Lite/Standard/Advanced toxicology plan", "CTD + SwissTargetPrediction + GeneCards + STRING", "CB-Dock2 docking study", "triclosan/BPA/cadmium/PFAS + disease". Also triggers for Chinese phrasings: "网络毒理学研究设计"、"毒物机制论文"、"靶点预测+PPI+对接"、"环境污染物与疾病机制". Trigger even for casual phrasings like "I want to study how chemical X affects disease Y" or "help me design a toxicology paper". Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.

Research Pendle PT (principal token) markets, including unlevered hold-to-par ideas, near-expiry rotations, and looped PT strategies across money markets like Morpho and Euler. Use when evaluating Pendle PT opportunities, comparing natural PT APY versus practical loopability, ranking PTs by time to par / implied APY / liquidity / underlying risk, assessing PT collateral support, or comparing manual-only loops against easier execution paths such as Contango.

Apply Karpathy's autoresearch methodology to autonomously iterate and improve anything measurable — Claude skills, n8n workflows, system prompts, business processes, or any artifact with a clear quality metric. Inspired by github.com/karpathy/autoresearch (56k stars). The loop: propose a change → test it → measure against the target metric → keep if better, discard if not → repeat indefinitely. ALWAYS trigger this skill when the user says things like: "improve this skill automatically", "iterate on this workflow", "run autoresearch on", "autonomous improvement loop", "overnight experiments", "keep iterating until it's better", "run experiments on this", "optimize this automatically", or any request to have Claude autonomously make and test changes to something measurable. Also trigger for requests to "set up an improvement loop", "run the autoresearch method", or anything involving iterative autonomous experimentation.

Use stronger lawful workflows for sites the user is authorized to access, including local browser login, session-aware browsing, JS-heavy pages, and post-login extraction. Do not bypass access controls.

Find viral YouTube Shorts channels that started recently and are doing really well. Use when Abdullah asks to find shorts niches, find channels, research YouTube Shorts, or find me channels. Runs the youtube-research.js script with criteria (≤60 days old, ≥15M total views) and returns qualifying channels with links. Uses a subagent (2.5-flash-lite) to process results.