Total 58,005 skills
Showing 12 of 58005 skills
Complex research requiring deeper analysis, multi-step reasoning, and sophisticated source evaluation for technical, academic, or specialized domain queries needing expert-level analysis, high-stakes decisions, or multi-layered problem solving.
Autonomous sBTC yield hunting daemon — monitors wallet sBTC balance and automatically deposits to Zest Protocol when balance exceeds a configurable threshold. Only works on mainnet. Requires an unlocked wallet with sBTC balance and STX for transaction fees.
Track product champions for job changes and qualify their new companies against ICP. Takes a CSV of known champions (with LinkedIn URLs), creates a baseline snapshot via Apify enrichment, then detects when champions move to new companies. Scores new companies on a 0-4 ICP fit scale. Outputs a downloadable CSV of movers with qualification verdicts.
Help users integrate Runway video generation APIs (text-to-video, image-to-video, video-to-video)
Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review
ALWAYS use when working with RxJS Observables, operators, and reactive patterns in Angular applications.
Create a LaunchDarkly metric that measures what matters for an experiment or rollout. Use when the user wants to create a metric, track an event, measure page views, button clicks, conversion, latency, error rate, or any custom numeric or binary outcome. Instruments the event first when needed (including SDK setup and .env), then creates and verifies the metric.
Use korean-law-mcp first for Korean law lookups, and fall back to Beopmang when the primary service is unavailable.
Visual UI annotation tool for AI agents. Drop the React toolbar into any app — humans click elements and leave feedback, agents receive structured CSS selectors, bounding boxes, and React component trees to find exact code. Supports MCP watch-loop, platform-specific hooks (Claude Code / Codex / Gemini CLI / OpenCode), webhook delivery, and autonomous self-driving critique with agent-browser.
Anymail Finder platform help — email finder and verification tool with 97%+ delivery guarantee. Finds emails by person name, company/domain, decision-maker role, or LinkedIn URL, with bulk search up to 100K rows and a GeoLead Finder. Use when looking up emails by name and company, finding decision-maker emails by role, verifying emails, running bulk email searches, finding emails from LinkedIn URLs, or working with the Anymail Finder API. Do NOT use for cross-platform enrichment strategy (use /sales-enrich), email deliverability strategy (use /sales-deliverability), or prospect list strategy (use /sales-prospect-list).
SendPulse platform help — email marketing, Automation 360, chatbots (WhatsApp/Instagram/Telegram/Facebook/Viber/TikTok), CRM, online course builder (EDU), website/landing page builder, web push notifications, SMS campaigns, Viber campaigns, SMTP/transactional email, pop-ups, email verifier, API. Use when asking 'how do I do X in SendPulse', setting up SendPulse email campaigns, configuring SendPulse automations, building SendPulse chatbots, managing SendPulse CRM deals, creating SendPulse courses, building SendPulse landing pages, SendPulse web push, SendPulse SMS, SendPulse pop-ups, or troubleshooting SendPulse. Do NOT use for general email marketing strategy (use /sales-email-marketing), general chatbot strategy (use /sales-chatbot), general SMS strategy (use /sales-sms-marketing), general push notification strategy (use /sales-push-notification), general funnel strategy (use /sales-funnel), or general course/membership strategy (use /sales-membership).
Converts an arxiv paper into a minimal, citation-anchored Python implementation. Trigger when user runs /paper2code with an arxiv URL or paper ID, says "implement this paper", or pastes an arxiv link asking for implementation. Flags all ambiguities honestly. Never invents implementation details not stated in the paper.